CN109858026A - Text emotion analysis method, device, computer equipment and storage medium - Google Patents
Text emotion analysis method, device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN109858026A CN109858026A CN201910043351.3A CN201910043351A CN109858026A CN 109858026 A CN109858026 A CN 109858026A CN 201910043351 A CN201910043351 A CN 201910043351A CN 109858026 A CN109858026 A CN 109858026A
- Authority
- CN
- China
- Prior art keywords
- text
- analyzed
- paragraph
- unit
- phrase
- 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
Abstract
The embodiment of the invention discloses a kind of text emotion analysis method, device, computer equipment and storage mediums.The present invention applies in the disaggregated model field in intelligent decision.This method comprises: obtaining text to be analyzed by the way of web crawlers and judging the type of the text to be analyzed according to the content of the text to be analyzed;If the type of the text to be analyzed is long text, the long text is subjected to the first pretreatment and obtains the phrase to be analyzed as unit of paragraph;It is matched according to default sentiment dictionary with the phrase to be analyzed with the emotional value of the determination paragraph;The emotional value of the paragraph in the long text is subjected to sum-average arithmetic and obtains the emotional value of the long text;The Sentiment orientation of the long text is determined according to the emotional value of the long text.Method by implementing the embodiment of the present invention can control the emotional value of long text in reasonable section, efficiently avoid the defect that the emotional value of long text is amplified, improve the accuracy of sentiment analysis.
Description
Technical field
The present invention relates to field of artificial intelligence more particularly to a kind of text emotion analysis method, device, computer to set
Standby and storage medium.
Background technique
With science and technology and expanding economy, the information of flood tide is generated in people's lives daily, in information of today
Generation, the value ever more important of information also more pay attention to the analysis of information.Sentiment analysis carries out emotion as a kind of pair of information
Method for analyzing tendentiousness is widely applied in public sentiment monitoring, box office receipts prediction and shares changing tendency prediction field.However,
Existing text emotion analysis method tends not to unification for the sentiment analysis of long text and short text, holds in long text analysis
Easily there is the phenomenon that sentiment analysis result is amplified.
Summary of the invention
The embodiment of the invention provides a kind of text emotion analysis method, device, computer equipment and storage mediums, it is intended to
Solve the problems, such as that the sentiment analysis result of long text is easy to be amplified.
In a first aspect, the embodiment of the invention provides a kind of text emotion analysis methods comprising: using web crawlers
Mode obtains text to be analyzed and judges the type of the text to be analyzed according to the content of the text to be analyzed;If it is described to
The type for analyzing text is long text, and the long text is carried out the first pretreatment and obtains the word to be analyzed as unit of paragraph
Group;It is matched according to default sentiment dictionary with the phrase to be analyzed with the emotional value of the determination paragraph;By the long article
The emotional value of the paragraph in this carries out sum-average arithmetic and obtains the emotional value of the long text;According to the emotion of the long text
Value determines the Sentiment orientation of the long text.
Second aspect, the embodiment of the invention also provides a kind of text emotion analytical equipments comprising: judging unit is used
In obtaining text to be analyzed by the way of web crawlers and judge the text to be analyzed according to the content of the text to be analyzed
This type;It is pre- to be carried out first if the type for the text to be analyzed is long text by pretreatment unit for the long text
Processing obtains the phrase to be analyzed as unit of paragraph;Matching unit, for according to default sentiment dictionary and the word to be analyzed
Group is matched with the emotional value of the determination paragraph;Sum-average arithmetic unit, for by the paragraph in the long text
Emotional value carries out sum-average arithmetic and obtains the emotional value of the long text;Determination unit, for the emotional value according to the long text
Determine the Sentiment orientation of the long text.
The third aspect, the embodiment of the invention also provides a kind of computer equipments comprising memory and processor, it is described
Computer program is stored on memory, the processor realizes the above method when executing the computer program.
Fourth aspect, the embodiment of the invention also provides a kind of computer readable storage medium, the storage medium storage
There is computer program, the computer program can realize the above method when being executed by a processor.
The embodiment of the invention provides a kind of text emotion analysis method, device, computer equipment and storage mediums.Its
In, which comprises text to be analyzed is obtained by the way of web crawlers and is sentenced according to the content of the text to be analyzed
Break the type of the text to be analyzed;If the type of the text to be analyzed is long text, it is pre- that the long text is carried out first
Processing obtains the phrase to be analyzed as unit of paragraph;It is matched according to default sentiment dictionary with the phrase to be analyzed with true
The emotional value of the fixed paragraph;The emotional value of the paragraph in the long text is subjected to sum-average arithmetic and obtains the long text
Emotional value;The Sentiment orientation of the long text is determined according to the emotional value of the long text.The embodiment of the present invention passes through default
Sentiment dictionary determines the emotional value of paragraph in long text, and the emotional value of paragraph in long text is carried out sum-average arithmetic and obtains long article
This emotional value efficiently avoids the emotion of long text, it can be achieved that by the emotional value control of long text in reasonable section
The defect that value is amplified improves the accuracy of sentiment analysis.
