CN107943789A - Mood analysis method, device and the server of topic information - Google Patents
Mood analysis method, device and the server of topic information Download PDFInfo
- Publication number
- CN107943789A CN107943789A CN201711148609.3A CN201711148609A CN107943789A CN 107943789 A CN107943789 A CN 107943789A CN 201711148609 A CN201711148609 A CN 201711148609A CN 107943789 A CN107943789 A CN 107943789A
- Authority
- CN
- China
- Prior art keywords
- mood
- information
- word
- emotional intensity
- matched
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
- G06F40/216—Parsing using statistical methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The present invention provides mood analysis method, device and the server of topic information.This method includes:Extract the text message included in preset corpus in either objective topic information and at least one emoticon information;According to text message, matched in preset mood dictionary, to determine at least one mood word and the corresponding mood classification of each mood word that are matched in text message;Determine first emotional intensity of the text message in the mood classification matched, and second emotional intensity of at least one emoticon information in the mood classification matched;According to the first emotional intensity and the second emotional intensity, emotional intensity of the text message with symbol expression information in the identical mood classification matched in target topic information is determined.Compared with the prior art, the topic comment sentiment classification method that the embodiment of the present invention realizes text message and emoticon information is combined, is inclined to the mood of the topic information so as to more accurately analyze user.
Description
Technical field
The present invention relates to text mining, natural language processing field, and specifically, the present invention relates to the mood of topic information
Analysis method, device and server.
Background technology
As the progress of Internet technology and the quick of internet are popularized, number of network users sharp increase, social media,
The various network service forms for being capable of providing user's exchange such as shopping website, bring sharply increasing for user-generated content, this
A little contents include the personal view that user delivers consumer products, video display amusement, news and current affairs etc., have expressed a human feelings of user
Thread.Included by identifying in user comment it is positive, passive, detest, oppose etc. various mood, user can be better understood from
For specific topic, product, policy and the personal mood of popular personage, be conducive to personal, businessman and enterprise, improve Service Quality
Amount, improves personal and corporate image.
In the prior art to the analysis method of topic information, the method for being based primarily upon machine learning, realizes comment content
The analysis such as front and negative, commendation and derogatory sense, analysis granularity is bigger, does not reflect user to the topic exactly sometimes
Mood expressed by information.
Therefore, a kind of mood analysis method of topic information is needed at present, realizes and topic information is divided with carrying out fine granularity
Analysis, is inclined to the mood of the topic information so as to more accurately analyze user..
The content of the invention
In view of the foregoing, the present invention provides mood analysis method, device and the server of topic information, dialogue is realized
Topic information is analyzed with carrying out fine granularity, and the mood of the topic information is inclined to so as to analyze user exactly.
An embodiment of the present invention provides a kind of mood analysis method of topic information, including:
Extract the text message included in preset corpus in either objective topic information and at least one emoticon letter
Breath;
According to text message, matched in preset mood dictionary, to determine to match at least in text message
One mood word and the corresponding mood classification of each mood word;
Determine first emotional intensity of the text message in the mood classification matched, and at least one emoticon letter
Cease the second emotional intensity in the mood classification matched;
According to the first emotional intensity and the second emotional intensity, determine that text message is believed with symbol expression in target topic information
Cease the emotional intensity in the identical mood classification matched.
Preferably, according to text message, matched in preset mood dictionary, to determine to match in text message
At least one mood word and the corresponding mood classification of each mood word, including:
Cutting word processing is carried out to text message;
Each word in cutting word result is matched with the mood word in preset mood dictionary, determine matching into
The corresponding mood classification of mood word, mood word and emotional intensity of work(, include multiple mood words in preset mood dictionary
Language and the corresponding mood classification of each mood word and emotional intensity.
Preferably, cutting word processing is carried out to text message, further included:
Delete the stop words in cutting word result.
Preferably, text message is determined the first emotional intensity in the mood classification matched the step of, including:
Determine that each mood word for belonging to identical mood classification in the mood word of successful match is believed for target topic
The weight of breath;
Corresponded to according to each mood word for the weight of target topic information and each mood word determined
Emotional intensity, determine first emotional intensity of the text message in the mood classification matched.
Preferably, each mood word for determining to belong to identical mood classification in the mood word of successful match is for target
The weight of topic information, including:
Total word that the number that is occurred according to the mood word of any successful match in text message, cutting word result include
The number of the sum of the target topic information included in number and preset corpus, the target topic information comprising the mood word
Amount, determines weight of the mood word for target topic information.
Preferably, the step of second emotional intensity of at least one emoticon information in the mood classification matched is determined
Suddenly, including:
Determine the first mutual information of any mood classification matched and at least one emoticon information, and all
Second mutual information of the mood classification being fitted on and at least one emoticon information;
According to the first mutual information and the second mutual information, second of emoticon information in the mood classification matched is determined
Emotional intensity.
Preferably, any mood classification matched and the step of the first mutual information of at least one emoticon information are determined
Suddenly, including:
Any mood word included according to any mood classification matched and any expression symbolic information are in preset language
Expect storehouse in co-occurrence the frequency, and in preset corpus comprising the mood word target topic information quantity and include the table
The quantity of feelings symbolic information, determines the mutual information of the mood word and the emoticon information;
Believed respectively with least one emoticon according to each mood word included under any mood classification matched
The mutual information of breath, determines the first mutual information of any mood classification matched and at least one emoticon information.
Preferably, mood analysis method provided in an embodiment of the present invention further includes:
According to the emotional intensity of each target topic information in preset corpus, the emotional intensity of the preset corpus is determined
Distribution.
The embodiment of the present invention also provides a kind of mood analytical equipment of topic information, including:
Extraction unit, matching unit, the first determination unit, the second determination unit, wherein:
Extraction unit is used to extract the text message included in either objective topic information in preset corpus and at least one
A emoticon information;
Matching unit is used to, according to text message, be matched in preset mood dictionary, to determine in text message
At least one mood word and the corresponding mood classification of each mood word matched;
First determination unit is used to determine first emotional intensity of the text message in the mood classification matched, Yi Jizhi
Few second emotional intensity of the emoticon information in the mood classification matched;
Second determination unit is used for according to the first emotional intensity and the second emotional intensity, determines text in target topic information
Emotional intensity of the information with symbol expression information in the identical mood classification matched.
Preferably, matching unit is specifically used for:
Cutting word processing is carried out to text message;
Each word in cutting word result is matched with the mood word in preset mood dictionary, determine matching into
The corresponding mood classification of mood word, mood word and emotional intensity of work(, include multiple mood words in preset mood dictionary
Language and the corresponding mood classification of each mood word and emotional intensity.
Preferably, matching unit is additionally operable to:
Delete the stop words in cutting word result.
