CN106547875A - A kind of online incident detection method of the microblogging based on sentiment analysis and label - Google Patents
A kind of online incident detection method of the microblogging based on sentiment analysis and label Download PDFInfo
- Publication number
- CN106547875A CN106547875A CN201610945406.6A CN201610945406A CN106547875A CN 106547875 A CN106547875 A CN 106547875A CN 201610945406 A CN201610945406 A CN 201610945406A CN 106547875 A CN106547875 A CN 106547875A
- Authority
- CN
- China
- Prior art keywords
- label
- microblogging
- word
- emotion
- sentiment analysis
- 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.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 26
- 230000008451 emotion Effects 0.000 claims abstract description 30
- 230000002996 emotional effect Effects 0.000 claims abstract description 12
- 230000011218 segmentation Effects 0.000 claims abstract description 11
- 238000010276 construction Methods 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims abstract description 5
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 4
- 238000013145 classification model Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 4
- 238000011524 similarity measure Methods 0.000 claims description 3
- 239000013598 vector Substances 0.000 description 4
- 238000007796 conventional method Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 206010028916 Neologism Diseases 0.000 description 1
- 244000097202 Rathbunia alamosensis Species 0.000 description 1
- 235000009776 Rathbunia alamosensis Nutrition 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Artificial Intelligence (AREA)
- Human Resources & Organizations (AREA)
- Computing Systems (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to network detection field, and in particular to a kind of online incident detection method of the microblogging based on sentiment analysis and label.The present invention includes:Using sentiment classification model emotion wheel, sentiment analysis model --- emotion co-occurrence figure is constructed;The sentiment analysis model constructed using step (1), carries out emotional semantic classification to the microblogging in microblogging stream, detects the burst period of microblogging stream using kleinberg algorithms;The microblog label in burst period is extracted, rubbish label is filtered out, word segmentation processing is carried out to remaining label;The initial key word of formation event;The keyword generated using step (3), in extraction microblogging, the word related to this keyword, forms the final description of event.Emotion co-occurrence figure of the present invention construction based on emotion wheel, emotional semantic classification are more careful, and emotion is easier to understand and explains, higher relative to the event detection accuracy rate based on emotional symbol.
Description
Technical field
The invention belongs to network detection field, and in particular to a kind of microblogging based on sentiment analysis and label is happened suddenly thing online
Part detection method.
Background technology
Flourish recently as Web2.0 technologies, emerge a series of social networks.These social networks such as Sina
Microblogging, push away top grade and attract substantial amounts of user.Users are active on social networks, issue substantial amounts of Twitter message, wherein
Comprising about some events view or viewpoint.By excavating these Twitter messages, can obtain substantial amounts of such as user feeling
Deng deeper information.The use of these profound information can be that government or enterprise provide service, for example, government can be with
Judge whether people are supported to law bill using these information, which type of view is held to a certain social event, so as to enter
Row public sentiment is controlled and is guided;The behavioural habits and preference of user by the Twitter message of digging user, can be learnt by enterprise, so as to
The commodity of most possible interested or purchase to its recommended user.
For incident detection, conventional method has two kinds, i.e., the incident detection and feature based based on document
Incident detection.Based on the incident detection thought of document it is, by document representation into term vector or name entity vector, meter
The similarity between document is calculated, cluster is carried out to document and is formed event.It is to excavate number that event detection is carried out to feature based burst
One of effective ways according to accident in stream, its main thought are abstracting document Feature Words first, by analyze Feature Words with
Then Feature Words with same burst track are polymerized by time change track detection burst phenomenon, form accident.
However, this two methods are in the case of microblogging short text and do not apply to.Microblog data amount is big first, for each microblogging is carried
Take Feature Words, formation tfidf matrixes to require a great deal of time.Secondly, microblogging expression way is irregular, and form is changeable, can
Substantial amounts of neologisms can be contained, the matrix of formation is sparse, be unfavorable for calculating similarity, increase identification difficulty.Meanwhile, conventional method is only
The extraction of accident is completed, deeper analysis, such as sentiment analysis are not carried out to accident.
The content of the invention
It is an object of the invention to provide a kind of online incident detection model for microblog data stream short text, energy
Enough microbloggings based on sentiment analysis and label for accurately and rapidly extracting the accident in data flow are happened suddenly thing online
Part detection method.