Detailed description of the invention
Technical solution in order to illustrate the embodiments of the present invention more clearly, below will be to needed in embodiment description
Attached drawing is briefly described, it should be apparent that, drawings in the following description are some embodiments of the invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is the application scenarios schematic diagram of text emotion analysis method provided in an embodiment of the present invention;
Fig. 2 is the flow diagram of text emotion analysis method provided in an embodiment of the present invention;
Fig. 3 is the sub-process schematic diagram of text emotion analysis method provided in an embodiment of the present invention;
Fig. 4 is the sub-process schematic diagram of text emotion analysis method provided in an embodiment of the present invention;
Fig. 5 is the sub-process schematic diagram of text emotion analysis method provided in an embodiment of the present invention;
Fig. 6 be another embodiment of the present invention provides text emotion analysis method flow diagram;
Fig. 7 is the schematic block diagram of text emotion analytical equipment provided in an embodiment of the present invention;
Fig. 8 is the schematic block diagram of the specific unit of text emotion analytical equipment provided in an embodiment of the present invention;And
Fig. 9 is the schematic block diagram of computer equipment provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are some of the embodiments of the present invention, instead of all the embodiments.Based on this hair
Embodiment in bright, every other implementation obtained by those of ordinary skill in the art without making creative efforts
Example, shall fall within the protection scope of the present invention.
It should be appreciated that ought use in this specification and in the appended claims, term " includes " and "comprising" instruction
Described feature, entirety, step, operation, the presence of element and/or component, but one or more of the other feature, whole is not precluded
Body, step, operation, the presence or addition of element, component and/or its set.
It is also understood that mesh of the term used in this description of the invention merely for the sake of description specific embodiment
And be not intended to limit the present invention.As description of the invention and it is used in the attached claims, unless on
Other situations are hereafter clearly indicated, otherwise " one " of singular, "one" and "the" are intended to include plural form.
It will be further appreciated that the term "and/or" used in description of the invention and the appended claims is
Refer to any combination and all possible combinations of one or more of associated item listed, and including these combinations.
Fig. 1 and Fig. 2 are please referred to, Fig. 1 is that the application scenarios of text emotion analysis method provided in an embodiment of the present invention are illustrated
Figure.Fig. 2 is the schematic flow chart of text emotion analysis method provided in an embodiment of the present invention.Text sentiment analysis method tool
Body is applied in terminal 10, by interacting realization between terminal 10 and server 20.
Fig. 2 is the flow diagram of text emotion analysis method provided in an embodiment of the present invention.As shown, this method packet
Include following steps S110-S150.
S110, text to be analyzed is obtained by the way of web crawlers and institute is judged according to the content of the text to be analyzed
State the type of text to be analyzed.
In one embodiment, obtain text to be analyzed by the way of web crawlers, web crawlers refer to it is a kind of according to
Certain rule automatically grabs the program of web message in server.Specifically, specific webpage is chosen first as just
Beginning page selects microblogging, Sina and Tencent etc. as initial page for example, monitoring field in public sentiment, or leads in Prediction of Stock Index
Domain selects east wealth, straight flush and huge damp net as initial page, or predicts field in box office receipts, selection opal,
Bean cotyledon and Meituan etc. are used as initial page;Then it is crawled since initial page, other chained addresses is grabbed in initial page, then
Next webpage is found by these chained addresses again, repeats the above process and is finished until crawling the content of all websites, most
Accessed web page contents are subjected to data cleansing afterwards, the filtering of the extraneous datas such as link, picture in web page contents is final
To text to be analyzed.Need further to judge the type of the text to be analyzed after obtaining text to be analyzed comprising long text
And short text two types, the content by scanning text to be analyzed is judged, if text to be analyzed has paragraph, is sentenced
The fixed text to be analyzed is long text;If text to be analyzed does not have paragraph, determine that the text to be analyzed is short text.
If the type of S120, the text to be analyzed be long text, by the long text carry out first pretreatment obtain with
Paragraph is the phrase to be analyzed of unit.
In one embodiment, as shown in figure 3, the step S120 may include step S121-S123.
S121, the long text is segmented to obtain multiple paragraphs according to default chopping rule.
S122, the sentence as unit of paragraph is obtained to paragraph progress subordinate sentence according to default punctuation mark.
S123, according to participle tool to the sentence as unit of paragraph segmented to obtain as unit of paragraph to
Analyze phrase.
In one embodiment, it is the content of text with paragraph that long text is specified, for example, news and article etc..First
Pretreatment refers to for long text being segmented, subordinate sentence and participle, is segmented long text to obtain multiple paragraphs first,
In to preset chopping rule include: that can be segmented according to every row sentence-initial with the presence or absence of space, or carried out according to subhead
Segmentation, or be segmented according to blank line, for example, including tri- titles of A, B and C in text, according to tri- titles of ABC
It is divided into three paragraphs.Then each paragraph progress subordinate sentence is obtained into multiple sentences, wherein default punctuation mark includes fullstop, asks
Number and exclamation mark, specifically, using fullstop, question mark and exclamation mark as the ending of each sentence carry out subordinate sentence, for example, " what
For bomb? bomb is a kind of weapon filled with explosive substance, has great risk.Therefore, it please be sure to remote
From!" wherein, " what is bomb? " it is to be divided into one with question mark ending;" bomb is a kind of weapon filled with explosive substance,
With great risk." it is to be divided into one with fullstop ending;" therefore, ask everybody separate!" it is to be ended up with exclamation mark
Be divided into one.Finally each sentence is segmented again, participle is referred to continuous word sequence according to certain specification weight
Combination nova is specifically segmented by participle tool at the process of word sequence, for example, jieba, SnowNLP and NLPIR
Equal participles tool, participle tool is used to a chinese character sequence being cut into individual word one by one, for example, " today, weather was true
Well ", " today/weather/very good " is obtained after participle.It should be noted that above-mentioned subordinate sentence is carried out according to as unit of paragraph
Subordinate sentence, participle is also to be segmented according to as unit of paragraph, for example, including tri- paragraphs of X, Y, Z in text, to X, Y, Z tri-
A paragraph carries out subordinate sentence and obtains the sentence of tri- paragraphs of X, Y, Z, then is segmented to obtain X, Y, Z tri- to tri- paragraphs of X, Y, Z
The phrase to be analyzed of paragraph.
