CN103544321A - Data processing method and device for micro-blog emotion information - Google Patents
Data processing method and device for micro-blog emotion information Download PDFInfo
- Publication number
- CN103544321A CN103544321A CN201310548148.4A CN201310548148A CN103544321A CN 103544321 A CN103544321 A CN 103544321A CN 201310548148 A CN201310548148 A CN 201310548148A CN 103544321 A CN103544321 A CN 103544321A
- Authority
- CN
- China
- Prior art keywords
- data
- microblogging
- content
- sentiment analysis
- emotion
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
Abstract
The invention discloses a data processing method and device for micro-blog emotion information. The data processing method for micro-blog emotion information includes the steps: acquiring text content data of a micro-blog; analyzing emotion of the text content data based on a natural language processing method to obtain emotion analysis data; outputting the emotion analysis data. As the acquired text content data of the micro-blog are not limited to specific micro-blog users, the text content of the micro-blog of an optional micro-blog user can be analyzed. By the data processing method, micro-blog emotion analysis is no longer limited to the specific micro-blog users.
Description
Technical field
The present invention relates to internet arena, in particular to a kind of data processing method for microblogging emotion information and device.
Background technology
Miniature blog (MicroBlog, be called for short microblogging), be one based on customer relationship Information Sharing, the platform propagating and obtain.User can express own to the view of some things and emotion by microblogging, user often has certain tendentiousness in the emotion of expressing oneself.
By the analysis to the emotion of microblogging, can understand the view of people to the service of some and product.No matter as government or enterprise, the important evidence of understanding these emotions of user and using these as microblog users, himself being approved, by understand people in the emotion embodying in microblogging, this is used, Improving Government or enterprise are in people's image in the heart effectively.
The existing product relevant to microblogging emotion and application can only be accomplished to calculate its emotion tendency for the microblogging content of specific user's generation, in order to represent the emotion of such customer group, the analysis of microblogging emotion are had to certain limitation.
For the analysis of microblogging emotion being had to certain circumscribed problem in prior art, effective solution is not yet proposed at present.
Summary of the invention
Fundamental purpose of the present invention is to provide a kind of data processing method for microblogging emotion information and device, to solve, the analysis of microblogging emotion is had to certain circumscribed problem.
To achieve these goals, according to an aspect of the present invention, provide a kind of data processing method for microblogging emotion information.Data processing method for microblogging emotion information according to the present invention comprises: the content of text data of obtaining microblogging; Based on natural language processing method, 13754 content of text data are carried out to sentiment analysis, obtain sentiment analysis data; Export 13754 sentiment analysis data.
Further, this data processing method also comprises: the user profile data of obtaining 13754 microbloggings.After obtaining 13754 user profile data and obtaining 13754 sentiment analysis data, 13754 data processing methods also comprise: store 13754 user profile data and 13754 sentiment analysis data; And, set up the corresponding relation of 13754 user profile data and 13754 sentiment analysis data.Exporting 13754 sentiment analysis data comprises: obtain user corresponding to 13754 user profile data; Export the sentiment analysis data corresponding with 13754 users, or, emotion information corresponding to 13754 sentiment analysis data obtained; Export the user profile corresponding with 13754 emotion informations.
Further, the content of text data of obtaining microblogging comprise: the content of text of 13754 microbloggings is carried out to pre-service to remove the predetermined information in 13754 microbloggings, and wherein, 13754 predetermined informations are predefined and the incoherent information of emotion information; Extracting pre-service content of text afterwards usings as 13754 content of text data.
Further, based on natural language processing method, 13754 content of text data are carried out to sentiment analysis, obtaining sentiment analysis data comprises: load predefined emotion dictionary, wherein, 13754 emotion dictionaries are for 13754 content of text data being carried out according to natural language processing method the dictionary of sentiment analysis; 13754 content of text data and the data in 13754 emotion dictionaries are carried out to matching treatment to obtain sentiment analysis data corresponding to 13754 content of text data.
Further, 13754 content of text data and the data in 13754 emotion dictionaries being carried out to matching treatment comprises to obtain sentiment analysis data corresponding to 13754 content of text data: 13754 microbloggings are carried out to word segmentation processing; Participle lexical data in microblogging after retrieval participle; According to predefined code of points successively to the participle lexical data the retrieving processing of marking; Score data to the 13754 participle lexical datas that retrieve gathers, and obtains the sentiment analysis data that 13754 microbloggings are corresponding.
To achieve these goals, according to a further aspect in the invention, provide a kind of data processing equipment for microblogging emotion information.Data processing equipment for microblogging emotion information according to the present invention comprises: the first acquiring unit, for obtaining the content of text data of microblogging; Analytic unit, for based on natural language processing method, 13754 content of text data being carried out to sentiment analysis, obtains sentiment analysis data; Output unit, for exporting 13754 sentiment analysis data.
Further, 13754 data processing equipments also comprise: second acquisition unit, for obtaining the user profile data of 13754 microbloggings; Storage unit, for after obtaining 13754 user profile data and obtaining 13754 sentiment analysis data, stores 13754 user profile data and 13754 sentiment analysis data; Set up unit, for setting up the corresponding relation of 13754 user profile data and 13754 sentiment analysis data, wherein, 13754 output units are for obtaining user corresponding to 13754 user profile data the output sentiment analysis data corresponding with 13754 users, or, obtain emotion information corresponding to 13754 sentiment analysis data the output user profile corresponding with 13754 emotion informations.
Further, 13754 first acquiring units comprise: pretreatment module, for the content of text of 13754 microbloggings is carried out to pre-service to remove the predetermined information of 13754 microbloggings, wherein, 13754 predetermined informations are predefined and the incoherent information of emotion information; Extraction module, usings as 13754 content of text data for extracting pre-service content of text afterwards.
Further, 13754 analytic units comprise: load-on module, and for loading predefined emotion dictionary, wherein, 13754 emotion dictionaries are for 13754 content of text data being carried out according to natural language processing method the dictionary of sentiment analysis; Matching module, for carrying out 13754 content of text data and the data of 13754 emotion dictionaries matching treatment to obtain sentiment analysis data corresponding to 13754 content of text data.
Further, 13754 matching modules comprise: participle submodule, for 13754 microbloggings are carried out to word segmentation processing; Retrieval submodule, for retrieving the participle lexical data of the microblogging after participle; Scoring submodule, for according to predefined code of points successively to the participle lexical data the retrieving processing of marking; Gather submodule, for the score data of the 13754 participle lexical datas that retrieve is gathered, obtain the sentiment analysis data that 13754 microbloggings are corresponding.