Preferably, the first determination unit is specifically used for:
Determine that each mood word for belonging to identical mood classification in the mood word of successful match is believed for target topic
The weight of breath;
Corresponded to according to each mood word for the weight of target topic information and each mood word determined
Emotional intensity, determine first emotional intensity of the text message in the mood classification matched.
Preferably, the first determination unit is specifically used for:
Total word that the number that is occurred according to the mood word of any successful match in text message, cutting word result include
The number of the sum of the target topic information included in number and preset corpus, the target topic information comprising the mood word
Amount, determines weight of the mood word for target topic information.
Preferably, the first determination unit is specifically used for:
Determine the first mutual information of any mood classification matched and at least one emoticon information, and all
Second mutual information of the mood classification being fitted on and at least one emoticon information;
According to the first mutual information and the second mutual information, second of emoticon information in the mood classification matched is determined
Emotional intensity.
Preferably, the first determination unit is specifically used for:
Any mood word included according to any mood classification matched and any expression symbolic information are in preset language
Expect storehouse in co-occurrence the frequency, and in preset corpus comprising the mood word target topic information quantity and include the table
The quantity of feelings symbolic information, determines the mutual information of the mood word and the emoticon information;
Believed respectively with least one emoticon according to each mood word included under any mood classification matched
The mutual information of breath, determines the first mutual information of any mood classification matched and at least one emoticon information.
Preferably, the 3rd determination unit is further included, the 3rd determination unit is used for:
According to the emotional intensity of each target topic information in preset corpus, the emotional intensity of the preset corpus is determined
Distribution.
The embodiment of the present invention also provides a kind of computer-readable recording medium, and meter is stored with computer-readable recording medium
Calculation machine program, the program realize method any one of provided in an embodiment of the present invention when being executed by processor.
The embodiment of the present invention also provides a kind of server, including memory and processor, and memory, which is used to store, includes journey
The information of sequence instruction, processor are used for the execution for controlling programmed instruction, realize that the present invention such as is implemented when program is executed by processor
The step of either method that example provides.
Had the beneficial effect that using what the embodiment of the present invention obtained:
In embodiments of the present invention, first extract the text message that is included in preset corpus in either objective topic information and
At least one emoticon information;According to text message, matched in preset mood dictionary, to determine in text message
The corresponding mood classification of at least one mood word and each mood word matched;Determine text message in the feelings matched
The first emotional intensity in thread classification, and second mood of at least one emoticon information in the mood classification matched
Intensity;According to the first emotional intensity and the second emotional intensity, text message and symbol expression information in target topic information are determined
Emotional intensity in the identical mood classification matched.Using the embodiment of the present invention in definite user for topic information
When mood is inclined to, mood analysis not only is carried out to the text message in topic information, also at least one table in topic information
Feelings symbolic information carries out mood analysis;It is strong by combining text message and the corresponding mood classification of emoticon information and mood
Degree, determines the mood classification and emotional intensity of topic information, i.e.,:Determine that user is inclined to the mood of the topic information.Phase
Than the topic comment tendentiousness point that in the prior art, the embodiment of the present invention realizes text message and emoticon information is combined
Analysis method, is inclined to the mood of the topic information so as to more accurately analyze user.
The additional aspect of the present invention and advantage will be set forth in part in the description, these will become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein:
Fig. 1 is a kind of flow diagram of the mood analysis method for topic information that the embodiment of the present invention 1 provides;
Fig. 2 is a kind of flow diagram for method for establishing emoticon mood storehouse that the embodiment of the present invention 1 provides;
Fig. 3 is a kind of flow diagram of the example of the mood analysis method for topic information that the embodiment of the present invention 1 provides;
Fig. 4 is a kind of structure diagram of the mood analytical equipment for topic information that the embodiment of the present invention 2 provides;
Fig. 5 is a kind of structure diagram for server that the embodiment of the present invention 3 provides.
Embodiment
The embodiment of the present invention is described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or has the function of same or like element.Below with reference to attached
The embodiment of figure description is exemplary, and is only used for explaining the present invention, and is not construed as limiting the claims.
Those skilled in the art of the present technique are appreciated that unless expressly stated, singulative " one " used herein, " one
It is a ", " described " and "the" may also comprise plural form.It is to be further understood that what is used in the specification of the present invention arranges
Diction " comprising " refer to there are the feature, integer, step, operation, element and/or component, but it is not excluded that in the presence of or addition
One or more other features, integer, step, operation, element, component and/or their groups.It should be understood that when we claim member
Part is " connected " or during " coupled " to another element, it can be directly connected or coupled to other elements, or there may also be
Intermediary element.In addition, " connection " used herein or " coupling " can include wireless connection or wireless coupling.It is used herein to arrange
Taking leave "and/or" includes whole or any cell and all combinations of one or more associated list items.
Those skilled in the art of the present technique are appreciated that unless otherwise defined, all terms used herein (including technology art
Language and scientific terminology), there is the meaning identical with the general understanding of the those of ordinary skill in fields of the present invention.Should also
Understand, those terms such as defined in the general dictionary, it should be understood that have with the context of the prior art
The consistent meaning of meaning, and unless by specific definitions as here, idealization or the implication of overly formal otherwise will not be used
To explain.
The technical solution of various embodiments of the present invention is specifically introduced below in conjunction with the accompanying drawings.
Embodiment 1
An embodiment of the present invention provides a kind of mood analysis method of topic information, flow diagram such as Fig. 1 of this method
It is shown, specifically include following steps:
S101:Extract the text message included in preset corpus in either objective topic information and at least one emoticon
Number information;
S102:According to text message, matched in preset mood dictionary, to determine what is matched in text message
At least one mood word and the corresponding mood classification of each mood word;
S103:Determine first emotional intensity of the text message in the mood classification matched, and at least one expression
Second emotional intensity of the symbolic information in the mood classification matched;
S104:According to the first emotional intensity and the second emotional intensity, text message and symbol in target topic information are determined
Emotional intensity of the expression information in the identical mood classification matched.
Using the embodiment of the present invention when determining that mood of the user for topic information is inclined to, not only in topic information
Text message carries out mood analysis, also carries out mood analysis at least one emoticon information in topic information;Pass through knot
Text message and the corresponding mood classification of emoticon information and emotional intensity are closed, determines the mood classification and feelings of topic information
Thread intensity, i.e.,:Determine that user is inclined to the mood of the topic information.Compared with the prior art, the embodiment of the present invention realizes
The topic comment sentiment classification method that text message and emoticon information are combined, so as to more accurately analyze user
The mood of the topic information is inclined to.
The specific implementation of each step is described further below for more than:
S101:Extract the text message included in preset corpus in either objective topic information and at least one emoticon
Number information.