The object of the present invention is achieved like this:
A kind of online incident detection method of the microblogging based on sentiment analysis and label, comprises the steps:
(1) using sentiment classification model emotion wheel, construct sentiment analysis model --- emotion co-occurrence figure;
(2) the sentiment analysis model constructed using step (1), carries out emotional semantic classification to the microblogging in microblogging stream, adopts
Kleinberg algorithms detect the burst period of microblogging stream;
(3) microblog label in burst period is extracted, rubbish label is filtered out, word segmentation processing is carried out to remaining label;Formed
The initial key word of event;
(4) keyword generated using step (3), in extraction microblogging, the word related to this keyword, forms event most
Describe eventually.
In the step (1), emotion co-occurrence figure is constructed by the following method:
(1.1) using emotion wheel model, manually rational vocabulary is given to emotional symbol;
(1.2) word segmentation processing is carried out to original microblog data, microblogging corpus is formed;
(1.3) using HowNet dictionaries, using word Similarity measures microblogging corpus word and emotion based on distance
Similarity between symbol word;
(1.3) used in, equation below calculates the similitude of word detection:
W in formula1And W2Represent word, word W1There is the k senses of a dictionary entry:{n11,n12,…,n1k, word W2There is the p senses of a dictionary entry:{n21,
n22,…,n2p, p1And p2Represent that two justice are former, d is p1And p2Path in adopted original hierarchical system, is a positive integer;
α is an adjustable parameter;
(1.4) similarity is set up more than the connection between the word of given threshold value λ, complete the construction of emotion co-occurrence figure;λ is selected
Select 0.6.
In described step (3), comprise the steps of:
(3.1) label to extracting carries out part-of-speech tagging, removes the mark of the only label of verb or only one of which noun
Sign;
(3.2) weed out the label containing additional character in label;
(3.3) weed out containing standard date format, only have the label of numeral and punctuation mark;
Comprise the following steps in described step (4):
(4.1) word segmentation processing is carried out to remaining label in burst period;
(4.2) calculate the frequent mode in burst period about microblog label keyword;
(4.3) 2 item collections in frequent mode are extracted, the mutual information between word in 2 item collection is calculated;
(4.4) retain morphology of the mutual information more than given threshold value γ into final event description;The value of γ selects 1.5;
In step 4.4, mutual information computing formula is:
C(W1) and C (W2) respectively represent corpus in contain W1And W2Microblogging quantity, C (W1,W2) represent and contain W simultaneously1
And W2Microblogging quantity;Scales of the R for corpus, i.e. microblogging sum.
The invention has the beneficial effects as follows:
Emotion co-occurrence figure of the present invention construction based on emotion wheel, emotional semantic classification are more careful, and emotion is easier to understand reconciliation
Release, it is higher relative to the event detection accuracy rate based on emotional symbol.Sentiment analysis, mistake are carried out using the emotion co-occurrence figure set up
Substantial amounts of useless microblogging is filtered, and the bursty state of microblog data stream, efficiency high is detected using sentiment analysis result.Using microblogging mark
Label carry out accident discovery as guiding, find that accuracy rate is high than the event based on cluster, and detection detection time is fast.
Description of the drawings
Online accident model frameworks of the Fig. 1 based on emotion co-occurrence figure.
Specific embodiment
With reference to the accompanying drawings and detailed description the implementation process of the present invention is described in further detail.
Step 1:Using sentiment classification model emotion wheel, sentiment analysis model --- emotion co-occurrence figure is constructed.Specifically include
Following steps:
Step 1.1:Using emotion wheel model, manually rational vocabulary is given to emotional symbol;
Step 1.2:Word segmentation processing is carried out to original microblog data, microblogging corpus is formed;
Step 1.3:Using HowNet dictionaries, using word Similarity measures microblogging corpus word and feelings based on distance
Similarity between sense symbol word.
Used in step 1.3, equation below calculates the similitude of word detection:
W in formula1And W2Represent word, word W1There is the k senses of a dictionary entry (concept):{n11,n12,…,n1k, word W2Have p it is adopted
Item (concept):{n21,n22,…,n2p, p1And p2Represent that two justice are former, d is p1And p2Path length in adopted original hierarchical system
Degree, is a positive integer.α is an adjustable parameter, takes 1.6 in the present invention.
Step 1.4:Similarity is set up more than the connection between the word of given threshold value λ, the construction of emotion co-occurrence figure is completed.
λ selects 0.6 in the present invention.
Step 2:The sentiment analysis model constructed using step 1, carries out emotional semantic classification to the microblogging in microblogging stream, adopts
Kleinberg algorithms detect the burst period of microblogging stream.
