CN107220241A - The user feeling analysis method and device of social networks - Google Patents
The user feeling analysis method and device of social networks Download PDFInfo
- Publication number
- CN107220241A CN107220241A CN201710581139.3A CN201710581139A CN107220241A CN 107220241 A CN107220241 A CN 107220241A CN 201710581139 A CN201710581139 A CN 201710581139A CN 107220241 A CN107220241 A CN 107220241A
- Authority
- CN
- China
- Prior art keywords
- social networks
- user
- user data
- collection
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/205—Parsing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- 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
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
Abstract
The invention discloses a kind of user feeling analysis method of social networks by first gathering the user data of social networks, that analyzes the user data again delivers content, extract the staple of conversation participated in, and obtain just negative word set, then subjective emotion collection of the user to each staple of conversation is analyzed, then emotion value technical scheme is obtained according to the just negative word set and subjective emotion collection, solve the relatively low problem of accuracy rate of existing sentiment analysis, the emotion value quantified is obtained, beneficial to the relational hierarchy that emotion value is integrated into acquisition social networks in relationship analysis network.
Description
Technical field
The present invention relates to the user feeling analysis method and dress of computer network field, more particularly to a kind of social networks
Put.
Background technology
In the last few years, sentiment analysis technology turned into the hot issue of natural language processing research field, sentiment analysis
Target is that the viewpoint and feeling polarities of user's expression are excavated from text, excavates Sentiment orientation in text and can be used for helping other
User makes a decision.Therefore sentiment analysis technology has obtained the concern of numerous researchers in natural language processing research field, has
Very big application value.At present, sentiment analysis is carried out as feature according to all words occurred in training text, and it is special by word
The sentiment analysis for levying progress only considers the word information of sentence, does not account for the semantic information of sentence in itself, can so cause feelings
The result for feeling analysis is inaccurate.For example, passing through word feature calculation sentence " alibaba is very rich " and sentence " Ma Yun makes a good deal of money "
Similarity is 0, but the semanteme of actually two sentences is very close.Therefore the accuracy rate of existing sentiment analysis is relatively low.
The content of the invention
The purpose of the embodiment of the present invention is to provide the user feeling analysis method and device of a kind of social networks, can effectively solve
The problem of accuracy rate of certainly existing sentiment analysis is relatively low.
To achieve the above object, the embodiments of the invention provide the user feeling analysis method and dress of a kind of social networks
Put, including step：
Gather the user data of social networks；
That analyzes the user data delivers content, extracts the staple of conversation participated in by LDA technologies, and obtain just negative
Word set；
Analyze subjective emotion collection of the user to each staple of conversation；
Emotion value is obtained according to the just negative word set and subjective emotion collection；
Compared with prior art, the user feeling analysis method of social networks disclosed by the invention is by first gathering social network
The user data of network, then the content of delivering of the user data is analyzed, the staple of conversation participated in is extracted, and obtain positive negation words
Collection, then analyzes subjective emotion collection of the user to each staple of conversation, then according to the just negative word set and subjective emotion collection
Emotion value technical scheme is obtained, the relatively low problem of accuracy rate of existing sentiment analysis is solved, the emotion value quantified is obtained, beneficial to general
Emotion value is integrated into the relational hierarchy that social networks is obtained in relationship analysis network.
As the improvement of such scheme, the social networks is microblogging or wechat.
It is used as the improvement of such scheme, in addition to step：
According to user's content recommendation from the emotion value to the social networks.
As the improvement of such scheme, the user data for gathering the social networks is specially：
The user data of the social networks is gathered using massively parallel processing(MPP).
As the improvement of such scheme, the user data for gathering the social networks is specially：
The user data of a large amount of social networks is received, the user data of the social networks is distributed to many services
No write de-lay hard disk is stored and backed up after device, inbound message queue system.By such scheme, the consumption of data is solved
Poor problem, can quickly receive the data of magnanimity, so as to ensure using hadoop systems to enter in the integrality storages of data again
Row storage and backup, ensure that the reliability of data.
The embodiment of the present invention additionally provides a kind of user feeling analytical equipment of social networks, including：
Acquisition module, the user data for gathering social networks；
Just negative word set acquisition module, the content of delivering for analyzing the user data extracts the staple of conversation participated in,
Obtain just negative word set；
Subjective emotion collection acquisition module, for analyzing subjective emotion collection of the user to each staple of conversation；
Emotion value acquisition module, for obtaining emotion value according to the just negative word set and subjective emotion collection.