S130, it is matched according to default sentiment dictionary with the phrase to be analyzed with the emotional value of the determination paragraph.
In one embodiment, as shown in figure 4, the step S130 may include step S131-S133.
S131, it is carried out matching point for obtaining the phrase to be analyzed with the phrase to be analyzed according to default sentiment dictionary
Value.
S132, the emotional value that the sentence as unit of paragraph is determined according to the score value of the phrase to be analyzed.
S133, the emotional value that the paragraph is determined according to the emotional value of the sentence as unit of paragraph.
In one embodiment, default sentiment dictionary refers to the dictionary that classification marking is carried out to emotion word, presets emotion word
Word is divided into three classes in allusion quotation, including emotion word, degree adverb and negative word, wherein emotion word include positive emotion word and
Negative Affect word, it is poor for example, like, like and happiness etc. is positive emotion word, dislike and rotten etc. for Negative Affect word;Journey
Degree adverbial word is used to indicate the degree of strength of emotion, for example, very, very and extremely etc.;Negative word indicates the reversion of emotion, example
Such as, it is not, absolutely not and is difficult to.Default sentiment dictionary is built in advance, by calling connecing for default sentiment dictionary
It mouthful uses.In default sentiment dictionary, each emotion word has a corresponding weight score value distributed, and each degree adverb has pair
The degree score value that should be distributed, phrase to be analyzed is by match obtaining phrase to be analyzed default with default sentiment dictionary
Weight score value or degree score value in sentiment dictionary.Specifically, it is traversed and is searched in default sentiment dictionary according to phrase to be analyzed
To same phrase, power of the phrase to be analyzed in default sentiment dictionary is obtained if the phrase to be analyzed is emotion word
Weight score value obtains degree score value of the phrase to be analyzed in default sentiment dictionary if the phrase to be analyzed is degree adverb,
Polarity inverts if the phrase to be analyzed is negative word.After the score value for getting phrase to be analyzed, start to be calculated, it is first
First as unit of paragraph, the emotional value of each sentence in paragraph is calculated, according to the following formula:
Score=W*P* (± 1)
Wherein, Score refers to the emotional value of sentence, and W refers to that the weight score value of emotion word, P refer to degree adverb
Degree score value, ± 1 indicates negative word, occurs negative word in sentence and is then multiplied by once (- 1).For example, " I/be not/very/
Happily ", wherein including emotion word " happy ", degree adverb " very " and negative word "no", the weight score value of " happy " is
0.6, the degree score value of " very " is 1.5, then being -0.9 by the emotional value that the sentence is calculated in formula.Continue to calculate the section
The emotional value of all sentences of the emotional value of other sentences in falling until obtaining the paragraph, then again by all sentences of the paragraph
The emotional value of son carries out summation and is averaged to obtain the emotional value of the paragraph.For example, in the paragraph include sentence 1, sentence 2 and
Sentence 3, the emotional value of sentence 1, sentence 2 and sentence 3 are respectively -0.9,8.5 and 3.6, then to sentence 1, sentence 2 with
And sentence 3 summed after to be averaged to obtain the emotional value of the paragraph be 3.73.
S140, the emotional value progress sum-average arithmetic of the paragraph in the long text is obtained into the emotion of the long text
Value.
In one embodiment, in obtaining long text after the emotional value of each paragraph, by the feelings of paragraphs all in long text
Inductance value carries out summation and is averaged to obtain the emotional value of long text.For example, including paragraph 1, paragraph 2 and paragraph in the long text
3, the emotional value of paragraph 1, paragraph 2 and paragraph 3 is respectively -3.5,12 and 5.2, then to paragraph 1, paragraph 2 and paragraph 3
Emotional value summed after to be averaged to obtain the emotional value of the long text be 13.7.
S150, the Sentiment orientation that the long text is determined according to the emotional value of the long text.
In one embodiment, as shown in figure 5, the step S150 may include step S151-S153.
S151, judge whether the emotional value of the long text is greater than zero.
If the emotional value of S152, the long text is greater than zero, determine that the Sentiment orientation of the long text is actively to be inclined to.
If the emotional value of S153, the long text less than zero, determines the Sentiment orientation of the long text for passiveness tendency.
In one embodiment, based on the judgement of emotional value, emotional value is bigger, and the emotion intensity for illustrating the text is higher,
The smaller emotion intensity for illustrating the text of emotional value is lower.The judgment rule of Sentiment orientation is by the emotional value of text and zero
Be compared, when emotional value is greater than zero, illustrate the Sentiment orientation of the text be it is positive, when emotional value is minus, say
The Sentiment orientation of the bright text is passive.
In another embodiment, as shown in fig. 6, further comprising the steps of: S160-S190 after the step S110.
If the type of S160, the text to be analyzed be short text, by the short text carry out second pretreatment obtain with
Sentence is the phrase to be analyzed of unit.
In one embodiment, short text refers to the content of text without paragraph, for example, microblogging and comment etc..The
Two pretreatments refer to short text carrying out subordinate sentence and participle, because paragraph is not present in short text, with the first pretreatment
Compared to the step of having lacked segmentation, other steps are identical as the first pretreatment.Subordinate sentence is carried out to short text first and obtains multiple sentences
Son, wherein default punctuation mark includes fullstop, question mark and exclamation mark, specifically, using fullstop, question mark and exclamation mark as
The ending of each sentence carries out subordinate sentence, for example, " my mood today is very bad.Can you comfort me once? prithee!",
Wherein, " my mood today is very bad." be with fullstop ending be divided into one, " you can comfort me once? " it is with question mark
Ending is divided into one, " prithee!" it is to be divided into one with exclamation mark ending.Then each sentence is segmented again,
It is also segmented by participle tool, for example, " my mood today is very bad.", obtained after segmenting " I/today/heart
Feelings/very/bad ".It should be noted that above-mentioned participle is segmented according to as unit of sentence, for example, wrapping in short text
Tri- sentences of U, W, Y are included, tri- sentences of U, W, Y are segmented to obtain the phrase to be analyzed of tri- sentences of U, W, Y.
S170, it is matched according to default sentiment dictionary with the phrase to be analyzed with the emotional value of the determination sentence.
In one embodiment, it is analysed to phrase first to be matched with default sentiment dictionary, is existed according to phrase to be analyzed
Traversal finds same phrase in default sentiment dictionary, obtains the word to be analyzed if the phrase to be analyzed is emotion word
Weight score value of the group in default sentiment dictionary obtains the phrase to be analyzed default if the phrase to be analyzed is degree adverb
Degree score value in sentiment dictionary, polarity inverts if the word is negative word.After the score value for getting phrase to be analyzed, with
Sentence is unit, and the emotional value of each sentence is calculated according to the formula in above-mentioned steps S133, for example, " I/it is not to open/very much/
The heart ", wherein including emotion word " happy ", degree adverb " very " and negative word "no", the weight score value of " happy " are 0.6,
" very " degree score value is 1.5, then being -0.9 by the emotional value that the sentence is calculated in formula.
S180, the emotional value progress sum-average arithmetic of the sentence in the short text is obtained into the emotion of the short text
Value.
In one embodiment, in obtaining short text after the emotional value of each sentence, by the feelings of sentences all in short text
Inductance value carries out summation and is averaged to obtain the emotional value of short text.For example, in short text include sentence 1, sentence 2 and sentence 3,
The emotional value of sentence 1, sentence 2 and sentence 3 is respectively 6, -5 and 8.3, then carrying out to sentence 1, sentence 2 and sentence 3
The emotional value for being averaged to obtain the paragraph after summation is 3.1.
S190, the Sentiment orientation that the short text is determined according to the emotional value of the short text.
In one embodiment, based on the judgement of emotional value, emotional value is bigger, and the emotion intensity for illustrating the text is higher,
The smaller emotion intensity for illustrating the text of emotional value is lower.The judgment rule of Sentiment orientation is by the emotional value of text and zero
Be compared, when emotional value is greater than zero, illustrate the Sentiment orientation of the text be it is positive, when emotional value is minus, say
The Sentiment orientation of the bright text is passive.
The embodiment of the present invention illustrates a kind of text emotion analysis method, obtains by using the mode of web crawlers wait divide
Analysis text and the type that the text to be analyzed is judged according to the content of the text to be analyzed;If the class of the text to be analyzed
Type is long text, and the long text is carried out the first pretreatment and obtains the phrase to be analyzed as unit of paragraph;According to default feelings
Sense dictionary is matched with the phrase to be analyzed with the emotional value of the determination paragraph;By the paragraph in the long text
Emotional value carry out sum-average arithmetic obtain the emotional value of the long text;The long article is determined according to the emotional value of the long text
The emotional value of long text can be controlled in reasonable section, efficiently avoid the emotional value of long text by this Sentiment orientation
The defect being amplified improves the accuracy of sentiment analysis.
Fig. 7 is a kind of schematic block diagram of text emotion analytical equipment 200 provided in an embodiment of the present invention.As shown in fig. 7,
Corresponding to the above text emotion analysis method, the present invention also provides a kind of text emotion analytical equipments 200.Text sentiment analysis
Device 200 includes the unit for executing above-mentioned text emotion analysis method, which can be configured in desktop computer, plate
Computer, laptop computer, etc. in terminals.Specifically, referring to Fig. 7, text sentiment analysis device 200 include judging unit 210,
Pretreatment unit 220, matching unit 230, sum-average arithmetic unit 240 and determination unit 250.
Judging unit 210, for obtaining text to be analyzed by the way of web crawlers and according to the text to be analyzed
Content judge the type of the text to be analyzed.
The long text is carried out first if the type for the text to be analyzed is long text by pretreatment unit 220
Pretreatment obtains the phrase to be analyzed as unit of paragraph.
In one embodiment, as shown in figure 8, the pretreatment unit 220 includes subelement: segmenting unit 221, subordinate sentence list
Member 222 and participle unit 223.
Segmenting unit 221, for being segmented to obtain multiple paragraphs to the long text according to default chopping rule.
Clause unit 222 obtains as unit of paragraph for carrying out subordinate sentence to the paragraph according to default punctuation mark
Sentence.