Step 2.1:Each microblogging in for microblogging stream, carries out word segmentation processing to which.
Step 2.2:The microblogging finished to participle, sets up the emotion vector of microblogging using the emotion co-occurrence graph model set up
Sd。
Step 2.3:Flag bit flag=true is set, if the corresponding emotion mark σ sk of Sd vectors are 1, by the microblogging
In adding emotion document sets Ds Tk, flag is set to into false.
Step 2.4:Repeat step 2.2 and 2.3 is finished until the classification of all of microblogging.
Step 2.5:For each class emotion microblogging, burst period is detected using kleinberg algorithms.
Step 3:The microblog label in burst period is extracted, rubbish label is filtered out, word segmentation processing is carried out to remaining label.Shape
Into the initial key word of event.
Step 3.1:Label to extracting carries out part-of-speech tagging, removes the only label of verb or only one of which noun
Label, such as " # good morning # ", " # good night # ", " # sings # ", " # Jiu Zhaigous # ", " # journey # " this kind of label.
Step 3.2:Weed out in label containing additional character ("《", "+", "-", "-") label.As " # makes laughs+regards
Frequency # ", " # good morning * loves shop # ", " #Weico+# ".
Step 3.3:Weed out containing standard date format, only the label of numeral and punctuation mark,.Such as " #365# ", " #
4.01#”。
Step 4:The keyword generated using step 3, in extraction microblogging, the word related to this keyword, forms event most
Describe eventually.
Step 4.1:Word segmentation processing is carried out to remaining label in burst period.
Step 4.2:Calculate the frequent mode about microblog label keyword in burst period.
Step 4.3:2 item collections in frequent mode are extracted, the mutual information between word in 2 item collection is calculated.
Step 4.4:Retain word of the mutual information more than given threshold value Y, word is ranked up by word frequency, form final event
Description.In the present invention, the value of Y selects 1.5.
In step 4.4, mutual information computing formula is:
C(W1) and C (W2) respectively represent corpus in contain W1And W2Microblogging quantity, C (W1, W2) represent and contain W simultaneously1
And W2Microblogging quantity.Scales of the R for corpus, i.e. microblogging sum.
Claims (4)
1. a kind of online incident detection method of microblogging based on sentiment analysis and label, it is characterised in that including following step
Suddenly:
(1) using sentiment classification model emotion wheel, construct sentiment analysis model --- emotion co-occurrence figure;
(2) the sentiment analysis model constructed using step (1), carries out emotional semantic classification to the microblogging in microblogging stream, adopts
Kleinberg algorithms detect the burst period of microblogging stream;
(3) microblog label in burst period is extracted, rubbish label is filtered out, word segmentation processing is carried out to remaining label;Formation event
Initial key word;
(4) keyword generated using step (3), in extraction microblogging, the word related to this keyword, forms finally retouching for event
State.
2. the online incident detection method of a kind of microblogging based on sentiment analysis and label according to claim 1, its
It is characterised by, in the step (1), constructs emotion co-occurrence figure by the following method:
(1.1) using emotion wheel model, manually rational vocabulary is given to emotional symbol;
(1.2) word segmentation processing is carried out to original microblog data, microblogging corpus is formed;
(1.3) using HowNet dictionaries, using word Similarity measures microblogging corpus word and emotional symbol based on distance
Similarity between word;
(1.3) used in, equation below calculates the similitude of word detection:
W in formula1And W2Represent word, word W1There is the k senses of a dictionary entry:{n11,n12,…,n1k, word W2There is the p senses of a dictionary entry:{n21,
n22,…,n2p, p1And p2Represent that two justice are former, d is p1And p2Path in adopted original hierarchical system, is a positive integer;
α is an adjustable parameter;
(1.4) similarity is set up more than the connection between the word of given threshold value λ, complete the construction of emotion co-occurrence figure;λ is selected
0.6。
3. the online incident detection method of a kind of microblogging based on sentiment analysis and label according to claim 1, its
It is characterised by, in described step (3), comprises the steps of:
(3.1) label to extracting carries out part-of-speech tagging, removes the label of the only label of verb or only one of which noun;
(3.2) weed out the label containing additional character in label;
(3.3) weed out containing standard date format, only have the label of numeral and punctuation mark.