Compared with prior art, the user feeling analytical equipment of social networks disclosed by the invention is first adopted by acquisition module
Collect the user data of social networks, then the content of delivering of the user data is analyzed by just negative word set acquisition module, extract
The staple of conversation of participation, and just negative word set is obtained, user is then analyzed to each main by subjective emotion collection acquisition module
The subjective emotion collection of topic, then obtains emotion by emotion value acquisition module according to the just negative word set and subjective emotion collection
It is worth technical scheme, solves the relatively low problem of accuracy rate of existing sentiment analysis, obtains the emotion value quantified, it is whole beneficial to emotion is worth
Close the relational hierarchy that social networks is obtained into relationship analysis network.
As the improvement of such scheme, the social networks is microblogging or wechat.
As the improvement of such scheme, in addition to：
Recommending module, for according to user's content recommendation from the emotion value to the social networks.
As the improvement of such scheme, the collection module using massively parallel processing(MPP) specifically for gathering the social activity
The user data of network.
It is used as the improvement of such scheme, number of users of the collection module specifically for a large amount of social networks of reception
According to the user data of the social networks is distributed into no write de-lay hard disk after multiple servers, inbound message queue system and entered
Row storage and backup.
Brief description of the drawings
Fig. 1 is a kind of schematic flow sheet of the user feeling analysis method for social networks that the embodiment of the present invention 1 is provided.
Fig. 2 is a kind of schematic flow sheet of the user feeling analysis method for social networks that the embodiment of the present invention 2 is provided.
Fig. 3 is a kind of structural representation of the user feeling analytical equipment for social networks that the embodiment of the present invention 3 is provided.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
It is a kind of flow signal of the user feeling analysis method for social networks that the embodiment of the present invention 1 is provided referring to Fig. 1
Figure, including step：
S1, the user data for gathering social networks；Wherein, the user data includes delivering content；
Preferably, the user data of the social networks is gathered using massively parallel processing(MPP), sea can be quickly received
The data of amount, so as to ensure the integrality of data again.
S2, the analysis user data staple of conversation delivered content, participation is extracted by LDA technologies, and obtain just
Negative word set；
Wherein, the LDA is a kind of non-supervisory machine learning techniques, can be for the extensive document sets of identification
The subject information hidden in (document collection) or corpus (corpus).It employs bag of words (bag of
Each document is considered as a word frequency vector by method words), this method, thus by text message conversion for ease of
The digital information of modeling.But bag of words method does not account for the order between word and word, this simplifies the complex nature of the problem, simultaneously
Also opportunity is provided for the improvement of model.The probability distribution that some themes of each documents representative are constituted, and it is each
Individual theme represents the probability distribution that many words are constituted again.
S3, analysis user are to the subjective emotion collection of each staple of conversation；
S4, emotion value obtained according to the just negative word set and subjective emotion collection.
When it is implemented, first gathering the user data of social networks, then the content of delivering of the user data is analyzed, extracted
The staple of conversation of participation, and just negative word set is obtained, user is then analyzed to the subjective emotion collection of each staple of conversation, Ran Hougen
Emotion value technical scheme is obtained according to the just negative word set and subjective emotion collection, the accuracy rate for solving existing sentiment analysis is relatively low
Problem, obtains the emotion value quantified, beneficial to the relational hierarchy that emotion value is integrated into acquisition social networks in relationship analysis network.
Preferably, in another embodiment, as shown in Fig. 2 also including step on the basis of embodiment 1：
S5, according to user's content recommendation from the emotion value to the social networks.
By above-mentioned steps, the content of personalization can be recommended to the user of the social networks by the emotion value of quantization,
It is more intelligent, realize the automatically screening of information.
The user data that step S1 gathers the social networks is specially：
The user data of a large amount of social networks is received, the user data of the social networks is distributed to many services
No write de-lay hard disk is stored and backed up after device, inbound message queue system.
By such scheme, the poor problem of consumption of data is solved, the data of magnanimity can be quickly received, so as to protect again
Stored and backed up using hadoop systems in the integrality storages for demonstrate,proving data, ensure that the reliability of data.