For this step, corpus is first obtained, target topic information is included in the corpus, for example, the topic is believed
Breath can be comment information of the user for event or commodity etc..The specific method for obtaining corpus has many kinds, for example, can be with
By web crawlers technology in news website, forum and the target topic information in relation to being captured in application platform.
In a kind of specific embodiment, by the relevant comment information of all topics from Hbase (distributed data base)
In be retrieved, and by kafka (Distributed Message Queue) for following topic informations mood analysis input data is provided.Tool
Body, topic index library unit stores the unique index of all topics, such as topic_001, topic_002, topic index
Stock is placed on home server, can be by traveling through the topic index database after analysis task of topic information is initiated, will be all
Topic and topic comment information are all taken out from Hbase, according to specific format (for example, JSON forms) tissue and deposit in
In kafka message queues.
In a preferred embodiment, after target topic information is obtained, to the target topic information duplicate removal, example
Such as, for some topic, same user may deliver a plurality of identical comment information, only retain one that the user delivers and comment
By information.Preferably, after to target topic information duplicate removal, then the noise information in target topic information is removed, noise letter
Breath includes:Character of theme label, URL (Uniform Resource Locator, universal resource locator) or repetition etc..
Obtaining the corresponding corpus of target topic information (i.e.:Preset corpus) after, identify each target topic information
In emoticon information, and extract the emoticon information, normally left content is just corresponding for the target topic information
Text message.The method of identification emoticon information can identify the mark of emoticon information, for example, can pass through identification
With the character string of " [" starts, with "] " ending, which is emoticon information.
As shown in table 1, it is assumed that target topic information is " Chinese common people will arrive at the time of most exciting over 5 years
![applause] [applause] [applause] [applause] ", extracts emoticon information in the target topic information.Result after processing is:
Text message is " Chinese common people will come finally at the time of most exciting over 5 years!", emoticon information is " [applause]
[applause] [applause] [applause] ".
Table 1
S102:According to text message, matched in preset mood dictionary, to determine what is matched in text message
At least one mood word and the corresponding mood classification of each mood word.
In this step, to S101 extraction text message carry out cutting word, by each word in cutting word result with it is preset
Mood dictionary in mood word matched, determine the corresponding mood classification of the mood word of successful match, mood word
And emotional intensity.
For the embodiment of the present invention, when by the mood word in each word in cutting word result and preset mood dictionary
When being matched, if there are the word of successful match, following S103 and S104 are continued to execute;If without successful match
Word, then processing step is no longer performed to the corresponding target topic information of text information.
It is the content in preset mood dictionary as shown in table 2, which specifically includes multiple mood words and each feelings
The corresponding mood classification of thread word and emotional intensity, for example, shown in table 2, in mood dictionary, the mood of mood word " happy "
Classification is " actively health ", and corresponding emotional intensity is " 90 " under the mood classification.Table 2 is only exemplary explanation base
The content that plinth mood dictionary is included, in practical applications, the content included in basic mood dictionary may it is more complicated,
Comprehensively, the embodiment of the present invention is not especially limited this.
Table 2
Mood word | Mood classification | Emotional intensity |
It is happy | Actively health | 90 |
Happiness | Actively health | 85 |
It is sad | It is dull passive | 90 |
It is unhappy | It is dull passive | 85 |
Each word in cutting word result is matched with each mood word in mood dictionary, determines text envelope
At least one mood word and each mood word matched in breath corresponding mood classification in mood dictionary.
S103:Determine first emotional intensity of the text message in the mood classification matched, and at least one expression
Second emotional intensity of the symbolic information in the mood classification matched.
In this step, determining the method for first emotional intensity of the text message in the mood classification matched includes:
Determine weight of each mood word for target topic information for belonging to identical mood classification in the mood word of successful match;
It is strong for the weight of target topic information and the corresponding mood of each mood word determined according to each mood word
Degree, determines first emotional intensity of the text message in the mood classification matched.
For example, text message to be matched is " the attitude let us admiration that your sincerity is endured hardships!It is but not complete enough in terms of XX
It is kind, it is desirable to which that you correct!", it is assumed that text information and the mood word of successful match in preset mood dictionary include:It is " sincere resistance to
Labor ", " admiration ", " not perfect enough " " correction ".Known by mood dictionary:" sincerity is endured hardships " and " admiration " belongs to identical mood class
Not, " not perfect enough " and " correction " belongs to identical mood classification.
Table 3
Mood word | Mood classification | Emotional intensity |
Sincerity is endured hardships | Commendation | 90 |
Admiration | Commendation | 85 |
It is not perfect enough | Derogatory sense | 80 |
Correction | Derogatory sense | 85 |
Specifically, belong in the mood word of above-mentioned definite successful match each mood word of identical mood classification for
The weight method of the target topic information is:Time occurred according to the mood word of any successful match in text message
The sum of the target topic information included in number, total word number for including of cutting word result and preset corpus, comprising the mood
The quantity of the target topic information of word, determines weight of the mood word for target topic information.
In one embodiment, each feelings for belonging to identical mood classification in the mood word of any successful match are calculated
Thread word is as follows for the formula of the weight of target topic information:
Wherein, k (w) represents the mood word of any successful match for the weight of target topic information, tf-id (w) tables
Show the mood word relative to text message (i.e.:The corresponding text message of wall scroll target information) importance, point in formula
Son for the mood word relative to the importance of text information logarithm, denominator for successful match mood word in relative to
The maximum of the logarithm of the importance of text information.
Tf-idf (w)=tf (w) × idf (w) (4)
Wherein, n (w) is expressed as the number that the mood word of any successful match occurs in text information, N (w) tables
Total word number that cutting word result includes is shown as, D (w) is expressed as the sum of the target topic information included in preset corpus, d
(w) it is expressed as the quantity of the target topic information comprising the mood word.
Calculated by above-mentioned formula 2,3 and 4 with belonging to identical mood class in the mood word of mood dictionary successful match
Other each mood word relative to text message importance, and then by formula 1 calculate the mood word for target talk about
Inscribe the weight of information.
After each mood word for belonging to identical mood classification is calculated for the weight of target topic information, according to this
Weight and the corresponding emotional intensity of each mood word that determines are (i.e.:Each mood word is strong in mood dictionary
Degree), determine emotional intensity (first emotional intensity) of the text information in the mood classification matched.
In one embodiment, emotional intensity of the mood word of any successful match in text information is calculated
Formula is as follows:
Wherein, Score (w) represents emotional intensity of the mood word of any successful match in text information,Represent weight of the mood word for the target topic information, score (w) represents the mood word
Emotional intensity of the language in mood dictionary.
In a kind of specific embodiment, by with belonging to identical mood class in the mood word of mood dictionary successful match
Other each mood word is summed for the weight of target topic information, obtains text information in the mood class matched
Emotional intensity (the first emotional intensity) on not, specific formula is as follows:
P(ci)=sum { Score (w), w ∈ c (w) } (6)
Wherein, P (ci) represent that text information belongs to mood classification ciEmotional intensity, i.e.,:Represent to belong in text message
Classification ciEach mood word emotional intensity superposition.