By the present invention, adopt the data processing method for microblogging emotion information to comprise: the content of text data of obtaining microblogging; Based on natural language processing method, content of text data are carried out to sentiment analysis, obtain sentiment analysis data; And output sentiment analysis data, because the content of text data of the microblogging obtaining are not limited to specific microblog users, thereby can analyze the content of text of the microblogging of any microblog users, solved the analysis of microblogging emotion has been had to certain circumscribed problem, and then reached the effect that the analysis of microblogging emotion is not limited to specific microblog users.
Accompanying drawing explanation
The accompanying drawing that forms the application's a part is used to provide a further understanding of the present invention, and schematic description and description of the present invention is used for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 is according to the structural representation of the data processing equipment for microblogging emotion information of first embodiment of the invention;
Fig. 2 is according to the structural representation of the data processing equipment for microblogging emotion information of second embodiment of the invention
Fig. 3 is according to the structural representation of the data processing equipment for microblogging emotion information of third embodiment of the invention
Fig. 4 is according to the process flow diagram of the data processing method for microblogging emotion information of first embodiment of the invention;
Fig. 5 is according to the process flow diagram of the data processing method for microblogging emotion information of second embodiment of the invention; And
Fig. 6 is according to the process flow diagram of the data processing method for microblogging emotion information of third embodiment of the invention;
Embodiment
It should be noted that, in the situation that not conflicting, embodiment and the feature in embodiment in the application can combine mutually.Describe below with reference to the accompanying drawings and in conjunction with the embodiments the present invention in detail.
The embodiment of the present invention provides a kind of data processing equipment for microblogging emotion information, and this device can be realized its function by computer equipment.
Fig. 1 is according to the structural representation of the data processing equipment for microblogging emotion information of first embodiment of the invention.As shown in Figure 1, should comprise the first acquiring unit 10, analytic unit 20 and output unit 30 for the data processing equipment of microblogging emotion information.
The first acquiring unit 10 is for obtaining the content of text data of microblogging.Every microblogging all includes microblogging content of text accordingly, and the first acquiring unit 10, for obtaining the content of text data that microblogging is corresponding, can be in the same period, the content of text data of the microblogging of all microblog users, and the wall scroll microblogging of take obtains as unit.The interface that can provide by microblogging service provider that obtains of the content of text data of microblogging obtains, or obtain by web crawlers, for example, content of text data for Sina's microblogging, can use the third party of Sina to apply api interface and carry out data acquisition to get microblogging content of text data, concrete, can obtain public microblogging https in GET request mode: the information on //api.weibo.com/2/statuses/public_timeline.json, and request OAuth2.0 agreement mandate and return recording entry data parameter be set, the access rights that just can provide according to third party's application are when the time comes sent request of data, obtain the content of text data of Sina's microblogging.The content of text data that the first acquiring unit 10 obtains also comprise the related data that text content is corresponding, for example the number of times being forwarded of the content of text of this microblogging, the number of times of being commented on and time of sending etc.
Analytic unit 20, for content of text data being carried out to sentiment analysis based on natural language processing method, obtains sentiment analysis data.Because microblog users is when delivering microblogging, can in the content of text of microblogging, express some the emotion tendencies of oneself, by content of text data are carried out to sentiment analysis, thereby obtain the sentiment analysis data of microblogging, these sentiment analysis data can be for reflecting user's emotion value emotion tendency and emotion tendency, the positive negativity of this emotion value represents the tendentiousness of the emotion of microblog users, for example, when emotion value is-2, the emotion that shows this microblogging is negative emotion, wherein, the absolute value 2 of emotion value represents the intensity of this negative emotion.According to these sentiment analysis data, can obtain the emotion tendency of microblog users, for example, based on natural language processing method, the content of text in content of text data is carried out to participle, obtain in content of text the vocabulary with emotion color, for example, the vocabulary of positive positive emotion such as like, glad, or the vocabulary of the negative passive emotion such as disagreeable, gloomy, based on these vocabulary with emotion color, can understand the tendentiousness of some emotions of microblog users, and the tendentious degree of emotion.
Output unit 30 is for exporting sentiment analysis data.By the output of sentiment analysis data, can microblog users colony be dissected for the sentiment analysis data by microblogging.Using the relevant information of the emotion of microblogging and microblog users as same dimension, for example, by the sentiment analysis data of microblogging and the geographic position of microblog users, the time of microblogging issue is as same dimension, can analyze and obtain within this period, the emotion tendency of this microblog users colony, or the emotion tendency of a certain geographic area Nei， microblog users colony etc.
According to the embodiment of the present invention, by to obtaining the content of text data of microblogging, and to content of text data analysis, obtain exporting this sentiment analysis data after sentiment analysis data, because the microblogging content of text obtaining can be the microblogging content of text data at microblogging service provider's full station, to analyze microblogging content of text data, be not limited to the user group of a certain particular category, solution has certain circumscribed problem to the analysis of microblogging emotion, and then has reached the effect that the analysis of microblogging emotion is not limited to specific microblog users.Further, an attribute of the content of text using sentiment analysis data as microblogging, the sentiment analysis data of microblogging are placed in same dimension with the relevant information of other microblog users, and then have reached data based on the microblogging emotion information effect of carrying out various dimensions anatomy to any microblog users colony.
Fig. 2 is according to the structural representation of the data processing equipment for microblogging emotion information of second embodiment of the invention.This embodiment can be used as a kind of preferred implementation of above-described embodiment.As shown in Figure 2, should comprise the first acquiring unit 10, analytic unit 20, output unit 30, second acquisition unit 40, storage unit 50 and set up unit 60 for the data processing equipment of microblogging emotion information.The first acquiring unit 10 is identical with analytic unit 20 functions with the first acquiring unit 10 shown in Fig. 1 with analytic unit 20, does not repeat here.
Second acquisition unit 40 is for obtaining the user profile data of microblogging.The user profile data of microblogging are and user-dependent information data, for example, this user's sex, age, registration area, be concerned quantity, bean vermicelli number, microblogging number, intelligent's information, famous person's information, class information, personality label etc., the interface that the user profile data of this microblogging can provide by microblogging service provider obtains, or obtain by web crawlers, for example, user profile data for Sina's microblogging, can use the third party of Sina to apply api interface and carry out data acquisition to get the user profile data of microblogging, concrete, can obtain public microblogging https in GET request mode: the information on //api.weibo.com/2/statuses/public_timeline.json, and request OAuth2.0 agreement mandate and return recording entry data parameter be set, the access rights that just can provide according to third party's application are when the time comes sent request of data, obtain the user profile data of Sina's microblogging.