It is a kind of structural representation of the user feeling analytical equipment for social networks that the embodiment of the present invention 3 is provided referring to Fig. 3
Figure, including:
Acquisition module 101, the user data for gathering social networks；
Just negative word set acquisition module 102, the content of delivering for analyzing the user data extracts the main words participated in
Topic, obtains just negative word set；
Subjective emotion collection acquisition module 103, for analyzing subjective emotion collection of the user to each staple of conversation；
Emotion value acquisition module 104, for obtaining emotion value according to the just negative word set and subjective emotion collection.
When it is implemented, acquisition module first gathers the user data of social networks, then pass through just negative word set acquisition module
The content of delivering of the user data is analyzed, the staple of conversation participated in is extracted, and obtains just negative word set, then passes through subjective feelings
Sense collection acquisition module analyzes subjective emotion collection of the user to each staple of conversation, then by emotion value acquisition module according to described
Just negative word set and subjective emotion collection obtain emotion value technical scheme, solve the relatively low problem of accuracy rate of existing sentiment analysis,
The emotion value quantified is obtained, beneficial to the relational hierarchy that emotion value is integrated into acquisition social networks in relationship analysis network.
In a preferred embodiment, the user feeling analytical equipment of the social networks also includes：
Recommending module, for according to user's content recommendation from the emotion value to the social networks.
In a preferred embodiment, as the improvement of such scheme, the collection module is specifically for utilizing on a large scale simultaneously
Row technology gathers the user data of the social networks.
It is used as the improvement of such scheme, number of users of the collection module specifically for a large amount of social networks of reception
According to the user data of the social networks is distributed into no write de-lay hard disk after multiple servers, inbound message queue system and entered
Row storage and backup, the data of magnanimity can quickly be received by solving the consumption difference problem of data, so as to ensure data again
Stored and backed up using hadoop systems in integrality storages, ensure that the reliability of data.
To sum up, the user feeling analysis method of social networks disclosed by the invention is by first gathering the number of users of social networks
According to, then the content of delivering of the user data is analyzed, the staple of conversation participated in is extracted, and just negative word set is obtained, then analyze
Then user obtains emotion value skill to the subjective emotion collection of each staple of conversation according to the just negative word set and subjective emotion collection
Art scheme, solves the relatively low problem of accuracy rate of existing sentiment analysis, obtains the emotion value quantified, is integrated into beneficial to by emotion value
The relational hierarchy of social networks is obtained in relationship analysis network.
Described above is the preferred embodiment of the present invention, it is noted that for those skilled in the art
For, under the premise without departing from the principles of the invention, some improvements and modifications can also be made, these improvements and modifications are also considered as
Protection scope of the present invention.
Claims (10)
1. the user feeling analysis method of a kind of social networks, it is characterised in that including step：
Gather the user data of social networks；Wherein, the user data includes delivering content；
That analyzes the user data delivers content, extracts the staple of conversation participated in by LDA technologies, and obtain positive negation words
Collection；
Analyze subjective emotion collection of the user to each staple of conversation；
Emotion value is obtained according to the just negative word set and subjective emotion collection.
2. the user feeling analysis method of social networks as claimed in claim 1, it is characterised in that the social networks is micro-
Rich or wechat.
3. the user feeling analysis method of social networks as claimed in claim 1, it is characterised in that also including step：
According to user's content recommendation from the emotion value to the social networks.
4. the user feeling analysis method of social networks as claimed in claim 1, it is characterised in that the collection social networks
User data be specially：
The user data of the social networks is gathered using massively parallel processing(MPP).
5. the user feeling analysis method of social networks as claimed in claim 1, it is characterised in that the collection social networks
User data be specially：
The user data of a large amount of social networks is received, the user data of the social networks is distributed to multiple servers,
No write de-lay hard disk is stored and backed up after inbound message queue system.
6. a kind of user feeling analytical equipment of social networks, it is characterised in that including：
Acquisition module, the user data for gathering social networks；
Just negative word set acquisition module, the content of delivering for analyzing the user data extracts the staple of conversation participated in, obtains
Just negative word set；
Subjective emotion collection acquisition module, for analyzing subjective emotion collection of the user to each staple of conversation；
Emotion value acquisition module, for obtaining emotion value according to the just negative word set and subjective emotion collection.
7. the user feeling analytical equipment of social networks as claimed in claim 6, it is characterised in that the social networks is micro-
Rich or wechat.
8. the user feeling analytical equipment of social networks as claimed in claim 6, it is characterised in that also include：
Recommending module, for according to user's content recommendation from the emotion value to the social networks.