Example in reference list 3, it is assumed that calculate the emotional intensity that text information belongs to mood classification " commendation ", then pass through
The emotional intensity of " sincerity is endured hardships " and " admiration " under mood classification " commendation " is obtained in mood dictionary, i.e.,:Emotional intensity point
Wei 90 and 85.If " sincerity is endured hardships " and " admiration " is respectively 0.9 and 0.6 in the weight for the target topic information, it is somebody's turn to do
The emotional intensity that text message belongs to mood classification " commendation " is 90 × 0.9+85 × 0.6.
In embodiments of the present invention, determine at least one emoticon information in target topic information in the feelings matched
The second emotional intensity in thread classification, can first look into from the preset corresponding mood storehouse of emoticon (emoticon mood storehouse)
Find out corresponding second emotional intensity of the emoticon information;Emoticon mood stock contains multiple emoticon information pair
The mood classification and the emotional intensity under each mood classification answered;If there is no the expression in preset emoticon mood storehouse
Symbolic information, can use following methods for determining the second emotional intensity.
At least one emoticon information in definite target topic information provided in an embodiment of the present invention is matching
The method of the second emotional intensity in mood classification is:Determine that any mood classification matched is believed with least one emoticon
First mutual information of breath, and the second mutual information of all mood classifications matched and at least one emoticon information;Root
According to the first mutual information and the second mutual information, second emotional intensity of the emoticon information in the mood classification matched is determined.
In a kind of specific embodiment, any mood classification matched and at least one emoticon information are determined
The method of the first mutual information include:Any mood word and any emoticon included according to any mood classification matched
The frequency of number information co-occurrence in preset corpus, and the target topic information comprising the mood word in preset corpus
Quantity and the quantity for including the emoticon information, determine the mutual information of the mood word and the emoticon information;According to appoint
The each mood word included under the one mood classification matched the mutual information with least one emoticon information respectively, determines
First mutual information of the mood classification matched and at least one emoticon information.
In one embodiment, any mood word and the expression that any mood classification matched includes are calculated
The formula of the mutual information of symbolic information is as follows:
Wherein, p (w, etag) is expressed as the mutual information of any mood word w and an emoticon information etag, freq
(w, etag) represents the frequency of the mood word and emoticon information co-occurrence in preset corpus, and freq (w) represents pre-
The quantity of the target topic information comprising the mood word in corpus is put, freq (etag) is represented to include in preset corpus and is somebody's turn to do
The quantity of emoticon information.
Calculate and determine that any mood classification matched and the formula of the first mutual information of an emoticon information are:
Calculate all mood classifications matched and the formula of the second mutual information of an emoticon information is:
Calculate the formula of emotional intensity (second emotional intensity) of the expression symbolic information in the mood classification matched such as
Under:
In practical applications, multiple and different emoticon information may be included in a topic information, for example, it is assumed that
Topic information is " Chinese common people will come finally at the time of most exciting over 5 years![happy] [applause] [happiness] [is sung
Song] ", emoticon information wherein included is " [happy] ", " [applause] ", " [happiness] ", " [singing] ".For this feelings
Shape, can first calculate emotional intensity of each emoticon information in the mood classification matched;By counting each expression
Emotional intensity of the symbolic information in identical mood classification, determines second mood of all emoticons in identical mood classification
Intensity.
For example, can directly be superimposed emotional intensity of each emoticon information in identical mood classification, determine
Second emotional intensity of all emoticons in identical mood classification.Merely just enumerate a kind of the second mood of simple acquisition
The method of intensity, in practical applications, the method that relative complex the second emotional intensity of calculating can be arranged as required to, this hair
Bright embodiment is not especially limited this.
Above formula 1~6 and 7~9 simply exemplarily illustrates a kind of definite text message in the mood classification matched
On the first emotional intensity, and the method for second emotional intensity of the emoticon information in the mood classification matched.Base
In the other methods that the thinking provided in an embodiment of the present invention for determining the first emotional intensity and the second emotional intensity is created, belong to
Within protection scope of the present invention.
S104:According to the first emotional intensity and the second emotional intensity, text message and symbol in target topic information are determined
Emotional intensity of the expression information in the identical mood classification matched.
For this step, in one embodiment, according to the first emotional intensity and the second emotional intensity, target words are calculated
The formula of emotional intensity of the text message with symbol expression information in the identical mood classification matched is in topic information:
Wherein, f (cj) represent topic information in mood classification cjOn emotional intensity, p1 (cj)、p2(cj) represent single respectively
The text message and emoticon information of bar target topic information are in mood classification cjOn emotional intensity.
Text message and emoticon information in wall scroll target topic information is determined, with being matched in mood dictionary
Mood classification under emotional intensity after, according to the emotional intensity of each target topic information in preset corpus, determine that this is pre-
Put the emotional intensity distribution of corpus.
For example, it is assumed that 100 user comment informations on same subject are stored with preset corpus, every comment letter
The comment information and emotional intensity under the mood classification matched in mood dictionary are all determined in breath.By counting this 100
Comment information emotional intensity under each identical mood classification, determines that the emotional intensity on the theme is distributed.
As shown in table 4, by being counted to emotional intensity of 100 comment informations under each identical mood classification, obtain
Average emotional intensity of the user to the topic information under each mood classification.By analyzing the comment information under each mood classification
Bar number, user obtain the emotional intensity distribution that this 100 comment informations correspond to corpus to the average emotional intensity of the topic.
Table 4
Mood classification | Comment on bar number | Average emotional intensity |
Commendation | 60 | 85 |
Derogatory sense | 20 | 40 |
It is neutral | 20 | 20 |
The embodiment of the present invention also provides a kind of method for establishing emoticon mood storehouse, and the flow diagram of this method is as schemed
Shown in 2, following steps are specifically included:
S201:Obtain the emoticon information in preset corpus;
S202:Remove repeat and comprising noise emoticon information;
S203:The frequency of use of each emoticon information included in the preset corpus is counted, chooses frequency of use
The emoticon information of preset value is put into emoticon mood storehouse before sequence;
S204:Calculate the mutual information of each mood word in emoticon and preset mood dictionary, and emoticon and really
The mutual information of classification is determined, to determine the mood classification and emotional intensity of each emoticon;
S205:The mood classification and emotional intensity of emoticon are stored into emoticon mood storehouse.
Above S201~S205 is only exemplary the method that explanation establishes emoticon mood storehouse, in practical applications,
Also a variety of method for building up, the embodiment of the present invention limit this without specific.