Storage unit 50 for obtain user profile data and obtain sentiment analysis data after, storing subscriber information data and sentiment analysis data.For user profile data and obtain sentiment analysis data, can take wall scroll microblogging as unit stores, be stored in predetermined database.Wherein, in storage unit 50, the data of storage also comprise the data that the content of text corresponding to it is relevant, as keyword, emotion value, emotional semantic classification, forwarding number, comment on number, send the time etc.For example, in storage unit 50, the data of storage can be as shown in table 1.
Table 1:
| Microblogging table | Subscriber's meter | Contingency table |
| MID | UID | MID |
| Text | The pet name | UID |
| Emotion tendency score | Registration geographic position | ? |
| Issuing time | Pay close attention to number, bean vermicelli number, microblogging number | ? |
| Issue source | User type | ? |
| …… | …… | ? |
In table 1, microblogging table is used for storing microblogging related data, and subscriber's meter is used for storing microblog users related data, and MID represents the numbering of microblogging, and UID represents the numbering of microblog users.
Set up unit 60 for setting up the corresponding relation of user profile data and sentiment analysis data.User profile data after storage and obtain setting up between sentiment analysis data corresponding relation, thereby microblog users is associated with microblogging, so that the relevant information of the relevant information based on microblog users and microblogging is carried out multi dimensional analysis to microblogging colony, wherein the relevant information of microblogging comprises the sentiment analysis data of microblogging content of text data and relevant content data corresponding to content of text etc.In contingency table, represent to set up the numbering of microblogging and the numbering of microblog users of corresponding relation, for example MID under contingency table and UID in table 1.
Output unit 30 is also exported the sentiment analysis data corresponding with user for obtaining user corresponding to user profile data, or, obtain emotion information corresponding to sentiment analysis data the output user profile corresponding with emotion information.After setting up the corresponding relation of user profile data and sentiment analysis data, output unit 30 can be for obtaining user corresponding to user profile data the output sentiment analysis data corresponding with user, this user can be the microblog users of any colony, wherein sentiment analysis data can be the sentiment analysis data corresponding to microblog users of any colony, for analyzing the microblog users of any colony.Output unit 30 can also be for obtaining emotion information corresponding to sentiment analysis data the output user profile corresponding with emotion information, the information that emotion information corresponding to sentiment analysis data is reflection user's emotion.By output unit 30 output sentiment analysis data or output with the emotion information corresponding user profile corresponding with user, so that the data of storage unit 50 storages are carried out to the analysis of various dimensions.
Preferably, storing subscriber information data and obtain sentiment analysis data and set up user profile data and the corresponding relation of sentiment analysis data after, can carry out various dimensions anatomy to the database data of storage, can be by selecting different sets of fields arbitrarily to carry out data anatomy, and according to the data type of user-selected number certificate, be the difference in continuity, discrete type, time series or geographic position, the operational fundamental figure masterplate of Intelligent Matching carries out visual demonstration.In addition, can also increase the dimension of analyzing by the various ways such as color, shape or hierarchical drawing of figure are set, thereby reach the effect that various dimensions dissect.For example, the emotion tendency score in his-and-hers watches 1, three dimensions of issuing time and issue source dissect, and show by figure, represent different time sections, the tendentiousness of the emotion of different geographic area microblog users.
Preferably, the first acquiring unit 10 comprises pretreatment module and extraction module.
Pretreatment module is for carrying out pre-service to remove the predetermined information of microblogging to the content of text of microblogging, wherein, predetermined information is predefined and the incoherent information of emotion information.This predetermined information can be incoherent or affect the information of microblogging sentiment analysis with emotion information in the content of text of microblogging, also can be called nonstandard part in microblogging, for example, content between "@+user name ", short connection, topic symbol ## etc., these are all the information that can affect microblogging sentiment analysis, and the content that does not comprise the statement objective fact of obvious emotion in content of text.Such predetermined information can be the predefined text with specific format, this category information is removed, so that content of text is carried out to sentiment analysis.
Extraction module is usingd as content of text data for extracting pre-service content of text afterwards.Extract to remove and the incoherent information of emotion information or the information that affect microblogging sentiment analysis content of text afterwards, using text content as content of text data, so that text content-data is carried out to sentiment analysis.
According to the embodiment of the present invention, by the content of text of microblogging is carried out to pre-service, remove with the incoherent information of emotion information or affect the information of microblogging sentiment analysis, thus the accuracy of raising to the sentiment analysis of content of text data.
Fig. 3 is according to the structural representation of the data processing equipment for microblogging emotion information of third embodiment of the invention.This embodiment can be used as a kind of preferred implementation of above-described embodiment.As shown in Figure 3, should comprise the first acquiring unit 10, analytic unit 20 and output unit 30 for the data processing equipment of microblogging emotion information, wherein, analytic unit 20 comprises load-on module 201 and matching module 202.The first acquiring unit 10 is identical with output unit 30 functions with the first acquiring unit 10 shown in Fig. 1 with output unit 30, does not repeat here.
Load-on module 201 is for loading predefined emotion dictionary, and wherein, emotion dictionary is for content of text data being carried out according to natural language processing method the dictionary of sentiment analysis.This sentiment dictionary can comprise: positive negative affect word dictionary, negative word dictionary, degree word dictionary, microblogging expression dictionary etc., wherein, in positive negative affect word dictionary, include positive positive vocabulary and negative passive vocabulary, for matched text content-data, whether there is positive positive vocabulary or negative passive vocabulary, such as " happiness " or " sad " etc.; In negative word dictionary, include the vocabulary with negative implication, for matched text content-data, whether have negative word, such as " no ", " non-" etc.; The vocabulary that includes expression degree in degree word dictionary, for representing the degree of microblogging content emotion, such as " very ", " very " etc.; In microblogging expression dictionary, include for representing the vocabulary of microblogging expression, such as " giggle ", " heartily " etc.
Matching module 202 is for carrying out content of text data and the data of emotion dictionary matching treatment to obtain sentiment analysis data corresponding to content of text data.Content of text data are mated with each sentiment dictionary in above-mentioned, or in above-mentioned sentiment dictionary, content of text data are retrieved, if coupling or retrieve corresponding vocabulary, can judge the emotion tendency of microblog users according to retrieval or the corresponding vocabulary matching, thereby obtain the sentiment analysis data corresponding with content of text data.
Preferably, matching module comprises: participle submodule, retrieve submodule, the submodule and gather submodule of marking.