4. the online incident detection method of a kind of microblogging based on sentiment analysis and label according to claim 1, its
It is characterised by, comprises the following steps in described step (4):
(4.1) word segmentation processing is carried out to remaining label in burst period;
(4.2) calculate the frequent mode in burst period about microblog label keyword;
(4.3) 2 item collections in frequent mode are extracted, the mutual information between word in 2 item collection is calculated;
(4.4) retain morphology of the mutual information more than given threshold value γ into final event description;The value of γ selects 1.5;
In step 4.4, mutual information computing formula is:
C(W1) and C (W2) respectively represent corpus in contain W1And W2Microblogging quantity, C (W1,W2) represent and contain W simultaneously1And W2
Microblogging quantity;Scales of the R for corpus, i.e. microblogging sum.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610945406.6A CN106547875B (en) | 2016-11-02 | 2016-11-02 | Microblog online emergency detection method based on emotion analysis and label |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610945406.6A CN106547875B (en) | 2016-11-02 | 2016-11-02 | Microblog online emergency detection method based on emotion analysis and label |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106547875A true CN106547875A (en) | 2017-03-29 |
CN106547875B CN106547875B (en) | 2020-05-15 |
Family
ID=58393729
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610945406.6A Active CN106547875B (en) | 2016-11-02 | 2016-11-02 | Microblog online emergency detection method based on emotion analysis and label |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106547875B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107886442A (en) * | 2017-11-28 | 2018-04-06 | 合肥工业大学 | Public's emotion distribution modeling method and device based on microblogging text |
CN109189910A (en) * | 2018-09-18 | 2019-01-11 | 哈尔滨工程大学 | A kind of label auto recommending method towards mobile application problem report |
CN109783800A (en) * | 2018-12-13 | 2019-05-21 | 北京百度网讯科技有限公司 | Acquisition methods, device, equipment and the storage medium of emotion keyword |
CN109977231A (en) * | 2019-04-10 | 2019-07-05 | 上海海事大学 | A kind of depressive emotion analysis method based on emotion decay factor |
JP2019144905A (en) * | 2018-02-21 | 2019-08-29 | 富士通株式会社 | Information processing program, message analysis program, information processor, and information processing method |
CN110990592A (en) * | 2019-11-07 | 2020-04-10 | 北京科技大学 | Microblog burst topic online detection method and detection device |
CN111950273A (en) * | 2020-07-31 | 2020-11-17 | 南京莱斯网信技术研究院有限公司 | Network public opinion emergency automatic identification method based on emotion information extraction analysis |
CN112084333A (en) * | 2020-08-31 | 2020-12-15 | 杭州电子科技大学 | Social user generation method based on emotional tendency analysis |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103246728A (en) * | 2013-05-10 | 2013-08-14 | 北京大学 | Emergency detection method based on document lexical feature variations |
CN103559233A (en) * | 2012-10-29 | 2014-02-05 | 中国人民解放军国防科学技术大学 | Extraction method for network new words in microblogs and microblog emotion analysis method and system |
CN104573031A (en) * | 2015-01-14 | 2015-04-29 | 哈尔滨工业大学深圳研究生院 | Micro blog emergency detection method |
CN105224604A (en) * | 2015-09-01 | 2016-01-06 | 天津大学 | A kind of microblogging incident detection method based on heap optimization and pick-up unit thereof |
CN105718598A (en) * | 2016-03-07 | 2016-06-29 | 天津大学 | AT based time model construction method and network emergency early warning method |
-
2016
- 2016-11-02 CN CN201610945406.6A patent/CN106547875B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103559233A (en) * | 2012-10-29 | 2014-02-05 | 中国人民解放军国防科学技术大学 | Extraction method for network new words in microblogs and microblog emotion analysis method and system |
CN103246728A (en) * | 2013-05-10 | 2013-08-14 | 北京大学 | Emergency detection method based on document lexical feature variations |
CN104573031A (en) * | 2015-01-14 | 2015-04-29 | 哈尔滨工业大学深圳研究生院 | Micro blog emergency detection method |
CN105224604A (en) * | 2015-09-01 | 2016-01-06 | 天津大学 | A kind of microblogging incident detection method based on heap optimization and pick-up unit thereof |
CN105718598A (en) * | 2016-03-07 | 2016-06-29 | 天津大学 | AT based time model construction method and network emergency early warning method |
Non-Patent Citations (1)
Title |
---|
张鲁民等: ""一种基于情感符号的在线突发事件检测方法"", 《计算机学报》 * |
Cited By (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107886442A (en) * | 2017-11-28 | 2018-04-06 | 合肥工业大学 | Public's emotion distribution modeling method and device based on microblogging text |