In order to clearly illustrate the embodiment of the present invention, illustrate implementation of the present invention below by a complete example
Example, the flow chart of the example is as shown in figure 3, specifically include following steps:S301:The retrieval from Hbase (distributed data base)
Out target topic information, and by kafka (Distributed Message Queue) input is provided for the mood analysis of target topic information
Data (target topic information);
S302:After target topic information is received, remove the target topic information of repetition, then remove the target after duplicate removal
Noise information in topic information;
S303:The text message included in extraction either objective topic information and at least one emoticon information;
S304:According to text message, matched in preset mood dictionary, to determine what is matched in text message
At least one mood word and the corresponding mood classification of each mood word;
S305:Cutting word processing is carried out to text message, obtains cutting word result;
S306:Delete the stop words in cutting word result;
S307:Each word in cutting word result is matched with each mood word in mood dictionary, is determined
At least one mood word and each mood word matched in text message corresponding mood class in mood dictionary
Not;
S308:Determine first emotional intensity of the text message in the mood classification matched, and at least one expression
Second emotional intensity of the symbolic information in the mood classification matched;
S309:According to the first emotional intensity and the second emotional intensity, text message and symbol in target topic information are determined
Emotional intensity of the expression information in the identical mood classification matched;
S310:Text message and emoticon information in wall scroll target topic information is determined, with mood dictionary
After emotional intensity under the mood classification matched, according to the emotional intensity of each target topic information in preset corpus, really
The emotional intensity distribution of the fixed preset corpus.
Embodiment 2
Based on identical inventive concept, the embodiment of the present invention provides a kind of mood analytical equipment of topic information, the device
Structure diagram as shown in figure 4, the device is specifically included with lower unit:
Extraction unit 401, matching unit 402, the first determination unit 403, the second determination unit 404, wherein:
Extraction unit 401 is used to extracting the text message that is included in preset corpus in either objective topic information and at least
One emoticon information;
Matching unit 402 is used to, according to text message, be matched in preset mood dictionary, to determine text message
In at least one mood word for matching and the corresponding mood classification of each mood word;
First determination unit 403 is used to determine first emotional intensity of the text message in the mood classification matched, with
And second emotional intensity of at least one emoticon information in the mood classification matched;
Second determination unit 404 is used for according to the first emotional intensity and the second emotional intensity, determines in target topic information
Emotional intensity of the text message with symbol expression information in the identical mood classification matched.
The specific workflow of present apparatus embodiment is:First, extraction unit 401 extracts either objective in preset corpus
The text message included in topic information and at least one emoticon information;Matching unit 402 is according to text information, pre-
Matched in the mood dictionary put, with least one mood word matched in definite text information and each feelings
The corresponding mood classification of thread word;First determination unit 403 determines first of text information in the mood classification matched
Emotional intensity, and second emotional intensity of the emoticon information in the mood classification matched;Second determination unit 404
According to the first emotional intensity and the second emotional intensity, determine that text message is being matched with symbol expression information in target topic information
To identical mood classification on emotional intensity.
Using the embodiment of the present invention when determining that mood of the user for topic information is inclined to, not only in topic information
Text message carries out mood analysis, also carries out mood analysis at least one emoticon information in topic information;Pass through knot
Text message and the corresponding mood classification of emoticon information and emotional intensity are closed, determines the mood classification and feelings of topic information
Thread intensity, i.e.,:User is inclined to the mood of the topic information.Compared with the prior art, the embodiment of the present invention realizes text envelope
The topic comment sentiment classification method that breath and emoticon information are combined, so as to more accurately analyze user to the words
Inscribe the mood tendency of information.
Present apparatus embodiment realizes that the mode for the mood for determining topic information has many kinds, for example, in the first embodiment party
In formula, matching unit 402 is specifically used for:
Cutting word processing is carried out to text message;
Each word in cutting word result is matched with the mood word in preset mood dictionary, determine matching into
The corresponding mood classification of mood word, mood word and emotional intensity of work(, include multiple mood words in preset mood dictionary
Language and the corresponding mood classification of each mood word and emotional intensity.
In second of embodiment, matching unit 402 is additionally operable to:
Delete the stop words in cutting word result.
In the third embodiment, the first determination unit 403 is specifically used for:
Determine that each mood word for belonging to identical mood classification in the mood word of successful match is believed for target topic
The weight of breath;
Corresponded to according to each mood word for the weight of target topic information and each mood word determined
Emotional intensity, determine first emotional intensity of the text message in the mood classification matched.
In the 4th kind of embodiment, the first determination unit 403 is specifically used for:
Total word that the number that is occurred according to the mood word of any successful match in text message, cutting word result include
The number of the sum of the target topic information included in number and preset corpus, the target topic information comprising the mood word
Amount, determines weight of the mood word for target topic information.
In the 5th kind of embodiment, the first determination unit 403 is specifically used for:
Determine the first mutual information of any mood classification matched and at least one emoticon information, and all
Second mutual information of the mood classification being fitted on and at least one emoticon information;
According to the first mutual information and the second mutual information, second of emoticon information in the mood classification matched is determined
Emotional intensity.
In the 6th kind of embodiment, the first determination unit 403 is specifically used for:
Any mood word included according to any mood classification matched and any expression symbolic information are in preset language
Expect storehouse in co-occurrence the frequency, and in preset corpus comprising the mood word target topic information quantity and include the table
The quantity of feelings symbolic information, determines the mutual information of the mood word and the emoticon information;
Believed respectively with least one emoticon according to each mood word included under any mood classification matched
The mutual information of breath, determines the first mutual information of any mood classification matched and at least one emoticon information.
In the 7th kind of embodiment, mood analytical equipment provided in an embodiment of the present invention further includes the 3rd determination unit,
3rd determination unit is used for:
According to the emotional intensity of each target topic information in preset corpus, the emotional intensity of the preset corpus is determined
Distribution.
Embodiment 3
Based on identical inventive concept, the embodiment of the present invention provides a kind of computer-readable recording medium, which can
Read to be stored with computer program on storage medium, at least one program realizes following steps when being executed by processor:
Extract the text message included in preset corpus in either objective topic information and at least one emoticon letter
Breath;
According to text message, matched in preset mood dictionary, to determine to match at least in text message
One mood word and the corresponding mood classification of each mood word;
Determine first emotional intensity of the text message in the mood classification matched, and at least one emoticon letter
Cease the second emotional intensity in the mood classification matched;
According to the first emotional intensity and the second emotional intensity, determine that text message is believed with symbol expression in target topic information
Cease the emotional intensity in the identical mood classification matched.
Preferably, at least one program is used for realization:
Cutting word processing is carried out to text message;
Each word in cutting word result is matched with the mood word in preset mood dictionary, determine matching into
The corresponding mood classification of mood word, mood word and emotional intensity of work(, include multiple mood words in preset mood dictionary
Language and the corresponding mood classification of each mood word and emotional intensity.
Preferably, at least one program is used for realization:
Delete the stop words in cutting word result.
Preferably, at least one program is used for realization:
Determine that each mood word for belonging to identical mood classification in the mood word of successful match is believed for target topic
The weight of breath;
Corresponded to according to each mood word for the weight of target topic information and each mood word determined
Emotional intensity, determine first emotional intensity of the text message in the mood classification matched.
Preferably, at least one program is used for realization:
Total word that the number that is occurred according to the mood word of any successful match in text message, cutting word result include
The number of the sum of the target topic information included in number and preset corpus, the target topic information comprising the mood word
Amount, determines weight of the mood word for target topic information.
Preferably, at least one program is used for realization:
Determine the first mutual information of any mood classification matched and at least one emoticon information, and all
Second mutual information of the mood classification being fitted on and at least one emoticon information;
According to the first mutual information and the second mutual information, second of emoticon information in the mood classification matched is determined
Emotional intensity.
Preferably, at least one program is used for realization:
Any mood word included according to any mood classification matched and any expression symbolic information are in preset language
Expect storehouse in co-occurrence the frequency, and in preset corpus comprising the mood word target topic information quantity and include the table
The quantity of feelings symbolic information, determines the mutual information of the mood word and the emoticon information;
Believed respectively with least one emoticon according to each mood word included under any mood classification matched
The mutual information of breath, determines the first mutual information of any mood classification matched and at least one emoticon information.
Preferably, at least one program is used for realization:
According to the emotional intensity of each target topic information in preset corpus, the emotional intensity of the preset corpus is determined
Distribution.
The embodiment of the present invention also provides a kind of server, and the structure diagram of the server is as shown in figure 5, including reservoir
501 and processor 502, memory 501 is used to store the information for including programmed instruction, and processor 502 is for controlling programmed instruction
Execution, program realizes the construction method of any Knowledge Organization System provided in an embodiment of the present invention when being performed by processor 502
The step of.
Specifically, at least one program stored in memory 501 is used to realize following steps when being performed by processor 502
Suddenly:
Extract the text message included in preset corpus in either objective topic information and at least one emoticon letter
Breath;
According to text message, matched in preset mood dictionary, to determine to match at least in text message
One mood word and the corresponding mood classification of each mood word;
Determine first emotional intensity of the text message in the mood classification matched, and at least one emoticon letter
Cease the second emotional intensity in the mood classification matched;
According to the first emotional intensity and the second emotional intensity, determine that text message is believed with symbol expression in target topic information
Cease the emotional intensity in the identical mood classification matched.
Preferably, at least one program is used for realization:
Cutting word processing is carried out to text message;
Each word in cutting word result is matched with the mood word in preset mood dictionary, determine matching into
The corresponding mood classification of mood word, mood word and emotional intensity of work(, include multiple mood words in preset mood dictionary
Language and the corresponding mood classification of each mood word and emotional intensity.
Preferably, at least one program is used for realization:
Delete the stop words in cutting word result.
Preferably, at least one program is used for realization:
Determine that each mood word for belonging to identical mood classification in the mood word of successful match is believed for target topic
The weight of breath;
Corresponded to according to each mood word for the weight of target topic information and each mood word determined
Emotional intensity, determine first emotional intensity of the text message in the mood classification matched.
Preferably, at least one program is used for realization:
Total word that the number that is occurred according to the mood word of any successful match in text message, cutting word result include
The number of the sum of the target topic information included in number and preset corpus, the target topic information comprising the mood word
Amount, determines weight of the mood word for target topic information.
Preferably, at least one program is used for realization:
Determine the first mutual information of any mood classification matched and at least one emoticon information, and all
Second mutual information of the mood classification being fitted on and at least one emoticon information;
According to the first mutual information and the second mutual information, second of emoticon information in the mood classification matched is determined
Emotional intensity.
Preferably, at least one program is used for realization:
Any mood word included according to any mood classification matched and any expression symbolic information are in preset language
Expect storehouse in co-occurrence the frequency, and in preset corpus comprising the mood word target topic information quantity and include the table
The quantity of feelings symbolic information, determines the mutual information of the mood word and the emoticon information;
Believed respectively with least one emoticon according to each mood word included under any mood classification matched
The mutual information of breath, determines the first mutual information of any mood classification matched and at least one emoticon information.
Preferably, at least one program is used for realization:
According to the emotional intensity of each target topic information in preset corpus, the emotional intensity of the preset corpus is determined
Distribution.
The beneficial effect obtained using computer-readable recording medium provided in an embodiment of the present invention and server, it is and preceding
The beneficial effect that the embodiment of the method or device embodiment stated are obtained is same or like, this is repeated no more.
Those skilled in the art of the present technique are appreciated that the present invention includes being related to for performing in operation described herein
One or more equipment.These equipment can specially be designed and manufactured for required purpose, or can also be included general
Known device in computer.These equipment have the computer program being stored in it, these computer programs are optionally
Activation or reconstruct.Such computer program can be stored in equipment (for example, computer) computer-readable recording medium or be stored in
E-command and it is coupled to respectively in any kind of medium of bus suitable for storage, the computer-readable medium is included but not
Be limited to any kind of disk (including floppy disk, hard disk, CD, CD-ROM and magneto-optic disk), ROM (Read-Only Memory, only
Read memory), RAM (Random Access Memory, immediately memory), EPROM (Erasable Programmable
Read-Only Memory, Erarable Programmable Read only Memory), EEPROM (Electrically Erasable
Programmable Read-Only Memory, Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic card or light card
Piece.It is, computer-readable recording medium includes by equipment (for example, computer) so as to any Jie for the form storage or transmission information read
Matter.
Those skilled in the art of the present technique be appreciated that can with computer program instructions come realize these structure charts and/or
The combination of each frame and these structure charts and/or the frame in block diagram and/or flow graph in block diagram and/or flow graph.This technology is led
Field technique personnel be appreciated that these computer program instructions can be supplied to all-purpose computer, special purpose computer or other
The processor of programmable data processing method is realized, so that the processing by computer or other programmable data processing methods
Device performs the scheme specified in the frame of structure chart and/or block diagram and/or flow graph disclosed by the invention or multiple frames.
Those skilled in the art of the present technique are appreciated that in the various operations discussed in the present invention, method, flow
Steps, measures, and schemes can be replaced, changed, combined or be deleted.Further, it is each with having been discussed in the present invention
Other steps, measures, and schemes in kind operation, method, flow may also be alternated, changed, rearranged, decomposed, combined or deleted.
Further, it is of the prior art to have and the step in the various operations disclosed in the present invention, method, flow, measure, scheme
It may also be alternated, changed, rearranged, decomposed, combined or deleted.