9. the user feeling analytical equipment of social networks as claimed in claim 6, it is characterised in that the collection module is specific
User data for gathering the social networks using massively parallel processing(MPP).
10. the user feeling analytical equipment of social networks as claimed in claim 6, it is characterised in that the collection module tool
Body is used for the user data for receiving a large amount of social networks, and the user data of the social networks is distributed into many services
No write de-lay hard disk is stored and backed up after device, inbound message queue system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710581139.3A CN107220241A (en) | 2017-07-17 | 2017-07-17 | The user feeling analysis method and device of social networks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710581139.3A CN107220241A (en) | 2017-07-17 | 2017-07-17 | The user feeling analysis method and device of social networks |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107220241A true CN107220241A (en) | 2017-09-29 |
Family
ID=59952939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710581139.3A Pending CN107220241A (en) | 2017-07-17 | 2017-07-17 | The user feeling analysis method and device of social networks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107220241A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942340A (en) * | 2014-05-09 | 2014-07-23 | 电子科技大学 | Microblog user interest recognizing method based on text mining |
| CN106599063A (en) * | 2016-11-15 | 2017-04-26 | 武汉璞华大数据技术有限公司 | Fine-grained viewpoint mining method based on theme emotion semantic extraction |
-
2017
- 2017-07-17 CN CN201710581139.3A patent/CN107220241A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103942340A (en) * | 2014-05-09 | 2014-07-23 | 电子科技大学 | Microblog user interest recognizing method based on text mining |
| CN106599063A (en) * | 2016-11-15 | 2017-04-26 | 武汉璞华大数据技术有限公司 | Fine-grained viewpoint mining method based on theme emotion semantic extraction |
Non-Patent Citations (5)
| Title |
|---|
| 刘晨晨，等: "基于主题角色的文本情感分类方法", 《计算机应用与软件》 * |
| 王英，等: "基于情感维度的大数据网络舆情情感倾向性分析研究", 《情报科学》 * |
| 蒋磊: "面向产品评论的意见挖掘关键技术研究", 《中国优秀硕士学位论文全文数据库信息科技辑（月刊）》 * |
| 赵占波，等: "《移动互联时代洞察消费者行为》", 31 March 2015, 首都经济贸易大学出版社 * |
| 陈敏，等: "《大数据浪潮——大数据整体解决方案及关键技术探索》", 31 October 2015, 华中科技大学出版社 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104915446B (en) | Event Evolvement extraction method and its system based on news | |
| CN103678670A (en) | Micro-blog hot word and hot topic mining system and method | |
| CN104699766B (en) | A kind of implicit attribute method for digging for merging word association relation and context of co-text deduction | |
| CN103745000B (en) | Hot topic detection method of Chinese micro-blogs | |
| Duan et al. | Twitter topic summarization by ranking tweets using social influence and content quality | |
| CN102890698B (en) | Method for automatically describing microblogging topic tag | |
| CN107193805A (en) | Article Valuation Method, device and storage medium based on artificial intelligence | |
| CN106980692A (en) | A kind of influence power computational methods based on microblogging particular event | |
| CN108363725B (en) | Method for extracting user comment opinions and generating opinion labels | |
| CN103942340A (en) | Microblog user interest recognizing method based on text mining | |
| CN102682120B (en) | Method and device for acquiring essential article commented on network | |
| CN103699626A (en) | Method and system for analysing individual emotion tendency of microblog user | |
| CN107273474A (en) | Autoabstract abstracting method and system based on latent semantic analysis | |
| CN104102681A (en) | Microblog key event acquiring method and device | |
| CN105095183A (en) | Text emotional tendency determination method and system | |
| CN109299865A (en) | Psychological assessment system and method, information data processing terminal based on semantic analysis | |
| CN110674298B (en) | Deep learning mixed topic model construction method | |
| CN105893484A (en) | Microblog Spammer recognition method based on text characteristics and behavior characteristics | |
| CN109086355A (en) | Hot spot association relationship analysis method and system based on theme of news word | |
| CN109885675A (en) | Method is found based on the text sub-topic for improving LDA | |
| CN104281565A (en) | Semantic dictionary constructing method and device | |
| CN106227720B (en) | A kind of APP software users comment mode identification method | |
| CN103761246B (en) | Link network based user domain identifying method and device | |
| CN107480197A (en) | Entity word recognition method and device | |
| CN105117466A (en) | Internet information screening system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170929 |