Participle unit 223, for being segmented to obtain with section to the sentence as unit of paragraph according to participle tool
Fall the phrase to be analyzed for unit.
Matching unit 230, for being matched according to default sentiment dictionary with the phrase to be analyzed with described section of determination
The emotional value fallen.
In one embodiment, as shown in figure 8, the matching unit 230 includes subelement: acquiring unit 231, first determines
Subelement 232 and the second determining subelement 233.
Acquiring unit 231, for match described in acquisition wait divide with the phrase to be analyzed according to default sentiment dictionary
Analyse the score value of phrase.
First determines subelement 232, described as unit of paragraph for being determined according to the score value of the phrase to be analyzed
The emotional value of sentence.
Second determines subelement 233, for determining the paragraph according to the emotional value of the sentence as unit of paragraph
Emotional value.
Sum-average arithmetic unit 240 is obtained for the emotional value of the paragraph in the long text to be carried out sum-average arithmetic
The emotional value of the long text.
Determination unit 250, for determining the Sentiment orientation of the long text according to the emotional value of the long text.
In one embodiment, as shown in figure 8, the determination unit 250 includes subelement: judgment sub-unit 251, first are sentenced
Order member 252 and the second judging unit 253.
Judgment sub-unit 251, for judging whether the emotional value of the long text is greater than zero;
First judging unit 252 determines that the emotion of the long text is inclined if the emotional value for the long text is greater than zero
It is inclined to to be positive;
Second judging unit 253, if the emotional value for the long text less than zero, determines that the emotion of the long text is inclined
It is inclined to for passiveness.
It should be noted that it is apparent to those skilled in the art that, above-mentioned text emotion analytical equipment
200 and each unit specific implementation process, can with reference to the corresponding description in preceding method embodiment, for convenience of description and
Succinctly, details are not described herein.
Above-mentioned text emotion analytical equipment can be implemented as a kind of form of computer program, which can be
It is run in computer equipment as shown in Figure 9.
Referring to Fig. 9, Fig. 9 is a kind of schematic block diagram of computer equipment provided by the embodiments of the present application.The computer
Equipment 500 can be terminal, wherein terminal can be smart phone, tablet computer, laptop, desktop computer, a number
Word assistant and wearable device etc. have the electronic equipment of communication function.
Refering to Fig. 9, which includes processor 502, memory and the net connected by system bus 501
Network interface 505, wherein memory may include non-volatile memory medium 503 and built-in storage 504.
The non-volatile memory medium 503 can storage program area 5031 and computer program 5032.The computer program
5032 include program instruction, which is performed, and processor 502 may make to execute a kind of text emotion analysis method.
The processor 502 is for providing calculating and control ability, to support the operation of entire computer equipment 500.
The built-in storage 504 provides environment for the operation of the computer program 5032 in non-volatile memory medium 503, should
When computer program 5032 is executed by processor 502, processor 502 may make to execute a kind of text emotion analysis method.
The network interface 505 is used to carry out network communication with other equipment.It will be understood by those skilled in the art that in Fig. 9
The structure shown, only the block diagram of part-structure relevant to application scheme, does not constitute and is applied to application scheme
The restriction of computer equipment 500 thereon, specific computer equipment 500 may include more more or fewer than as shown in the figure
Component perhaps combines certain components or with different component layouts.
Wherein, the processor 502 is for running computer program 5032 stored in memory, to realize following step
It is rapid: to obtain text to be analyzed by the way of web crawlers and the text to be analyzed is judged according to the content of the text to be analyzed
This type;If the type of the text to be analyzed is long text, the long text is subjected to the first pretreatment and is obtained with paragraph
For the phrase to be analyzed of unit;It is matched according to default sentiment dictionary with the phrase to be analyzed with the feelings of the determination paragraph
Inductance value;The emotional value of the paragraph in the long text is subjected to sum-average arithmetic and obtains the emotional value of the long text;According to
The emotional value of the long text determines the Sentiment orientation of the long text.
In one embodiment, processor 502 is obtained in described pre-process long text progress first of realization with paragraph
For unit phrase step to be analyzed when, be implemented as follows step: the long text being divided according to default chopping rule
Section obtains multiple paragraphs;Subordinate sentence is carried out to the paragraph according to default punctuation mark and obtains the sentence as unit of paragraph;According to
Participle tool is segmented to obtain the phrase to be analyzed as unit of paragraph to the sentence as unit of paragraph.
In one embodiment, processor 502 is realizing that the basis presets sentiment dictionary and the phrase to be analyzed carries out
When matching the emotional value step with the determination paragraph, it is implemented as follows step: according to default sentiment dictionary with described wait divide
Analysis phrase carries out the score value that matching obtains the phrase to be analyzed;It is determined according to the score value of the phrase to be analyzed described with paragraph
For the emotional value of the sentence of unit;The emotional value of the paragraph is determined according to the emotional value of the sentence as unit of paragraph.
In one embodiment, processor 502 determines the long text in the realization emotional value according to the long text
Sentiment orientation step when, be implemented as follows step: judging whether the emotional value of the long text is greater than zero;If the long article
This emotional value is greater than zero, determines that the Sentiment orientation of the long text is actively to be inclined to;If the emotional value of the long text is less than
Zero, determine the Sentiment orientation of the long text for passiveness tendency.
In one embodiment, processor 502 is realizing text to be analyzed and the root of obtaining by the way of web crawlers
After the type step for judging the text to be analyzed according to the content of the text to be analyzed, following steps are also realized: if described
The type of text to be analyzed is short text, and the short text is carried out the second pretreatment and obtains the word to be analyzed as unit of sentence
Group;It is matched according to default sentiment dictionary with the phrase to be analyzed with the emotional value of the determination sentence;By the short essay
The emotional value of the sentence in this carries out sum-average arithmetic and obtains the emotional value of the short text;According to the emotion of the short text
Value determines the Sentiment orientation of the short text.
It should be appreciated that in the embodiment of the present application, processor 502 can be central processing unit (Central
Processing Unit, CPU), which can also be other general processors, digital signal processor (Digital
Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit,
ASIC), ready-made programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic
Device, discrete gate or transistor logic, discrete hardware components etc..Wherein, general processor can be microprocessor or
Person's processor is also possible to any conventional processor etc..
Those of ordinary skill in the art will appreciate that be realize above-described embodiment method in all or part of the process,
It is that relevant hardware can be instructed to complete by computer program.The computer program includes program instruction, computer journey
Sequence can be stored in a storage medium, which is computer readable storage medium.The program instruction is by the department of computer science
At least one processor in system executes, to realize the process step of the embodiment of the above method.
Therefore, the present invention also provides a kind of storage mediums.The storage medium can be computer readable storage medium.This is deposited
Storage media is stored with computer program, and wherein computer program includes program instruction.The program instruction makes when being executed by processor
Processor executes following steps: text to be analyzed is obtained by the way of web crawlers and according to the content of the text to be analyzed
Judge the type of the text to be analyzed;If the type of the text to be analyzed is long text, the long text is carried out first
Pretreatment obtains the phrase to be analyzed as unit of paragraph;Matched according to default sentiment dictionary with the phrase to be analyzed with
Determine the emotional value of the paragraph;The emotional value of the paragraph in the long text is subjected to sum-average arithmetic and obtains the long article
This emotional value;
The Sentiment orientation of the long text is determined according to the emotional value of the long text.
In one embodiment, the processor is realized and described the long text is carried out the executing described program instruction
When one pretreatment obtains the phrase step to be analyzed as unit of paragraph, it is implemented as follows step: according to default chopping rule
The long text is segmented to obtain multiple paragraphs;Subordinate sentence is carried out to the paragraph according to default punctuation mark to obtain with paragraph
For the sentence of unit;According to participle tool to the sentence as unit of paragraph segmented to obtain as unit of paragraph to
Analyze phrase.
In one embodiment, the processor execute described program instruction and realize the basis preset sentiment dictionary with
When the phrase to be analyzed is matched with the emotional value step of the determination paragraph, it is implemented as follows step: according to default
Sentiment dictionary carries out matching the score value for obtaining the phrase to be analyzed with the phrase to be analyzed;According to the phrase to be analyzed
Score value determines the emotional value of the sentence as unit of paragraph;It is determined according to the emotional value of the sentence as unit of paragraph
The emotional value of the paragraph.
In one embodiment, the processor realizes the feelings according to the long text executing described program instruction
When inductance value determines the Sentiment orientation step of the long text, be implemented as follows step: judging the emotional value of the long text is
It is no to be greater than zero;If the emotional value of the long text is greater than zero, determine that the Sentiment orientation of the long text is actively to be inclined to;If described
The emotional value of long text determines the Sentiment orientation of the long text for passiveness tendency less than zero.
In one embodiment, the processor is realized described by the way of web crawlers in the instruction of execution described program
It is also real after obtaining text to be analyzed and judging the type step of the text to be analyzed according to the content of the text to be analyzed
Existing following steps: if the type of the text to be analyzed is short text, the short text is subjected to the second pretreatment and is obtained with sentence
Son is the phrase to be analyzed of unit;It is matched according to default sentiment dictionary with the phrase to be analyzed with the determination sentence
Emotional value;The emotional value of the sentence in the short text is subjected to sum-average arithmetic and obtains the emotional value of the short text;Root
The Sentiment orientation of the short text is determined according to the emotional value of the short text.
The storage medium can be USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), magnetic disk
Or the various computer readable storage mediums that can store program code such as CD.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps, can be realized with electronic hardware, computer software, or a combination of the two, in order to clearly demonstrate hardware
With the interchangeability of software, each exemplary composition and step are generally described according to function in the above description.This
A little functions are implemented in hardware or software actually, the specific application and design constraint depending on technical solution.Specially
Industry technical staff can use different methods to achieve the described function each specific application, but this realization is not
It is considered as beyond the scope of this invention.
In several embodiments provided by the present invention, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary.For example, the division of each unit, only
Only a kind of logical function partition, there may be another division manner in actual implementation.Such as multiple units or components can be tied
Another system is closed or is desirably integrated into, or some features can be ignored or not executed.
The steps in the embodiment of the present invention can be sequentially adjusted, merged and deleted according to actual needs.This hair
Unit in bright embodiment device can be combined, divided and deleted according to actual needs.In addition, in each implementation of the present invention
Each functional unit in example can integrate in one processing unit, is also possible to each unit and physically exists alone, can also be with
It is that two or more units are integrated in one unit.
If the integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product,
It can store in one storage medium.Based on this understanding, technical solution of the present invention is substantially in other words to existing skill
The all or part of part or the technical solution that art contributes can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, terminal or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or replace
It changes, these modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with right
It is required that protection scope subject to.
Claims (10)
1. a kind of text emotion analysis method characterized by comprising
Text to be analyzed is obtained by the way of web crawlers and is judged according to the content of the text to be analyzed described to be analyzed
The type of text;
If the type of the text to be analyzed is long text, the long text is subjected to the first pretreatment and is obtained as unit of paragraph
Phrase to be analyzed;
It is matched according to default sentiment dictionary with the phrase to be analyzed with the emotional value of the determination paragraph;
The emotional value of the paragraph in the long text is subjected to sum-average arithmetic and obtains the emotional value of the long text;
The Sentiment orientation of the long text is determined according to the emotional value of the long text.
2. text emotion analysis method according to claim 1, which is characterized in that described that the long text is carried out first
Pretreatment obtains the phrase to be analyzed as unit of paragraph, comprising:
The long text is segmented according to default chopping rule to obtain multiple paragraphs;
Subordinate sentence is carried out to the paragraph according to default punctuation mark and obtains the sentence as unit of paragraph;
Segmented to obtain the phrase to be analyzed as unit of paragraph to the sentence as unit of paragraph according to participle tool.
3. text emotion analysis method according to claim 2, which is characterized in that the basis presets sentiment dictionary and institute
Phrase to be analyzed is stated to be matched with the emotional value of the determination paragraph, comprising:
It is carried out matching the score value for obtaining the phrase to be analyzed with the phrase to be analyzed according to default sentiment dictionary;
The emotional value of the sentence as unit of paragraph is determined according to the score value of the phrase to be analyzed;
The emotional value of the paragraph is determined according to the emotional value of the sentence as unit of paragraph.
4. text emotion analysis method according to claim 1, which is characterized in that the emotion according to the long text
Value determines the Sentiment orientation of the long text, comprising:
Judge whether the emotional value of the long text is greater than zero;
If the emotional value of the long text is greater than zero, determine that the Sentiment orientation of the long text is actively to be inclined to;
If the emotional value of the long text less than zero, determines the Sentiment orientation of the long text for passiveness tendency.
5. text emotion analysis method according to claim 1, which is characterized in that described to be obtained by the way of web crawlers
After taking text to be analyzed and judging the type of the text to be analyzed according to the content of the text to be analyzed, further includes:
If the type of the text to be analyzed is short text, the short text is subjected to the second pretreatment and is obtained as unit of sentence
Phrase to be analyzed;
It is matched according to default sentiment dictionary with the phrase to be analyzed with the emotional value of the determination sentence;
The emotional value of the sentence in the short text is subjected to sum-average arithmetic and obtains the emotional value of the short text;
The Sentiment orientation of the short text is determined according to the emotional value of the short text.
6. a kind of text emotion analytical equipment characterized by comprising
Judging unit, for obtaining text to be analyzed by the way of web crawlers and being sentenced according to the content of the text to be analyzed
Break the type of the text to be analyzed;
The long text is carried out the first pretreatment if the type for the text to be analyzed is long text by pretreatment unit
Obtain the phrase to be analyzed as unit of paragraph;
Matching unit, for being matched according to default sentiment dictionary with the phrase to be analyzed with the emotion of the determination paragraph
Value;
Sum-average arithmetic unit obtains the long article for the emotional value of the paragraph in the long text to be carried out sum-average arithmetic
This emotional value;
Determination unit, for determining the Sentiment orientation of the long text according to the emotional value of the long text.
7. text emotion analytical equipment according to claim 1 characterized by comprising
Segmenting unit, for being segmented to obtain multiple paragraphs to the long text according to default chopping rule;
Clause unit obtains the sentence as unit of paragraph for carrying out subordinate sentence to the paragraph according to default punctuation mark;
Participle unit, for being segmented to obtain as unit of paragraph to the sentence as unit of paragraph according to participle tool
Phrase to be analyzed.
8. text emotion analytical equipment according to claim 1 characterized by comprising
Acquiring unit obtains the phrase to be analyzed for match with the phrase to be analyzed according to default sentiment dictionary
Score value;
First determines subelement, for determining the feelings of the sentence as unit of paragraph according to the score value of the phrase to be analyzed
Inductance value;
Second determines subelement, for determining the emotion of the paragraph according to the emotional value of the sentence as unit of paragraph
Value.
9. a kind of computer equipment, which is characterized in that the computer equipment includes memory and processor, on the memory
It is stored with computer program, the processor is realized as described in any one of claim 1-5 when executing the computer program
Method.
10. a kind of storage medium, which is characterized in that the storage medium is stored with computer program, and the computer program is worked as
Method according to any one of claims 1 to 5 can be realized when being executed by processor.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910043351.3A CN109858026A (en) | 2019-01-17 | 2019-01-17 | Text emotion analysis method, device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910043351.3A CN109858026A (en) | 2019-01-17 | 2019-01-17 | Text emotion analysis method, device, computer equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109858026A true CN109858026A (en) | 2019-06-07 |
Family
ID=66894991
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910043351.3A Pending CN109858026A (en) | 2019-01-17 | 2019-01-17 | Text emotion analysis method, device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109858026A (en) |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334182A (en) * | 2019-06-24 | 2019-10-15 | 中国南方电网有限责任公司 | Online service method with speech emotion recognition |
CN110399484A (en) * | 2019-06-25 | 2019-11-01 | 平安科技(深圳)有限公司 | Sentiment analysis method, apparatus, computer equipment and the storage medium of long text |
CN110888983A (en) * | 2019-11-26 | 2020-03-17 | 厦门市美亚柏科信息股份有限公司 | Positive and negative emotion analysis method, terminal device and storage medium |
CN111985223A (en) * | 2020-08-25 | 2020-11-24 | 武汉长江通信产业集团股份有限公司 | Emotion calculation method based on combination of long and short memory networks and emotion dictionaries |
CN112182332A (en) * | 2020-09-25 | 2021-01-05 | 科大国创云网科技有限公司 | Emotion classification method and system based on crawler collection |
WO2021134177A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳市优必选科技股份有限公司 | Sentiment labeling method, apparatus and device for speaking content, and storage medium |
CN113255368A (en) * | 2021-06-07 | 2021-08-13 | 中国平安人寿保险股份有限公司 | Method and device for emotion analysis of text data and related equipment |
CN115794988A (en) * | 2022-09-13 | 2023-03-14 | 广东美云智数科技有限公司 | Method, apparatus, and computer storage medium for extracting viewpoint of text |
CN116805147A (en) * | 2023-02-27 | 2023-09-26 | 杭州城市大脑有限公司 | Text labeling method and device applied to urban brain natural language processing |
-
2019
- 2019-01-17 CN CN201910043351.3A patent/CN109858026A/en active Pending
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110334182A (en) * | 2019-06-24 | 2019-10-15 | 中国南方电网有限责任公司 | Online service method with speech emotion recognition |
CN110399484A (en) * | 2019-06-25 | 2019-11-01 | 平安科技(深圳)有限公司 | Sentiment analysis method, apparatus, computer equipment and the storage medium of long text |
CN110888983A (en) * | 2019-11-26 | 2020-03-17 | 厦门市美亚柏科信息股份有限公司 | Positive and negative emotion analysis method, terminal device and storage medium |
CN110888983B (en) * | 2019-11-26 | 2022-07-15 | 厦门市美亚柏科信息股份有限公司 | Positive and negative emotion analysis method, terminal equipment and storage medium |
WO2021134177A1 (en) * | 2019-12-30 | 2021-07-08 | 深圳市优必选科技股份有限公司 | Sentiment labeling method, apparatus and device for speaking content, and storage medium |
CN111985223A (en) * | 2020-08-25 | 2020-11-24 | 武汉长江通信产业集团股份有限公司 | Emotion calculation method based on combination of long and short memory networks and emotion dictionaries |
CN112182332A (en) * | 2020-09-25 | 2021-01-05 | 科大国创云网科技有限公司 | Emotion classification method and system based on crawler collection |
CN113255368A (en) * | 2021-06-07 | 2021-08-13 | 中国平安人寿保险股份有限公司 | Method and device for emotion analysis of text data and related equipment |
CN115794988A (en) * | 2022-09-13 | 2023-03-14 | 广东美云智数科技有限公司 | Method, apparatus, and computer storage medium for extracting viewpoint of text |
CN116805147A (en) * | 2023-02-27 | 2023-09-26 | 杭州城市大脑有限公司 | Text labeling method and device applied to urban brain natural language processing |
CN116805147B (en) * | 2023-02-27 | 2024-03-22 | 杭州城市大脑有限公司 | Text labeling method and device applied to urban brain natural language processing |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109858026A (en) | Text emotion analysis method, device, computer equipment and storage medium | |
CN105005594B (en) | Abnormal microblog users recognition methods | |
CN111310476B (en) | Public opinion monitoring method and system using aspect-based emotion analysis method | |
CN106682387A (en) | Method and device used for outputting information | |
CN113407677B (en) | Method, apparatus, device and storage medium for evaluating consultation dialogue quality | |
Bentz | Adaptive languages: An information-theoretic account of linguistic diversity | |
CN106844330B (en) | The analysis method and device of article emotion | |
CN107895027A (en) | Individual feelings and emotions knowledge mapping method for building up and device | |
CN112579733A (en) | Rule matching method, rule matching device, storage medium and electronic equipment | |
CN112926308A (en) | Method, apparatus, device, storage medium and program product for matching text | |
Filho et al. | Gender classification of twitter data based on textual meta-attributes extraction | |
CN114519613B (en) | Price data processing method and device, electronic equipment and storage medium | |
Nickels et al. | Computational modelling of phonological dyslexia: How does the DRC model fare? | |
Xu et al. | Network-based prediction of the disclosure of ideation about self-harm and suicide in online counseling sessions | |
US20230206007A1 (en) | Method for mining conversation content and method for generating conversation content evaluation model | |
CN111666513A (en) | Page processing method and device, electronic equipment and readable storage medium | |
CN115098665A (en) | Method, device and equipment for expanding session data | |
US11748573B2 (en) | System and method to quantify subject-specific sentiment | |
CN115827832A (en) | Dialog system content relating to external events | |
WO2022216722A1 (en) | Generating aspects from attributes identified in digital video audio tracks | |
CN114416941A (en) | Generation method and device of dialogue knowledge point determination model fusing knowledge graph | |
CN116541517A (en) | Text information processing method, apparatus, device, software program, and storage medium | |
CN108460017B (en) | The extensive method, apparatus of corpus, electronic equipment and readable storage medium storing program for executing | |
CN112100378A (en) | Text classification model training method and device, computer equipment and storage medium | |
CN112231444A (en) | Processing method and device for corpus data combining RPA and AI and electronic equipment |
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 |