The above is only some embodiments of the present invention, it is noted that for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications also should
It is considered as protection scope of the present invention.
Claims (18)
- A kind of 1. mood analysis method of topic information, it is characterised in that including:Extract the text message included in preset corpus in either objective topic information and at least one emoticon information;According to the text message, matched in preset mood dictionary, to determine what is matched in the text message At least one mood word and the corresponding mood classification of each mood word;Determine first emotional intensity of the text message in the mood classification matched, and at least one emoticon Number second emotional intensity of the information in the mood classification matched;According to first emotional intensity and the second emotional intensity, text message and symbol table in the target topic information are determined Emotional intensity of the feelings information in the identical mood classification matched.
- 2. mood analysis method according to claim 1, it is characterised in that it is described according to the text message, preset Mood dictionary in matched, to determine at least one mood word for matching and each feelings in the text message The corresponding mood classification of thread word, including:Cutting word processing is carried out to the text message;Each word in cutting word result is matched with the mood word in preset mood dictionary, determines successful match The corresponding mood classification of mood word, mood word and emotional intensity, include multiple mood words in the preset mood dictionary Language and the corresponding mood classification of each mood word and emotional intensity.
- 3. mood analysis method according to claim 2, it is characterised in that described to be carried out to the text message at cutting word Reason, further includes:Delete the stop words in cutting word result.
- 4. mood analysis method according to claim 1, it is characterised in that described to determine that the text message is matching Mood classification on the first emotional intensity the step of, including:Determine that each mood word for belonging to identical mood classification in the mood word of successful match is believed for the target topic The weight of breath;According to each mood word for the weight of the target topic information and each mood determined The corresponding emotional intensity of word, determines first emotional intensity of the text message in the mood classification matched.
- 5. mood analysis method according to claim 4, it is characterised in that in the mood word of the definite successful match Belong to weight of each mood word for the target topic information of identical mood classification, including:The number that is occurred according to the mood word of any successful match in the text message, the cutting word result include Sum, the target topic comprising the mood word of the target topic information included in total word number and the preset corpus The quantity of information, determines weight of the mood word for the target topic information.
- 6. mood analysis method according to claim 1, it is characterised in that described to determine at least one emoticon Information the second emotional intensity in the mood classification matched the step of, including:Determine the first mutual information of any mood classification matched and at least one emoticon information, and all Second mutual information of the mood classification being fitted on and at least one emoticon information;According to the first mutual information and the second mutual information, second of the emoticon information in the mood classification matched is determined Emotional intensity.
- 7. mood analysis method according to claim 6, it is characterised in that described to determine any mood classification matched The step of with the first mutual information of at least one emoticon information, including:Any mood word included according to any mood classification matched and any expression symbolic information are in the preset language Expect storehouse in co-occurrence the frequency, and in the preset corpus comprising the mood word target topic information quantity and comprising The quantity of the emoticon information, determines the mutual information of the mood word and the emoticon information;According to each mood word included under any mood classification matched respectively with least one emoticon information Mutual information, determines the first mutual information of any mood classification matched and at least one emoticon information.
- 8. mood analysis method according to claim 1, it is characterised in that further include:According in the preset corpus The emotional intensity of each target topic information, determines the emotional intensity distribution of the preset corpus.
- A kind of 9. mood analytical equipment of topic information, it is characterised in that including:Extraction unit, matching unit, the first determination unit, the second determination unit, wherein:The extraction unit is used to extract the text message included in either objective topic information in preset corpus and at least one A emoticon information;The matching unit is used to, according to the text message, be matched in preset mood dictionary, to determine the text At least one mood word and the corresponding mood classification of each mood word matched in this information;First determination unit is used to determine first emotional intensity of the text message in the mood classification matched, with And second emotional intensity of at least one emoticon information in the mood classification matched;Second determination unit is used for according to first emotional intensity and the second emotional intensity, determines the target topic letter Emotional intensity of the text message with symbol expression information in the identical mood classification matched in breath.
- 10. mood analytical equipment according to claim 9, it is characterised in that the matching unit is specifically used for:Cutting word processing is carried out to the text message;Each word in cutting word result is matched with the mood word in preset mood dictionary, determines successful match The corresponding mood classification of mood word, mood word and emotional intensity, include multiple mood words in the preset mood dictionary Language and the corresponding mood classification of each mood word and emotional intensity.
- 11. mood analytical equipment according to claim 10, it is characterised in that the matching unit is additionally operable to:Delete the stop words in cutting word result.
- 12. mood analytical equipment according to claim 9, it is characterised in that first determination unit is specifically used for:Determine that each mood word for belonging to identical mood classification in the mood word of successful match is believed for the target topic The weight of breath;According to each mood word for the weight of the target topic information and each mood determined The corresponding emotional intensity of word, determines first emotional intensity of the text message in the mood classification matched.
- 13. mood analytical equipment according to claim 11, it is characterised in that first determination unit is specifically used for:The number that is occurred according to the mood word of any successful match in the text message, the cutting word result include Sum, the target topic comprising the mood word of the target topic information included in total word number and the preset corpus The quantity of information, determines weight of the mood word for the target topic information.
- 14. mood analytical equipment according to claim 9, it is characterised in that first determination unit is specifically used for:Determine the first mutual information of any mood classification matched and at least one emoticon information, and all Second mutual information of the mood classification being fitted on and at least one emoticon information;According to the first mutual information and the second mutual information, second of the emoticon information in the mood classification matched is determined Emotional intensity.
- 15. mood analytical equipment according to claim 14, it is characterised in that first determination unit is specifically used for:Any mood word included according to any mood classification matched and any expression symbolic information are in the preset language Expect storehouse in co-occurrence the frequency, and in the preset corpus comprising the mood word target topic information quantity and comprising The quantity of the emoticon information, determines the mutual information of the mood word and the emoticon information;According to each mood word included under any mood classification matched respectively with least one emoticon information Mutual information, determines the first mutual information of any mood classification matched and at least one emoticon information.
- 16. mood analytical equipment according to claim 9, it is characterised in that further include the 3rd determination unit, the described 3rd Determination unit is used for:According to the emotional intensity of each target topic information in the preset corpus, the emotional intensity of the preset corpus is determined Distribution.
- 17. a kind of computer-readable recording medium, it is characterised in that be stored with computer on the computer-readable recording medium Program, the program realize the method any one of claim 1-8 when being executed by processor.
- 18. a kind of server, including memory and processor, the memory is used to store the information for including programmed instruction, institute State the execution that processor is used to control programmed instruction, it is characterised in that realize that right such as will when program is performed by the processor The step of seeking 1-8 any the methods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711148609.3A CN107943789A (en) | 2017-11-17 | 2017-11-17 | Mood analysis method, device and the server of topic information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711148609.3A CN107943789A (en) | 2017-11-17 | 2017-11-17 | Mood analysis method, device and the server of topic information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107943789A true CN107943789A (en) | 2018-04-20 |
Family
ID=61931850
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711148609.3A Pending CN107943789A (en) | 2017-11-17 | 2017-11-17 | Mood analysis method, device and the server of topic information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107943789A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109325124A (en) * | 2018-09-30 | 2019-02-12 | 武汉斗鱼网络科技有限公司 | A kind of sensibility classification method, device, server and storage medium |
CN109829157A (en) * | 2019-01-21 | 2019-05-31 | 三角兽(北京)科技有限公司 | Text mood rendering method, text mood presentation device and storage medium |
CN110069601A (en) * | 2019-04-03 | 2019-07-30 | 平安科技(深圳)有限公司 | Mood determination method and relevant apparatus |
CN110189742A (en) * | 2019-05-30 | 2019-08-30 | 芋头科技(杭州)有限公司 | Determine emotion audio, affect display, the method for text-to-speech and relevant apparatus |
CN110858099A (en) * | 2018-08-20 | 2020-03-03 | 北京搜狗科技发展有限公司 | Candidate word generation method and device |
CN111783468A (en) * | 2020-06-28 | 2020-10-16 | 百度在线网络技术(北京)有限公司 | Text processing method, device, equipment and medium |
CN113450793A (en) * | 2021-06-25 | 2021-09-28 | 平安科技(深圳)有限公司 | User emotion analysis method and device, computer readable storage medium and server |
CN116341996A (en) * | 2023-05-31 | 2023-06-27 | 云账户技术(天津)有限公司 | Leader efficiency evaluation method and device, electronic equipment and readable storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103699626A (en) * | 2013-12-20 | 2014-04-02 | 华南理工大学 | Method and system for analysing individual emotion tendency of microblog user |
CN106294316A (en) * | 2016-07-29 | 2017-01-04 | 陕西师范大学 | A kind of text emotion based on dictionary analyzes method |
CN106503220A (en) * | 2016-10-28 | 2017-03-15 | 上海大学 | A kind of microblogging emoticon affection computation method based on a mutual information |
CN106598944A (en) * | 2016-11-25 | 2017-04-26 | 中国民航大学 | Civil aviation security public opinion emotion analysis method |
-
2017
- 2017-11-17 CN CN201711148609.3A patent/CN107943789A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103699626A (en) * | 2013-12-20 | 2014-04-02 | 华南理工大学 | Method and system for analysing individual emotion tendency of microblog user |
CN106294316A (en) * | 2016-07-29 | 2017-01-04 | 陕西师范大学 | A kind of text emotion based on dictionary analyzes method |
CN106503220A (en) * | 2016-10-28 | 2017-03-15 | 上海大学 | A kind of microblogging emoticon affection computation method based on a mutual information |
CN106598944A (en) * | 2016-11-25 | 2017-04-26 | 中国民航大学 | Civil aviation security public opinion emotion analysis method |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110858099A (en) * | 2018-08-20 | 2020-03-03 | 北京搜狗科技发展有限公司 | Candidate word generation method and device |
CN110858099B (en) * | 2018-08-20 | 2024-04-12 | 北京搜狗科技发展有限公司 | Candidate word generation method and device |
CN109325124A (en) * | 2018-09-30 | 2019-02-12 | 武汉斗鱼网络科技有限公司 | A kind of sensibility classification method, device, server and storage medium |
CN109325124B (en) * | 2018-09-30 | 2020-10-16 | 武汉斗鱼网络科技有限公司 | Emotion classification method, device, server and storage medium |
CN109829157A (en) * | 2019-01-21 | 2019-05-31 | 三角兽(北京)科技有限公司 | Text mood rendering method, text mood presentation device and storage medium |
CN110069601A (en) * | 2019-04-03 | 2019-07-30 | 平安科技(深圳)有限公司 | Mood determination method and relevant apparatus |
CN110189742A (en) * | 2019-05-30 | 2019-08-30 | 芋头科技(杭州)有限公司 | Determine emotion audio, affect display, the method for text-to-speech and relevant apparatus |
CN111783468A (en) * | 2020-06-28 | 2020-10-16 | 百度在线网络技术(北京)有限公司 | Text processing method, device, equipment and medium |
CN111783468B (en) * | 2020-06-28 | 2023-08-15 | 百度在线网络技术(北京)有限公司 | Text processing method, device, equipment and medium |
CN113450793A (en) * | 2021-06-25 | 2021-09-28 | 平安科技(深圳)有限公司 | User emotion analysis method and device, computer readable storage medium and server |
CN116341996A (en) * | 2023-05-31 | 2023-06-27 | 云账户技术(天津)有限公司 | Leader efficiency evaluation method and device, electronic equipment and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107943789A (en) | Mood analysis method, device and the server of topic information | |
CN108304526B (en) | Data processing method and device and server | |
CN108628833B (en) | Method and device for determining summary of original content and method and device for recommending original content | |
US20140172415A1 (en) | Apparatus, system, and method of providing sentiment analysis result based on text | |
JP6369053B2 (en) | MATCHING DEVICE, MATCHING METHOD, AND PROGRAM | |
Herzig et al. | Predicting customer satisfaction in customer support conversations in social media using affective features | |
CN107273348B (en) | Topic and emotion combined detection method and device for text | |
Wagner et al. | Semantic stability in social tagging streams | |
Nalisnick et al. | Extracting sentiment networks from Shakespeare's plays | |
CN111914172B (en) | Medical information recommendation method and system based on user tags | |
WO2014048479A1 (en) | A system and method for the automatic creation or augmentation of an electronically rendered publication document | |
Zamani et al. | Sentiment analysis: determining people’s emotions in Facebook | |
CN108269122A (en) | The similarity treating method and apparatus of advertisement | |
Li et al. | Feature extraction from social media posts for psychometric typing of participants | |
KR20170027576A (en) | Apparatus and method of researcher rcommendation based on matching studying career | |
EP2613275B1 (en) | Search device, search method, search program, and computer-readable memory medium for recording search program | |
Rygl | Automatic adaptation of author’s stylometric features to document types | |
CN107807920A (en) | Construction method, device and the server of mood dictionary based on big data | |
CN105468654A (en) | Method and system for selecting reading range of digital resource | |
Ahiladas et al. | Ruchi: Rating individual food items in restaurant reviews | |
CN109446378A (en) | Information recommendation method, Sentiment orientation determine method and device and electronic equipment | |
CN106997340A (en) | The generation of dictionary and the Document Classification Method and device using dictionary | |
Bhattacharyya et al. | An emoticon-based sentiment aggregation on metaverse related tweets | |
Hu et al. | Individual popularity and activity in online social systems | |
CN107871254A (en) | The method and device of data object information is provided |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180420 |