Participle submodule is for carrying out word segmentation processing to microblogging.First to carry out subordinate sentence processing to content of text, then by participle submodule, the sentence of microblogging content of text be carried out to participle, the word after participle is carried out to part-of-speech tagging, thereby extract adjective, noun, verb and adverbial word in sentence.So that the word in content of text is mated with sentiment dictionary.
Retrieval submodule is for retrieving the participle lexical data of the microblogging after participle.Retrieval submodule is for retrieving the participle lexical data in microblogging at sentiment dictionary, and participle lexical data comprises each word that carries out participle after microblogging content of text subordinate sentence.For example, microblogging expression word in participle lexical data is retrieved, coupling microblogging expression dictionary, positive vocabulary positive in participle lexical data or negative passive vocabulary are retrieved, mate positive negative affect word dictionary, negative word in participle lexical data is retrieved, coupling negative word dictionary, Chengdu word in participle lexical data is retrieved to matching degree word dictionary.
Scoring submodule for according to predefined code of points successively to the participle lexical data the retrieving processing of marking.Predefined code of points is to preset corresponding standards of grading, when the microblogging expression word in participle lexical data is retrieved, coupling microblogging expression dictionary, each microblogging expression word is in predefined code of points, all preset corresponding polarity and intensity, wherein, polarity is for judging that microblogging expression word is positive positive expression word or the expression word of negative passiveness, intensity represent the to express one's feelings degree of emotion of word, for example, when retrieving word " heartily ", scoring can be 2, " 2 " represent the expression word that true face is positive for positive number, the degree of the emotion of this expression word of 2 value representation, the positive face amount of note microblogging expression word is PosiExpressionSum, negative value is NegaExpressionSum.Positive vocabulary positive in participle lexical data or negative passive vocabulary are retrieved, mate positive negative affect word dictionary, if word appears in dictionary in text, carry out mark, the vocabulary of mark is got to corresponding intensity according to predefined code of points, as get 1.Coupling negative word dictionary and degree word dictionary, if match negative word, the intensity by the vocabulary by positive negative affect word dictionary matching of mark is multiplied by-1, if match degree word, get the intensity (intensity as corresponding in " very " is 3) of this degree word, then the intensity that the intensity of the vocabulary of positive negative affect word dictionary matching is multiplied by degree word is obtained to final front mark score is designated as PosiSenSum and negative mark score is designated as NegaSenSum.
Gather submodule and gather for the score data of the participle lexical data to retrieving, obtain the sentiment analysis data that microblogging is corresponding.Score data after the scoring of scoring submodule is gathered, the corresponding microblogging emotion tendency of note sentiment analysis data must be divided into weiboOrientation=PosiSenSum+PosiExpressionSum – NegaSenSum – NegaExpressionSum, the symbol direction of weiboOrientation represents microblogging tendentiousness direction, and the size of absolute value represents the intensity in direction.
The embodiment of the present invention also provides a kind of data processing method for microblogging emotion information.The method operates on computer equipment.It should be noted that, the data processing equipment for microblogging emotion information that the data processing method for microblogging emotion information of the embodiment of the present invention can provide by the embodiment of the present invention is carried out, the data processing method for microblogging emotion information that the data processing equipment for microblogging emotion information of the embodiment of the present invention also can provide for carrying out the embodiment of the present invention.
Fig. 4 is according to the process flow diagram of the data processing method for microblogging emotion information of first embodiment of the invention.As shown in Figure 4, should comprise that step was as follows for the data processing method of microblogging emotion information:
Step S101, obtains the content of text data of microblogging.Every microblogging all includes microblogging content of text accordingly, obtains the content of text data that microblogging is corresponding, can be in the same period, the content of text data of the microblogging of all microblog users, and the wall scroll microblogging of take obtains as unit.The interface that can provide by microblogging service provider that obtains of the content of text data of microblogging obtains, or obtain by web crawlers, for example, content of text data for Sina's microblogging, can use the third party of Sina to apply api interface and carry out data acquisition to get microblogging content of text data, concrete, can obtain public microblogging https in GET request mode: the information on //api.weibo.com/2/statuses/public_timeline.json, and request OAuth2.0 agreement mandate and return recording entry data parameter be set, the access rights that just can provide according to third party's application are when the time comes sent request of data, obtain the content of text data of Sina's microblogging.The content of text data of obtaining can also comprise the related data that text content is corresponding, for example the number of times being forwarded of the content of text of this microblogging, the number of times of being commented on and time of sending etc.
Step S102, carries out sentiment analysis based on natural language processing method to content of text data, obtains sentiment analysis data.Because microblog users is when delivering microblogging, can in the content of text of microblogging, express some the emotion tendencies of oneself, by content of text data are carried out to sentiment analysis, thereby obtain the sentiment analysis data of microblogging, these sentiment analysis data can be for reflecting user's emotion value emotion tendency and emotion tendency, the positive negativity of this emotion value represents the tendentiousness of the emotion of microblog users, for example, when emotion value is-2, the emotion that shows this microblogging is negative emotion, wherein, the absolute value 2 of emotion value represents the intensity of this negative emotion.According to these sentiment analysis data, can obtain the emotion tendency of microblog users, for example, based on natural language processing method, the content of text in content of text data is carried out to participle, obtain in content of text the vocabulary with emotion color, for example, the vocabulary of positive positive emotion such as like, glad, or the vocabulary of the negative passive emotion such as disagreeable, gloomy, based on these vocabulary with emotion color, can understand the tendentiousness of some emotions of microblog users, and the tendentious degree of emotion.
Step S103, output sentiment analysis data.By the output of sentiment analysis data, can microblog users colony be dissected for the sentiment analysis data by microblogging.Using the relevant information of the emotion of microblogging and microblog users as same dimension, for example, by the sentiment analysis data of microblogging and the geographic position of microblog users, the time of microblogging issue is as same dimension, can analyze and obtain within this period, the emotion tendency of this microblog users colony, or the emotion tendency of a certain geographic area Nei， microblog users colony etc.
According to the embodiment of the present invention, by to obtaining the content of text data of microblogging, and to content of text data analysis, obtain exporting this sentiment analysis data after sentiment analysis data, because the microblogging content of text obtaining can be the microblogging content of text data at microblogging service provider's full station, to analyze microblogging content of text data, be not limited to the user group of a certain particular category, solution has certain circumscribed problem to the analysis of microblogging emotion, and then has reached the effect that the analysis of microblogging emotion is not limited to specific microblog users.Further, an attribute of the content of text using sentiment analysis data as microblogging, the sentiment analysis data of microblogging are placed in same dimension with the relevant information of other microblog users, and then have reached data based on the microblogging emotion information effect of carrying out various dimensions anatomy to any microblog users colony.
Fig. 5 is according to the process flow diagram of the data processing method for microblogging emotion information of second embodiment of the invention.The data processing method for microblogging emotion information of this embodiment can be used as above-described embodiment for the data processing method of microblogging emotion information a kind of preferred implementation.As shown in Figure 5, should comprise that step was as follows for the data processing method of microblogging emotion information:
Step S201, obtains the content of text data of microblogging.Every microblogging all includes microblogging content of text accordingly, obtains the content of text data that microblogging is corresponding, can be in the same period, the content of text data of the microblogging of all microblog users, and the wall scroll microblogging of take obtains as unit.The interface that can provide by microblogging service provider that obtains of the content of text data of microblogging obtains, or obtain by web crawlers, for example, content of text data for Sina's microblogging, can use the third party of Sina to apply api interface and carry out data acquisition to get microblogging content of text data, concrete, can obtain public microblogging https in GET request mode: the information on //api.weibo.com/2/statuses/public_timeline.json, and request OAuth2.0 agreement mandate and return recording entry data parameter be set, the access rights that just can provide according to third party's application are when the time comes sent request of data, obtain the content of text data of Sina's microblogging.The content of text data of obtaining can also comprise the related data that text content is corresponding, for example the number of times being forwarded of the content of text of this microblogging, the number of times of being commented on and time of sending etc.
Preferably, step S201 can comprise step S2011 and step S2012.
Step S2011, carries out pre-service to remove the predetermined information in microblogging to the content of text of microblogging, and wherein, predetermined information is predefined and the incoherent information of emotion information.This predetermined information can be incoherent or affect the information of microblogging sentiment analysis with emotion information in the content of text of microblogging, also can be called nonstandard part in microblogging, for example, content between "@+user name ", short connection, topic symbol ## etc., these are all the information that can affect microblogging sentiment analysis, and the content that does not comprise the statement objective fact of obvious emotion in content of text.Such predetermined information can be the predefined text with specific format, this category information is removed, so that content of text is carried out to sentiment analysis.
Step S2011, extracts pre-service content of text afterwards and usings as content of text data.Extract to remove and the incoherent information of emotion information or the information that affect microblogging sentiment analysis content of text afterwards, using text content as content of text data, so that text content-data is carried out to sentiment analysis.
Step S202, carries out sentiment analysis based on natural language processing method to content of text data, obtains sentiment analysis data.Because microblog users is when delivering microblogging, can in the content of text of microblogging, express some the emotion tendencies of oneself, by content of text data are carried out to sentiment analysis, thereby obtain the sentiment analysis data of microblogging, these sentiment analysis data can be for reflecting user's emotion value emotion tendency and emotion tendency, the positive negativity of this emotion value represents the tendentiousness of the emotion of microblog users, for example, when emotion value is-2, the emotion that shows this microblogging is negative emotion, wherein, the absolute value 2 of emotion value represents the intensity of this negative emotion.According to these sentiment analysis data, can obtain the emotion tendency of microblog users, for example, based on natural language processing method, the content of text in content of text data is carried out to participle, obtain in content of text the vocabulary with emotion color, for example, the vocabulary of positive positive emotion such as like, glad, or the vocabulary of the negative passive emotion such as disagreeable, gloomy, based on these vocabulary with emotion color, can understand the tendentiousness of some emotions of microblog users, and the tendentious degree of emotion.
Step S203, obtains the user profile data of microblogging.The user profile data of microblogging are and user-dependent information data, for example, this user's sex, age, registration area, be concerned quantity, bean vermicelli number, microblogging number, intelligent's information, famous person's information, class information, personality label etc., the interface that the user profile data of this microblogging can provide by microblogging service provider obtains, or obtain by web crawlers, for example, user profile data for Sina's microblogging, can use the third party of Sina to apply api interface and carry out data acquisition to get the user profile data of microblogging, concrete, can obtain public microblogging https in GET request mode: the information on //api.weibo.com/2/statuses/public_timeline.json, and request OAuth2.0 agreement mandate and return recording entry data parameter be set, the access rights that just can provide according to third party's application are when the time comes sent request of data, obtain the user profile data of Sina's microblogging.
Step S204, storing subscriber information data and sentiment analysis data.For user profile data and obtain sentiment analysis data, can take wall scroll microblogging as unit stores, be stored in predetermined database.Wherein, in storage unit 50, the data of storage also comprise the data that the content of text corresponding to it is relevant, as keyword, emotion value, emotional semantic classification, forwarding number, comment on number, send the time etc.For example, in storage unit 50, the data of storage can be as shown in table 1.
Step S205, sets up the corresponding relation of user profile data and sentiment analysis data.User profile data after storage and obtain setting up between sentiment analysis data corresponding relation, thereby microblog users is associated with microblogging, so that the relevant information of the relevant information based on microblog users and microblogging is carried out multi dimensional analysis to microblogging colony, wherein the relevant information of microblogging comprises the sentiment analysis data of microblogging content of text data and relevant content data corresponding to content of text etc.In contingency table, represent to set up the numbering of microblogging and the numbering of microblog users of corresponding relation, for example MID under contingency table and UID in table 1.
Step S206, obtains user corresponding to user profile data, exports the sentiment analysis data corresponding with user.After setting up the corresponding relation of user profile data and sentiment analysis data, can be to obtain user corresponding to user profile data the output sentiment analysis data corresponding with user, this user can be the microblog users of any colony, wherein sentiment analysis data can be the sentiment analysis data corresponding to microblog users of any colony, for analyzing the microblog users of any colony.
Alternatively, step S205 obtains emotion information corresponding to sentiment analysis data, exports the user profile corresponding with emotion information.Obtain emotion information corresponding to sentiment analysis data the output user profile corresponding with emotion information, the information that emotion information corresponding to sentiment analysis data is reflection user's emotion.By output sentiment analysis data or output with the emotion information corresponding user profile corresponding with user, so that the data of storage unit 50 storages are carried out to the analysis of various dimensions.
Preferably, storing subscriber information data and obtain sentiment analysis data and set up user profile data and the corresponding relation of sentiment analysis data after, can carry out various dimensions anatomy to the database data of storage, can be by selecting different sets of fields arbitrarily to carry out data anatomy, and according to the data type of user-selected number certificate, be the difference in continuity, discrete type, time series or geographic position, the operational fundamental figure masterplate of Intelligent Matching carries out visual demonstration.In addition, can also increase the dimension of analyzing by the various ways such as color, shape or hierarchical drawing of figure are set, thereby reach the effect that various dimensions dissect.For example, the emotion tendency score in his-and-hers watches 1, three dimensions of issuing time and issue source dissect, and show by figure, represent different time sections, the tendentiousness of the emotion of different geographic area microblog users.
Fig. 6 is according to the process flow diagram of the data processing method for microblogging emotion information of third embodiment of the invention.The data processing method for microblogging emotion information of this embodiment can be used as a kind of preferred implementation of above-described embodiment.As shown in Figure 6, should comprise that step was as follows for the data processing method of microblogging emotion information:
Step S301, obtains the content of text data of microblogging.Every microblogging all includes microblogging content of text accordingly, obtains the content of text data that microblogging is corresponding, can be in the same period, the content of text data of the microblogging of all microblog users, and the wall scroll microblogging of take obtains as unit.The interface that can provide by microblogging service provider that obtains of the content of text data of microblogging obtains, or obtain by web crawlers, for example, content of text data for Sina's microblogging, can use the third party of Sina to apply api interface and carry out data acquisition to get microblogging content of text data, concrete, can obtain public microblogging https in GET request mode: the information on //api.weibo.com/2/statuses/public_timeline.json, and request OAuth2.0 agreement mandate and return recording entry data parameter be set, the access rights that just can provide according to third party's application are when the time comes sent request of data, obtain the content of text data of Sina's microblogging.The content of text data of obtaining can also comprise the related data that text content is corresponding, for example the number of times being forwarded of the content of text of this microblogging, the number of times of being commented on and time of sending etc.
Step S302, loads predefined emotion dictionary, and wherein, emotion dictionary is for text data being carried out according to natural language processing method the dictionary of sentiment analysis.This sentiment dictionary can comprise: positive negative affect word dictionary, negative word dictionary, degree word dictionary, microblogging expression dictionary etc., wherein, in positive negative affect word dictionary, include positive positive vocabulary and negative passive vocabulary, for matched text content-data, whether there is positive positive vocabulary or negative passive vocabulary, such as " happiness " or " sad " etc.; In negative word dictionary, include the vocabulary with negative implication, for matched text content-data, whether have negative word, such as " no ", " non-" etc.; The vocabulary that includes expression degree in degree word dictionary, for representing the degree of microblogging content emotion, such as " very ", " very " etc.; In microblogging expression dictionary, include for representing the vocabulary of microblogging expression, such as " giggle ", " heartily " etc.
Step S303, carries out matching treatment to obtain sentiment analysis data corresponding to content of text data by content of text data and the data in emotion dictionary.Content of text data are mated with each sentiment dictionary in above-mentioned, or in above-mentioned sentiment dictionary, content of text data are retrieved, if coupling or retrieve corresponding vocabulary, can judge the emotion tendency of microblog users according to retrieval or the corresponding vocabulary matching, thereby obtain the sentiment analysis data corresponding with content of text data.
Step S304, output sentiment analysis data.By the output of sentiment analysis data, can microblog users colony be dissected for the sentiment analysis data by microblogging.Using the relevant information of the emotion of microblogging and microblog users as same dimension, for example, by the sentiment analysis data of microblogging and the geographic position of microblog users, the time of microblogging issue is as same dimension, can analyze and obtain within this period, the emotion tendency of this microblog users colony, or the emotion tendency of a certain geographic area Nei， microblog users colony etc.
Preferably, step step S303 can comprise that step S3031 is to step S3034.
Step S3031, carries out word segmentation processing to microblogging.First to carry out subordinate sentence processing to content of text, then by participle submodule, the sentence of microblogging content of text be carried out to participle, the word after participle is carried out to part-of-speech tagging, thereby extract adjective, noun, verb and adverbial word in sentence.So that the word in content of text is mated with sentiment dictionary.
Step S3032, the participle lexical data in the microblogging after retrieval participle.Retrieval submodule is for retrieving the participle lexical data in microblogging at sentiment dictionary, and participle lexical data comprises each word that carries out participle after microblogging content of text subordinate sentence.For example, microblogging expression word in participle lexical data is retrieved, coupling microblogging expression dictionary, positive vocabulary positive in participle lexical data or negative passive vocabulary are retrieved, mate positive negative affect word dictionary, negative word in participle lexical data is retrieved, coupling negative word dictionary, Chengdu word in participle lexical data is retrieved to matching degree word dictionary.
Step S3033, according to predefined code of points successively to the participle lexical data the retrieving processing of marking.Predefined code of points is to preset corresponding standards of grading, when the microblogging expression word in participle lexical data is retrieved, coupling microblogging expression dictionary, each microblogging expression word is in predefined code of points, all preset corresponding polarity and intensity, wherein, polarity is for judging that microblogging expression word is positive positive expression word or the expression word of negative passiveness, intensity represent the to express one's feelings degree of emotion of word, for example, when retrieving word " heartily ", scoring can be 2, " 2 " represent the expression word that true face is positive for positive number, the degree of the emotion of this expression word of 2 value representation, the positive face amount of note microblogging expression word is PosiExpressionSum, negative value is NegaExpressionSum.Positive vocabulary positive in participle lexical data or negative passive vocabulary are retrieved, mate positive negative affect word dictionary, if word appears in dictionary in text, carry out mark, the vocabulary of mark is got to corresponding intensity according to predefined code of points, as get 1.Coupling negative word dictionary and degree word dictionary, if match negative word, the intensity by the vocabulary by positive negative affect word dictionary matching of mark is multiplied by-1, if match degree word, get the intensity (intensity as corresponding in " very " is 3) of this degree word, then the intensity that the intensity of the vocabulary of positive negative affect word dictionary matching is multiplied by degree word is obtained to final front mark score is designated as PosiSenSum and negative mark score is designated as NegaSenSum.
Step S3034, gathers the score data of the participle lexical data retrieving, and obtains the sentiment analysis data that microblogging is corresponding.Score data after the scoring of scoring submodule is gathered, the corresponding microblogging emotion tendency of note sentiment analysis data must be divided into weiboOrientation=PosiSenSum+PosiExpressionSum – NegaSenSum – NegaExpressionSum, the symbol direction of weiboOrientation represents microblogging tendentiousness direction, and the size of absolute value represents the intensity in direction.
It should be noted that, in the step shown in the process flow diagram of accompanying drawing, can in the computer system such as one group of computer executable instructions, carry out, and, although there is shown logical order in flow process, but in some cases, can carry out shown or described step with the order being different from herein.
Obviously, those skilled in the art should be understood that, above-mentioned each module of the present invention or each step can realize with general calculation element, they can concentrate on single calculation element, or be distributed on the network that a plurality of calculation elements form, alternatively, they can be realized with the executable program code of calculation element, thereby, they can be stored in memory storage and be carried out by calculation element, or they are made into respectively to each integrated circuit modules, or a plurality of modules in them or step are made into single integrated circuit module to be realized.Like this, the present invention is not restricted to any specific hardware and software combination.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (10)
1. for a data processing method for microblogging emotion information, it is characterized in that, comprising:
Obtain the content of text data of microblogging;
Based on natural language processing method, described content of text data are carried out to sentiment analysis, obtain sentiment analysis data; And
Export described sentiment analysis data.
2. the data processing method for microblogging emotion information according to claim 1, is characterized in that,
Described data processing method also comprises: the user profile data of obtaining described microblogging;
After obtaining described user profile data and obtaining described sentiment analysis data, described data processing method also comprises: store described user profile data and described sentiment analysis data; And, set up the corresponding relation of described user profile data and described sentiment analysis data;
Exporting described sentiment analysis data comprises: obtain user corresponding to described user profile data; Export the sentiment analysis data corresponding with described user, or, emotion information corresponding to described sentiment analysis data obtained; Export the user profile corresponding with described emotion information.
3. the data processing method for microblogging emotion information according to claim 1, is characterized in that, the content of text data of obtaining microblogging comprise:
The content of text of described microblogging is carried out to pre-service to remove the predetermined information in described microblogging, and wherein, described predetermined information is predefined and the incoherent information of emotion information;
Extracting pre-service content of text afterwards usings as described content of text data.
4. the data processing method for microblogging emotion information according to claim 1, is characterized in that, based on natural language processing method, described content of text data is carried out to sentiment analysis, obtains sentiment analysis data and comprises:
Load predefined emotion dictionary, wherein, described emotion dictionary is for described content of text data being carried out according to natural language processing method the dictionary of sentiment analysis; And
Described content of text data and the data in described emotion dictionary are carried out to matching treatment to obtain sentiment analysis data corresponding to described content of text data.
5. the data processing method for microblogging emotion information according to claim 4, it is characterized in that, described content of text data and the data in described emotion dictionary are carried out to matching treatment and to obtain sentiment analysis data corresponding to described content of text data, comprise:
Described microblogging is carried out to word segmentation processing;
Participle lexical data in microblogging after retrieval participle;
According to predefined code of points successively to the participle lexical data the retrieving processing of marking; And
Score data to the described participle lexical data retrieving gathers, and obtains the sentiment analysis data that described microblogging is corresponding.
6. for a data processing equipment for microblogging emotion information, it is characterized in that, comprising:
The first acquiring unit, for obtaining the content of text data of microblogging;
Analytic unit, for based on natural language processing method, described content of text data being carried out to sentiment analysis, obtains sentiment analysis data; And
Output unit, for exporting described sentiment analysis data.
7. the data processing equipment for microblogging emotion information according to claim 6, is characterized in that, described data processing equipment also comprises:
Second acquisition unit, for obtaining the user profile data of described microblogging;
Storage unit, for after obtaining described user profile data and obtaining described sentiment analysis data, stores described user profile data and described sentiment analysis data; And,
Set up unit, for setting up the corresponding relation of described user profile data and described sentiment analysis data,
Wherein, described output unit is for obtaining user corresponding to described user profile data the output sentiment analysis data corresponding with described user, or, obtain emotion information corresponding to described sentiment analysis data the output user profile corresponding with described emotion information.
8. the data processing equipment for microblogging emotion information according to claim 6, is characterized in that, described the first acquiring unit comprises:
Pretreatment module, for the content of text of described microblogging being carried out to pre-service to remove the predetermined information of described microblogging, wherein, described predetermined information is predefined and the incoherent information of emotion information;
Extraction module, usings as described content of text data for extracting pre-service content of text afterwards.
9. the data processing equipment for microblogging emotion information according to claim 6, is characterized in that, described analytic unit comprises:
Load-on module, for loading predefined emotion dictionary, wherein, described emotion dictionary is for described content of text data being carried out according to natural language processing method the dictionary of sentiment analysis; And
Matching module, for carrying out described content of text data and the data of described emotion dictionary matching treatment to obtain sentiment analysis data corresponding to described content of text data.
10. the data processing equipment for microblogging emotion information according to claim 9, is characterized in that, described matching module comprises:
Participle submodule, for carrying out word segmentation processing to described microblogging;
Retrieval submodule, for retrieving the participle lexical data of the microblogging after participle;
Scoring submodule, for according to predefined code of points successively to the participle lexical data the retrieving processing of marking; And
Gather submodule, for the score data of the described participle lexical data retrieving is gathered, obtain the sentiment analysis data that described microblogging is corresponding.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310548148.4A CN103544321A (en) | 2013-11-06 | 2013-11-06 | Data processing method and device for micro-blog emotion information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310548148.4A CN103544321A (en) | 2013-11-06 | 2013-11-06 | Data processing method and device for micro-blog emotion information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103544321A true CN103544321A (en) | 2014-01-29 |
Family
ID=49967773
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310548148.4A Pending CN103544321A (en) | 2013-11-06 | 2013-11-06 | Data processing method and device for micro-blog emotion information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103544321A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104090866A (en) * | 2014-07-10 | 2014-10-08 | 北京国双科技有限公司 | Method and device for processing text data |
| CN105631022A (en) * | 2015-12-29 | 2016-06-01 | 上海智臻智能网络科技股份有限公司 | Method and device for processing information |
| CN106933898A (en) * | 2015-12-31 | 2017-07-07 | 北京国双科技有限公司 | The treating method and apparatus of info web |
| CN107180095A (en) * | 2017-05-16 | 2017-09-19 | 百度在线网络技术（北京）有限公司 | Method and apparatus for exhibition information |
| CN107704763A (en) * | 2017-09-04 | 2018-02-16 | 中国移动通信集团广东有限公司 | Multi-source heterogeneous leak information De-weight method, stage division and device |
| CN107908782A (en) * | 2017-12-06 | 2018-04-13 | 陕西识代运筹信息科技股份有限公司 | A kind of data processing method and device based on sentiment analysis |
| CN108898435A (en) * | 2018-06-28 | 2018-11-27 | 北京京东尚科信息技术有限公司 | Session data processing method and system, computer system and readable storage medium storing program for executing |
| WO2019041528A1 (en) * | 2017-08-31 | 2019-03-07 | 平安科技（深圳）有限公司 | Method, electronic apparatus, and computer readable storage medium for determining polarity of news sentiment |
| CN109994207A (en) * | 2019-03-25 | 2019-07-09 | 广东邮电职业技术学院 | Mental health method for early warning, server and system |
| CN110826317A (en) * | 2019-11-07 | 2020-02-21 | 成都国腾实业集团有限公司 | Text emotion analysis method based on dictionary and rule |
| CN111312394A (en) * | 2020-01-15 | 2020-06-19 | 东北电力大学 | Psychological health condition evaluation system based on combined emotion and processing method thereof |
| CN112632361A (en) * | 2020-12-29 | 2021-04-09 | 中科院计算技术研究所大数据研究院 | Iterative data acquisition method |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120041953A1 (en) * | 2010-08-16 | 2012-02-16 | Microsoft Corporation | Text mining of microblogs using latent topic labels |
| CN102663046A (en) * | 2012-03-29 | 2012-09-12 | 中国科学院自动化研究所 | Sentiment analysis method oriented to micro-blog short text |
-
2013
- 2013-11-06 CN CN201310548148.4A patent/CN103544321A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120041953A1 (en) * | 2010-08-16 | 2012-02-16 | Microsoft Corporation | Text mining of microblogs using latent topic labels |
| CN102663046A (en) * | 2012-03-29 | 2012-09-12 | 中国科学院自动化研究所 | Sentiment analysis method oriented to micro-blog short text |
Non-Patent Citations (3)
| Title |
|---|
| 周胜臣等: "中文微博情感分析研究综述", 《计算机应用与软件》 * |
| 张鲁民等: "基于情感计算的微博突发事件检测方法研究", 《第27次全国计算机安全学术交流会论文集》 * |
| 陈晓东: "基于情感词典的中文微博情感倾向分析研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104090866A (en) * | 2014-07-10 | 2014-10-08 | 北京国双科技有限公司 | Method and device for processing text data |
| CN105631022B (en) * | 2015-12-29 | 2019-03-05 | 上海智臻智能网络科技股份有限公司 | Information processing method and device |
| CN105631022A (en) * | 2015-12-29 | 2016-06-01 | 上海智臻智能网络科技股份有限公司 | Method and device for processing information |
| CN106933898A (en) * | 2015-12-31 | 2017-07-07 | 北京国双科技有限公司 | The treating method and apparatus of info web |
| CN106933898B (en) * | 2015-12-31 | 2020-08-11 | 北京国双科技有限公司 | Webpage information processing method and device |
| CN107180095A (en) * | 2017-05-16 | 2017-09-19 | 百度在线网络技术（北京）有限公司 | Method and apparatus for exhibition information |
| WO2019041528A1 (en) * | 2017-08-31 | 2019-03-07 | 平安科技（深圳）有限公司 | Method, electronic apparatus, and computer readable storage medium for determining polarity of news sentiment |
| CN107704763A (en) * | 2017-09-04 | 2018-02-16 | 中国移动通信集团广东有限公司 | Multi-source heterogeneous leak information De-weight method, stage division and device |
| CN107908782A (en) * | 2017-12-06 | 2018-04-13 | 陕西识代运筹信息科技股份有限公司 | A kind of data processing method and device based on sentiment analysis |
| CN108898435A (en) * | 2018-06-28 | 2018-11-27 | 北京京东尚科信息技术有限公司 | Session data processing method and system, computer system and readable storage medium storing program for executing |
| CN109994207A (en) * | 2019-03-25 | 2019-07-09 | 广东邮电职业技术学院 | Mental health method for early warning, server and system |
| CN109994207B (en) * | 2019-03-25 | 2021-08-03 | 广东邮电职业技术学院 | Mental health early warning method, server and system |
| CN110826317A (en) * | 2019-11-07 | 2020-02-21 | 成都国腾实业集团有限公司 | Text emotion analysis method based on dictionary and rule |
| CN111312394A (en) * | 2020-01-15 | 2020-06-19 | 东北电力大学 | Psychological health condition evaluation system based on combined emotion and processing method thereof |
| CN111312394B (en) * | 2020-01-15 | 2023-09-29 | 东北电力大学 | Psychological health assessment system based on combined emotion and processing method thereof |
| CN112632361A (en) * | 2020-12-29 | 2021-04-09 | 中科院计算技术研究所大数据研究院 | Iterative data acquisition method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103544321A (en) | Data processing method and device for micro-blog emotion information | |
| Alwakid et al. | Challenges in sentiment analysis for Arabic social networks | |
| US10691770B2 (en) | Real-time classification of evolving dictionaries | |
| US20170017635A1 (en) | Natural language processing system and method | |
| Habernal et al. | SWSNL: semantic web search using natural language | |
| US20130263019A1 (en) | Analyzing social media | |
| WO2016199160A2 (en) | Language processing and knowledge building system | |
| US10824816B2 (en) | Semantic parsing method and apparatus | |
| CN102682120B (en) | Method and device for acquiring essential article commented on network | |
| Lloret et al. | A novel concept-level approach for ultra-concise opinion summarization | |
| Gómez-Adorno et al. | Automatic authorship detection using textual patterns extracted from integrated syntactic graphs | |
| KR102064292B1 (en) | Method and Apparatus for Recommending Personalized Social Network Service Content | |
| Susanti et al. | Twitter’s sentiment analysis on GSM services using Multinomial Naïve Bayes | |
| US20130275438A1 (en) | Disambiguating authors in social media communications | |
| CN107798622B (en) | Method and device for identifying user intention | |
| Benamara et al. | Introduction to the special issue on language in social media: exploiting discourse and other contextual information | |
| CN109992653A (en) | Information processing method and processing system | |
| CN104268192A (en) | Webpage information extracting method, device and terminal | |
| Wijeratne et al. | Natural language processing for government: Problems and potential | |
| Colhon et al. | Relating the opinion holder and the review accuracy in sentiment analysis of tourist reviews | |
| CN103150331A (en) | Method and device for providing search engine tags | |
| Arafat et al. | Analyzing public emotion and predicting stock market using social media | |
| Kim et al. | Comparing machine learning classifiers for movie WOM opinion mining | |
| Biswas et al. | Drug Usage Analysis by VADER Sentiment Analysis on Leading Countries. | |
| Yan et al. | Two Diverging roads: a semantic network analysis of chinese social connection (“guanxi”) on Twitter |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |
Application publication date: 20140129 |
|
| RJ01 | Rejection of invention patent application after publication |