JP7091700B2 (en) | 2018-02-21 | 2022-06-28 | 富士通株式会社 | Information processing program, message analysis program, information processing device and information processing method |
JP2019144905A (en) * | 2018-02-21 | 2019-08-29 | 富士通株式会社 | Information processing program, message analysis program, information processor, and information processing method |
CN109189910A (en) * | 2018-09-18 | 2019-01-11 | 哈尔滨工程大学 | A kind of label auto recommending method towards mobile application problem report |
CN109189910B (en) * | 2018-09-18 | 2019-09-10 | 哈尔滨工程大学 | A kind of label auto recommending method towards mobile application problem report |
CN109783800A (en) * | 2018-12-13 | 2019-05-21 | 北京百度网讯科技有限公司 | Acquisition methods, device, equipment and the storage medium of emotion keyword |
CN109783800B (en) * | 2018-12-13 | 2024-04-12 | 北京百度网讯科技有限公司 | Emotion keyword acquisition method, device, equipment and storage medium |
CN109977231A (en) * | 2019-04-10 | 2019-07-05 | 上海海事大学 | A kind of depressive emotion analysis method based on emotion decay factor |
CN110990592A (en) * | 2019-11-07 | 2020-04-10 | 北京科技大学 | Microblog burst topic online detection method and detection device |
CN110990592B (en) * | 2019-11-07 | 2023-06-23 | 北京科技大学 | Online microblog burst topic detection method and detection device |
CN111950273B (en) * | 2020-07-31 | 2023-09-01 | 南京莱斯网信技术研究院有限公司 | Automatic network public opinion emergency identification method based on emotion information extraction analysis |
CN111950273A (en) * | 2020-07-31 | 2020-11-17 | 南京莱斯网信技术研究院有限公司 | Network public opinion emergency automatic identification method based on emotion information extraction analysis |
CN112084333B (en) * | 2020-08-31 | 2022-04-22 | 杭州电子科技大学 | Social user generation method based on emotional tendency analysis |
CN112084333A (en) * | 2020-08-31 | 2020-12-15 | 杭州电子科技大学 | Social user generation method based on emotional tendency analysis |
Also Published As
Publication number | Publication date |
---|---|
CN106547875B (en) | 2020-05-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106547875A (en) | A kind of online incident detection method of the microblogging based on sentiment analysis and label | |
CN109800310B (en) | Electric power operation and maintenance text analysis method based on structured expression | |
CN104199972B (en) | A kind of name entity relation extraction and construction method based on deep learning | |
CN104778209B (en) | A kind of opining mining method for millions scale news analysis | |
Akaichi et al. | Text mining facebook status updates for sentiment classification | |
CN104008091B (en) | A kind of network text sentiment analysis method based on emotion value | |
CN108363725B (en) | Method for extracting user comment opinions and generating opinion labels | |
CN103500175B (en) | A kind of method based on sentiment analysis on-line checking microblog hot event | |
CN104268160A (en) | Evaluation object extraction method based on domain dictionary and semantic roles | |
CN105045857A (en) | Social network rumor recognition method and system | |
CN104281653A (en) | Viewpoint mining method for ten million microblog texts | |
CN103218444A (en) | Method of Tibetan language webpage text classification based on semanteme | |
CN105183717A (en) | OSN user emotion analysis method based on random forest and user relationship | |
CN114579833B (en) | Microblog public opinion visual analysis method based on topic mining and emotion analysis | |
CN102436480B (en) | Incidence relation excavation method for text-oriented knowledge unit | |
CN104199845B (en) | Line Evaluation based on agent model discusses sensibility classification method | |
CN106126502A (en) | A kind of emotional semantic classification system and method based on support vector machine | |
CN105843796A (en) | Microblog emotional tendency analysis method and device | |
CN115017303A (en) | Method, computing device and medium for enterprise risk assessment based on news text | |
CN107463703A (en) | English social media account number classification method based on information gain | |
CN102073646A (en) | Blog group-oriented subject propensity processing method and system | |
CN103455639A (en) | Method and device for recognizing microblog burst hotspot events | |
Bouchlaghem et al. | A machine learning approach for classifying sentiments in Arabic tweets | |
CN109857869A (en) | A kind of hot topic prediction technique based on Ap increment cluster and network primitive | |
CN110019820A (en) | Main suit and present illness history symptom Timing Coincidence Detection method in a kind of case history |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |