CN103116644A - Method for mining orientation of Web themes and supporting decisions - Google Patents
Method for mining orientation of Web themes and supporting decisions Download PDFInfo
- Publication number
- CN103116644A CN103116644A CN2013100591702A CN201310059170A CN103116644A CN 103116644 A CN103116644 A CN 103116644A CN 2013100591702 A CN2013100591702 A CN 2013100591702A CN 201310059170 A CN201310059170 A CN 201310059170A CN 103116644 A CN103116644 A CN 103116644A
- Authority
- CN
- China
- Prior art keywords
- topic
- sub
- information
- cluster
- emotional semantic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Machine Translation (AREA)
Abstract
The invention discloses a method for mining the orientation of Web themes and supporting decisions. The method includes steps of S1, extracting and storing network information, acquiring information on the internet via a network mining technology, and storing results in a database and a local file system; S2, detecting and tracking viewpoint themes of the information, detecting and identifying interested viewpoint themes with complete semantic information by the aid of thematic comment data and keeping tracking and following the viewpoint themes; and S3, identifying the emotion orientation of the viewpoint themes, classifying the emotion orientation of hot topics of an enterprise, and mining the emotion orientation of the view themes. The method has the advantages that related business information is acquired from the internet, so that the tendency of the orientation of the themes related to the enterprise can be quickly and effectively mined from the massive network information, real-time business intelligence can be realized, and decision support service can be effectively provided for the enterprise.
Description
Technical field
The theme tendentiousness that the present invention relates to the Web data is excavated and the method for decision support, especially for theme emotional orientation analysis and the decision support of magnanimity Web data.
Background technology
Global financial crisis has brought effect of depth for many conventional industries, makes industry personage and investor more recognize believable bussiness imformation and obtains the importance of technology.For enterprise, these technology can assist them to form quickly and effectively business decision, effectively risk are managed and control, and improve their commercial competitiveness and finally make them win in market competition.Based on above-mentioned common recognition, industrial community is excavated by the network information and the demand of intelligent decision service becomes day by day urgent.The network information is excavated and the intelligent decision service relates to technology for information acquisition, Text Classification, text cluster technology, theme recognition and tracking technology and text tendency analysis etc.These technology one are to being the field that domestic and international information worker pays close attention to.Text retrieval meeting (TREC), information retrieval special interest group meeting (SIGIR), text detection and tracking meeting (TDT) etc. are all topmost international conference and the forums that shows this type of technology newest research results.
The current research person has proposed many network text based on sentiment classification algorithms, mainly concentrates on the text tendency analysis of Sentence-level and chapter level.Present research work can be divided into two kinds of Research Thinkings: based on the method for emotion knowledge and based on the method for tagsort.The former relies on some existing sentiment dictionaries or field dictionary, and in subjective text, the combination evaluation unit with feeling polarities calculates, and obtains the polarity of subjective text.The latter is mainly the method for using machine learning, chooses a large amount of significant features and completes classification task.These two kinds of Research Thinkings have a lot of representational research work.In the method based on tagsort, Pang is applied to the method for machine learning in the emotional semantic classification task of chapter level first.They attempt having used n-gram word feature and part of speech feature, and have contrasted Navie Bayes, Max Entropy and Support Vector Machine(SVM) three kinds of disaggregated models, find that the unigram characteristic effect is best.Yet Cui proves by experiment, and when corpus was less, the effect of unigram was more excellent, but along with the increasing of corpus, and n-gram (n〉3) has brought into play more and more important effect.Kim has also introduced position feature and has estimated the classification of passing judgement on that the word feature is come the sentence completion level except investigating traditional n-gram model.It is a three-layer classification task that Zhao refines Sentence-level emotional semantic classification task, utilize the interaction of class label between each layer, and consider interacting of emotion between the sentence of up and down, and using Conditional Random Field(CRF) model merges these features.Be similar to the subjective and objective information classification task, be the discovery of validity feature based on the research emphasis of the method for feature, and the research of the problems such as feature selecting and Fusion Features.Except to the passing judgement on binary classification of subjective text message, also have some research work to carry out finer emotional semantic classification task.Pang will pass judgement on grade and be divided three classes, and use one-vs-all multivariate classification algorithm and returned sorting algorithm and completed emotional semantic classification.The sorting algorithm that Goldberg has used a kind of graph-based half to instruct is completed the classification that passing judgement on of comment comprises four grades.
In sum, at present for the method for the tendentiousness sentiment analysis of enterprise hot spots topic on the internet and excavation also seldom, the instant business wisdom of distance still has distance.Therefore, be necessary to provide a kind of Web theme tendentiousness sentiment analysis to excavate and the method and system of decision support, to make up the deficiencies in the prior art.Topic detection can be found theme also the content association of Topic relative together automatically automatically with tracking from the Web data stream, the Web theme relevant to enterprise carries out tendentiousness sentiment analysis and excavation, realize instant business wisdom, can provide the decision support service for enterprise better.
Summary of the invention
Based on this, for above-mentioned problems of the prior art, the object of the present invention is to provide a kind of Web theme tendentiousness to excavate method with decision support, be intended to tendentiousness sentiment analysis and excavation for enterprise hot spots topic on the internet, for the decision-making of enterprise provide with reference to and support.
For achieving the above object, technical solution of the present invention is:
A kind of Web theme tendentiousness is excavated the method with decision support, comprises step:
S1. network information extraction and storage, by the Web Mining technology, obtaining information on the internet, and deposit result in database and local file system;
S2. viewpoint topic detection and the tracking of information, utilize thematic comment data, detects and identify interested viewpoint theme with integrated semantic, and continue to follow the tracks of and pay close attention to this viewpoint theme;
S3. viewpoint theme emotion tendency identification is carried out the classification of topic emotion tendency to the much-talked-about topic of enterprise, excavates the emotion tendency of viewpoint theme.
Further, described step S1 also comprises:
S11. natural language processing is carried out pre-service to primitive network information, comprising: Chinese word segmentation, part-of-speech tagging, stop words are processed, named entity recognition.
Further, in described step S2, the viewpoint topic detection of network information and the process of tracking specifically comprise:
S21. the information that collects from network is through the information classification based on template, filtered noise information;
S22. the relevant information after filtering adopts time-based increase of function clustering method, realizes the detection of sub-topic, and with result store in the sub-topic table of database;
S23. according to the result of sub-topic, extract summary and the keyword of sub-topic, and revise sub-topic table relevant information;
S24. in the information according to sub-topic, window similarity increment clustering method relatively between the basis, carry out topic detection, and extract keyword again, obtains topic information and deposit database in;
S25. according to the quantity of information in time of information in topic and topic, the discovering hot topic, and present to the user.
Further, the process of the detection of described step S22 neutron topic specifically comprises:
S221. every piece of document in sequential processes information;
S222. utilize hierarchy clustering method to carry out cluster to untreated document;
If S223. history of existence cluster not, according to current cluster result, store sub-topic;
If S224. the history of existence cluster, to the sub-topic of history and the sub-topic that new cluster goes out, carry out hierarchical clustering again;
The sub-topic that S225. will newly produce deposits database in;
S226. upgrade the relation of sub-topic and document;
The information such as the keyword of the sub-topic that S227. calculates new generation and upgraded, multi-document summary deposit database in.
Further, in described step S24, the process of the detection of topic specifically comprises:
S241. every the sub-topic of sequential processes;
S242. the vector of first sub-topic becomes the cluster centre of first cluster automatically;
If S243. similarity is greater than certain threshold value, this sub-topic is assigned to this cluster;
S244. when certain cluster distributed in a sheet topic, recomputate the cluster centre of this cluster;
If S245. any cluster do not distributed in certain sub-topic, this sub-topic becomes a new cluster, is also the cluster centre of this cluster simultaneously;
The topic that S246. will newly produce adds database to;
S247. upgrade the information of topic.
Further, in described step S3, the process of network themes emotion tendency identification specifically comprises:
S31. train topic emotional semantic classification model, read mark good topic language material and sentiment dictionary, utilize the svm classifier algorithm, obtain topic emotional semantic classification model by training;
S32. sub-topic emotional semantic classification, the antithetical phrase topic extracts affective characteristics, utilizes topic emotional semantic classification model and svm classifier algorithm to obtain sub-topic classification results;
S33. topic emotional semantic classification utilizes the result of sub-topic emotional semantic classification, builds the graph model based on sub-topic, according to graph model output topic emotional semantic classification result;
Further, in described step S31, the process of training topic emotional semantic classification model specifically comprises:
S311. read in the good topic emotional semantic classification language material of mark;
S312. by natural language processing, obtain through Chinese word segmentation and the good language material of part-of-speech tagging;
S313. according to sentiment dictionary and grammatical pattern storehouse, extract affective characteristics from language material, structure topic classification based training data set;
S314. sorter reads training dataset, utilizes the svm classifier algorithm, obtains topic emotional semantic classification model by training.
Further, the process of described step S32 neutron topic emotional semantic classification specifically comprises:
S321. read in sub-topic to be sorted;
S322. by natural language processing, obtain through Chinese word segmentation and the good sub-topic of part-of-speech tagging;
S323. according to sentiment dictionary and grammatical pattern storehouse, extract affective characteristics from sub-topic, the structure test data set;
S324. sorter read test data and the topic emotional semantic classification model that trains before, utilize the svm classifier algorithm, exports sub-topic emotional semantic classification result.
Further, in described step S33, the process of topic emotional semantic classification specifically comprises:
S331. read in topic to be sorted;
S332. topic to be sorted is resolved, obtain sub-topic collection;
S333. call sub-topic emotion classifiers, every sub-topic classified, obtain sub-topic emotional semantic classification result;
S334. according to the similarity between sub-topic, build the LexRank graph model, utilize constructed graph model, calculate importance and the redundance of sub-topic, finally export topic emotional semantic classification result.
Compared with prior art, the present invention has following beneficial effect: the present invention obtains the relative commercial information by Web Mining and information extraction technique from the internet, bussiness imformation is analyzed, find New Topics, and continue follow the tracks of and pay close attention to this topic, by the emotion tendency that obtains topic and the emotion trend to topic.The present invention can fast and effeciently excavate the relevant theme tendentiousness tendency of enterprise from the mass network information, realize instant business wisdom, can provide the decision support service for enterprise better.
Description of drawings
Fig. 1 is embodiments of the invention one flow process schematic diagram.
Fig. 2 is embodiments of the invention two flow process schematic diagram.
Embodiment
The present invention is further detailed explanation below in conjunction with drawings and Examples.
Embodiment one
The schematic flow sheet of the embodiment of the present invention one has been shown in Fig. 1.
As shown in Figure 1, in this embodiment, a kind of Web theme tendentiousness is excavated the method with decision support, comprises step:
S101. network information extraction and storage, by the Web Mining technology, obtaining information on the internet, and deposit result in database and local file system;
S102. natural language processing is carried out pre-service to primitive network information, comprising: Chinese word segmentation, part-of-speech tagging, stop words are processed, named entity recognition;
S103. viewpoint topic detection and the tracking of information, utilize thematic comment data, detects and identify interested viewpoint theme with integrated semantic.And continue tracking and pay close attention to this viewpoint theme;
S104. viewpoint theme emotion tendency identification is carried out the classification of topic emotion tendency to the much-talked-about topic of enterprise, excavates the emotion tendency of viewpoint theme.
Embodiment two
The schematic flow sheet of the embodiment of the present invention two has been shown in Fig. 2.
As shown in Figure 2, in this embodiment,
A kind of Web theme tendentiousness is excavated the method with decision support, comprises step:
S201. network information extraction and storage, by the Web Mining technology, obtaining information on the internet, and deposit result in database and local file system;
S202. natural language processing is carried out pre-service to primitive network information, comprising: Chinese word segmentation, part-of-speech tagging, stop words are processed, named entity recognition;
The information that S203. will collect from network is through the information classification based on template, filtered noise information;
S204. the relevant information after filtering adopts time-based increase of function clustering method, realizes the detection of sub-topic, and with result store in the sub-topic table of database;
S205. according to the result of sub-topic, extract summary and the keyword of sub-topic, and revise sub-topic table relevant information;
S206. in the information according to sub-topic, window similarity increment clustering method relatively between the basis, carry out topic detection, and extract keyword again, obtains topic information and deposit database in;
S207. according to the quantity of information in time of information in topic and topic, the discovering hot topic, and present to the user;
S208. train topic emotional semantic classification model, read mark good topic language material and sentiment dictionary, utilize the svm classifier algorithm, obtain topic emotional semantic classification model by training;
S209. sub-topic emotional semantic classification, the antithetical phrase topic extracts affective characteristics, utilizes topic emotional semantic classification model and svm classifier algorithm to obtain sub-topic classification results;
S210. topic emotional semantic classification utilizes the result of sub-topic emotional semantic classification, builds the graph model based on sub-topic, according to graph model output topic emotional semantic classification result.
Embodiment three
A kind of Web theme tendentiousness is excavated the method with decision support, comprises step:
S301. network information extraction and storage, by the Web Mining technology, obtaining information on the internet, and deposit result in database and local file system;
S302. natural language processing is carried out pre-service to primitive network information, comprising: Chinese word segmentation, part-of-speech tagging, stop words are processed, named entity recognition;
S303. the information that collects from network is through the information classification based on template, filtered noise information;
S304. every piece of document in sequential processes information;
S305. utilize hierarchy clustering method to carry out cluster to untreated document;
If S306. history of existence cluster not, according to current cluster result, store sub-topic;
If S307. the history of existence cluster, to the sub-topic of history and the sub-topic that new cluster goes out, carry out hierarchical clustering again;
The sub-topic that S308. will newly produce deposits database in;
S309. upgrade the relation of sub-topic and document;
The information such as the keyword of the sub-topic that S310. calculates new generation and upgraded, multi-document summary deposit database in;
S311. according to the result of sub-topic, extract summary and the keyword of sub-topic, and revise sub-topic table relevant information;
S312. every the sub-topic of sequential processes;
S313. the vector of first sub-topic becomes the cluster centre of first cluster automatically;
If S314. similarity is greater than certain threshold value, this sub-topic is assigned to this cluster;
S315. when certain cluster distributed in a sheet topic, recomputate the cluster centre of this cluster;
If S316. any cluster do not distributed in certain sub-topic, this sub-topic becomes a new cluster, is also the cluster centre of this cluster simultaneously;
The topic that S317. will newly produce adds database to;
S318. upgrade the information of topic;
S319. according to the quantity of information in time of information in topic and topic, the discovering hot topic, and present to the user;
S320. read in the good topic emotional semantic classification language material of mark;
S321. by natural language processing, obtain through Chinese word segmentation and the good language material of part-of-speech tagging;
S322. according to sentiment dictionary and grammatical pattern storehouse, extract affective characteristics from language material, structure topic classification based training data set;
S323. sorter reads training dataset, utilizes the svm classifier algorithm, obtains topic emotional semantic classification model by training;
S324. read in sub-topic to be sorted;
S325. by natural language processing, obtain through Chinese word segmentation and the good sub-topic of part-of-speech tagging;
S326. according to sentiment dictionary and grammatical pattern storehouse, extract affective characteristics from sub-topic, the structure test data set;
S327 sorter read test data and the topic emotional semantic classification model that trains before utilize the svm classifier algorithm, export sub-topic emotional semantic classification result;
S328. read in topic to be sorted;
S329. topic to be sorted is resolved, obtain sub-topic collection;
S330. call sub-topic emotion classifiers, every sub-topic classified, obtain sub-topic emotional semantic classification result;
S331. according to the similarity between sub-topic, build the LexRank graph model, utilize constructed graph model, calculate importance and the redundance of sub-topic, output topic emotional semantic classification result.
As adopt reptile to be responsible for targeted website downloading web pages from the internet, and webpage is resolved and information extraction, result deposits database and local file system in.Adopt focused crawler, filter and irrelevant the linking of theme according to certain web page analysis algorithm, remain with the link of use and put it into the URL formation of waiting for crawl.Then, it will select according to certain search strategy next step webpage URL that will grasp from formation, and repeat said process, until stop when reaching a certain condition of system.In addition, all will be stored by system by the webpage of crawler capturing, carry out certain analysis, filtration, and set up index, so that retrieval and indexing afterwards.
In sub-topic detection and topic detection, concrete clustering method is as follows:
First text is carried out pre-service, thereby then extract and select the speech of speech feature reasonable representation, carry out the topic cluster according to speech feature and topic feature calculation similarity at last.After carrying out the topic cluster, then upgrade the topic feature.At first, regard each speech as a topic that only contains a speech, and calculate the similarity of each speech team.Secondly, calculate the similarity of each class bunch.The similarity of class bunch A and class bunch B can be regarded as the arithmetic mean value of the similarity of the speech team in each class bunch.At last, suppose that A and B are that the highest class of similarity is bunch right, if similarity higher than predefined threshold value, with class bunch A, B is merged into a new class bunch, and continues to carry out second step, otherwise stops the topic cluster.
These are only the preferred embodiments of the present invention, but design concept of the present invention is not limited to this, all insubstantial modifications of utilizing this design that the present invention is made are within also all falling into protection scope of the present invention.
Claims (9)
1. a Web theme tendentiousness is excavated the method with decision support, it is characterized in that, comprises step:
S1. network information extraction and storage, by the Web Mining technology, obtaining information on the internet, and deposit result in database and local file system;
S2. viewpoint topic detection and the tracking of information, utilize thematic comment data, detects and identify interested viewpoint theme with integrated semantic, and continue to follow the tracks of and pay close attention to this viewpoint theme;
S3. viewpoint theme emotion tendency identification is carried out the classification of topic emotion tendency to the much-talked-about topic of enterprise, excavates the emotion tendency of viewpoint theme.
2. the method for Web theme tendentiousness excavation according to claim 1 and decision support, is characterized in that, described step S1 also comprises:
S11. natural language processing is carried out pre-service to primitive network information, comprising: Chinese word segmentation, part-of-speech tagging, stop words are processed, named entity recognition.
3. the method for Web theme tendentiousness excavation according to claim 2 and decision support, is characterized in that, in described step S2, the process of viewpoint topic detection and tracking specifically comprises:
S21. the information that collects from network is through the information classification based on template, filtered noise information;
S22. the relevant information after filtering adopts time-based increase of function clustering method, realizes the detection of sub-topic, and with result store in the sub-topic table of database;
S23. according to the result of sub-topic, extract summary and the keyword of sub-topic, and revise sub-topic table relevant information;
S24. in the information according to sub-topic, window similarity increment clustering method relatively between the basis, carry out topic detection, and extract keyword again, obtains topic information and deposit database in;
S25. according to the quantity of information in time of information in topic and topic, the discovering hot topic, and present to the user.
4. the method for Web theme tendentiousness excavation according to claim 3 and decision support, is characterized in that, the process of the detection of described step S22 neutron topic specifically comprises:
S221. every piece of document in the sequential processes relevant information;
S222. utilize hierarchy clustering method to carry out cluster to untreated document;
If S223. history of existence cluster not, according to current cluster result, store sub-topic;
If S224. the history of existence cluster, to the sub-topic of history and the sub-topic that new cluster goes out, carry out hierarchical clustering again;
The sub-topic that S225. will newly produce deposits database in;
S226. upgrade the relation of sub-topic and document;
The information such as the keyword of the sub-topic that S227. calculates new generation and upgraded, multi-document summary deposit database in.
5. the method for Web theme tendentiousness excavation according to claim 3 and decision support, is characterized in that, in described step S24, the process of the detection of topic specifically comprises:
S241. every the sub-topic of sequential processes;
S242. the vector of first sub-topic becomes the cluster centre of first cluster automatically;
If S243. similarity is greater than certain threshold value, this sub-topic is assigned to this cluster;
S244. when certain cluster distributed in a sheet topic, recomputate the cluster centre of this cluster;
If S245. any cluster do not distributed in certain sub-topic, this sub-topic becomes a new cluster, is also the cluster centre of this cluster simultaneously;
The topic that S246. will newly produce adds database to;
S247. upgrade the information of topic.
6. the method for Web theme tendentiousness excavation according to claim 1 and decision support, is characterized in that, in described step S3, the process of network themes emotion tendency identification specifically comprises:
S31. train topic emotional semantic classification model, read mark good topic language material and sentiment dictionary, utilize the svm classifier algorithm, obtain topic emotional semantic classification model by training;
S32. sub-topic emotional semantic classification, the antithetical phrase topic extracts affective characteristics, utilizes topic emotional semantic classification model and svm classifier algorithm to obtain sub-topic classification results;
S33. topic emotional semantic classification utilizes the result of sub-topic emotional semantic classification, builds the graph model based on sub-topic, according to graph model output topic emotional semantic classification result.
7. the method for Web theme tendentiousness excavation according to claim 6 and decision support, is characterized in that, in described step S31, the process of training topic emotional semantic classification model specifically comprises:
S311. read in the good topic emotional semantic classification language material of mark;
S312. by natural language processing, obtain through Chinese word segmentation and the good language material of part-of-speech tagging;
S313. according to sentiment dictionary and grammatical pattern storehouse, extract affective characteristics from language material, structure topic classification based training data set;
S314. sorter reads training dataset, utilizes the svm classifier algorithm, obtains topic emotional semantic classification model by training.
8. the method for Web theme tendentiousness excavation according to claim 6 and decision support, is characterized in that, the process of described step S32 neutron topic emotional semantic classification specifically comprises:
S321. read in sub-topic to be sorted;
S322. by natural language processing, obtain through Chinese word segmentation and the good sub-topic of part-of-speech tagging;
S323. according to sentiment dictionary and grammatical pattern storehouse, extract affective characteristics from sub-topic, the structure test data set;
S324. sorter read test data and the topic emotional semantic classification model that trains before, utilize the svm classifier algorithm, exports sub-topic emotional semantic classification result.
9. the method for Web theme tendentiousness excavation according to claim 6 and decision support, is characterized in that, in described step S33, the process of topic emotional semantic classification specifically comprises:
S331. read in topic to be sorted;
S332. topic to be sorted is resolved, obtain sub-topic collection;
S333. call sub-topic emotion classifiers, every sub-topic classified, obtain sub-topic emotional semantic classification result;
S334. according to the similarity between sub-topic, build the LexRank graph model, utilize constructed graph model, calculate importance and the redundance of sub-topic, finally export topic emotional semantic classification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310059170.2A CN103116644B (en) | 2013-02-26 | 2013-02-26 | Web topic tendentiousness excavates the method with decision support |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310059170.2A CN103116644B (en) | 2013-02-26 | 2013-02-26 | Web topic tendentiousness excavates the method with decision support |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103116644A true CN103116644A (en) | 2013-05-22 |
| CN103116644B CN103116644B (en) | 2016-04-13 |
Family
ID=48415017
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310059170.2A Active CN103116644B (en) | 2013-02-26 | 2013-02-26 | Web topic tendentiousness excavates the method with decision support |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103116644B (en) |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473280A (en) * | 2013-08-28 | 2013-12-25 | 中国科学院合肥物质科学研究院 | Method and device for mining comparable network language materials |
| CN104123395A (en) * | 2014-08-13 | 2014-10-29 | 北京赛科世纪数码科技有限公司 | Decision making method and system based on big data |
| CN104331394A (en) * | 2014-08-29 | 2015-02-04 | 南通大学 | Text classification method based on viewpoint |
| CN104504087A (en) * | 2014-12-25 | 2015-04-08 | 中国科学院电子学研究所 | Low-rank decomposition based delicate topic mining method |
| CN104794212A (en) * | 2015-04-27 | 2015-07-22 | 清华大学 | Context sentiment classification method and system based on user comment text |
| CN104965823A (en) * | 2015-07-30 | 2015-10-07 | 成都鼎智汇科技有限公司 | Big data based opinion extraction method |
| CN105159972A (en) * | 2015-08-26 | 2015-12-16 | 苏州大学张家港工业技术研究院 | Classification method and system for evaluation types |
| CN105787026A (en) * | 2016-02-24 | 2016-07-20 | 人民网股份有限公司 | Information stream display method and device |
| CN106126502A (en) * | 2016-07-07 | 2016-11-16 | 四川长虹电器股份有限公司 | A kind of emotional semantic classification system and method based on support vector machine |
| CN106528538A (en) * | 2016-12-07 | 2017-03-22 | 竹间智能科技（上海）有限公司 | Method and device for intelligent emotion recognition |
| CN103841121B (en) * | 2014-03-28 | 2017-03-29 | 中国科学技术大学 | A kind of comment and interaction systems and method based on local file |
| CN106855879A (en) * | 2016-12-14 | 2017-06-16 | 竹间智能科技（上海）有限公司 | The robot that artificial intelligence psychology is seeked advice from music |
| CN109902230A (en) * | 2019-02-13 | 2019-06-18 | 北京航空航天大学 | A kind of processing method and processing device of news data |
| CN111428510A (en) * | 2020-03-10 | 2020-07-17 | 蚌埠学院 | Public praise-based P2P platform risk analysis method |
| CN112231470A (en) * | 2019-06-28 | 2021-01-15 | 上海智臻智能网络科技股份有限公司 | Topic mining method and device, storage medium and terminal |
| CN114218381A (en) * | 2021-12-08 | 2022-03-22 | 北京中科闻歌科技股份有限公司 | Method, device, equipment and medium for identifying position |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073647A (en) * | 2009-11-23 | 2011-05-25 | 北京科技大学 | E-Science environment-oriented multi-domain Web text feature extracting system and method |
| CN102646114A (en) * | 2012-02-17 | 2012-08-22 | 清华大学 | News topic timeline abstract generating method based on breakthrough point |
-
2013
- 2013-02-26 CN CN201310059170.2A patent/CN103116644B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102073647A (en) * | 2009-11-23 | 2011-05-25 | 北京科技大学 | E-Science environment-oriented multi-domain Web text feature extracting system and method |
| CN102646114A (en) * | 2012-02-17 | 2012-08-22 | 清华大学 | News topic timeline abstract generating method based on breakthrough point |
Non-Patent Citations (1)
| Title |
|---|
| 吴泽衡: "基于话题检测和情感分析的互联网热点分析与监控技术研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473280B (en) * | 2013-08-28 | 2017-02-08 | 中国科学院合肥物质科学研究院 | Method for mining comparable network language materials |
| CN103473280A (en) * | 2013-08-28 | 2013-12-25 | 中国科学院合肥物质科学研究院 | Method and device for mining comparable network language materials |
| CN103841121B (en) * | 2014-03-28 | 2017-03-29 | 中国科学技术大学 | A kind of comment and interaction systems and method based on local file |
| CN104123395A (en) * | 2014-08-13 | 2014-10-29 | 北京赛科世纪数码科技有限公司 | Decision making method and system based on big data |
| CN104331394A (en) * | 2014-08-29 | 2015-02-04 | 南通大学 | Text classification method based on viewpoint |
| CN104504087A (en) * | 2014-12-25 | 2015-04-08 | 中国科学院电子学研究所 | Low-rank decomposition based delicate topic mining method |
| CN104794212A (en) * | 2015-04-27 | 2015-07-22 | 清华大学 | Context sentiment classification method and system based on user comment text |
| CN104794212B (en) * | 2015-04-27 | 2018-04-10 | 清华大学 | Context sensibility classification method and categorizing system based on user comment text |
| CN104965823A (en) * | 2015-07-30 | 2015-10-07 | 成都鼎智汇科技有限公司 | Big data based opinion extraction method |
| CN105159972A (en) * | 2015-08-26 | 2015-12-16 | 苏州大学张家港工业技术研究院 | Classification method and system for evaluation types |
| CN105787026A (en) * | 2016-02-24 | 2016-07-20 | 人民网股份有限公司 | Information stream display method and device |
| CN105787026B (en) * | 2016-02-24 | 2019-07-09 | 人民网股份有限公司 | The display methods and device of information flow |
| CN106126502A (en) * | 2016-07-07 | 2016-11-16 | 四川长虹电器股份有限公司 | A kind of emotional semantic classification system and method based on support vector machine |
| CN106126502B (en) * | 2016-07-07 | 2018-10-30 | 四川长虹电器股份有限公司 | A kind of emotional semantic classification system and method based on support vector machines |
| CN106528538A (en) * | 2016-12-07 | 2017-03-22 | 竹间智能科技（上海）有限公司 | Method and device for intelligent emotion recognition |
| CN106855879A (en) * | 2016-12-14 | 2017-06-16 | 竹间智能科技（上海）有限公司 | The robot that artificial intelligence psychology is seeked advice from music |
| CN109902230A (en) * | 2019-02-13 | 2019-06-18 | 北京航空航天大学 | A kind of processing method and processing device of news data |
| CN112231470A (en) * | 2019-06-28 | 2021-01-15 | 上海智臻智能网络科技股份有限公司 | Topic mining method and device, storage medium and terminal |
| CN111428510A (en) * | 2020-03-10 | 2020-07-17 | 蚌埠学院 | Public praise-based P2P platform risk analysis method |
| CN111428510B (en) * | 2020-03-10 | 2023-04-07 | 蚌埠学院 | Public praise-based P2P platform risk analysis method |
| CN114218381A (en) * | 2021-12-08 | 2022-03-22 | 北京中科闻歌科技股份有限公司 | Method, device, equipment and medium for identifying position |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103116644B (en) | 2016-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103116644B (en) | Web topic tendentiousness excavates the method with decision support | |
| Arulanandam et al. | Extracting crime information from online newspaper articles | |
| CN102708096B (en) | Network intelligence public sentiment monitoring system based on semantics and work method thereof | |
| Venugopalan et al. | Exploring sentiment analysis on twitter data | |
| CN103617169B (en) | A kind of hot microblog topic extracting method based on Hadoop | |
| CN101609450A (en) | Web page classification method based on training set | |
| CN108959431A (en) | Label automatic generation method, system, computer readable storage medium and equipment | |
| CN102915335B (en) | Based on the information correlation method of user operation records and resource content | |
| CN103365924A (en) | Method, device and terminal for searching information | |
| CN104408093A (en) | News event element extracting method and device | |
| Chawla et al. | Product opinion mining using sentiment analysis on smartphone reviews | |
| CN103177024A (en) | Method and device of topic information show | |
| CN103544255A (en) | Text semantic relativity based network public opinion information analysis method | |
| CN103544242A (en) | Microblog-oriented emotion entity searching system | |
| CN105224521A (en) | Key phrases extraction method and use its method obtaining correlated digital resource and device | |
| CN105608200A (en) | Network public opinion tendency prediction analysis method | |
| CN102207948A (en) | Method for generating incident statement sentence material base | |
| CN103226578A (en) | Method for identifying websites and finely classifying web pages in medical field | |
| CN103226576A (en) | Comment spam filtering method based on semantic similarity | |
| CN107943909A (en) | User demand trend method for digging and device, storage medium based on comment data | |
| CN101393555A (en) | Rubbish blog detecting method | |
| CN104731812A (en) | Text emotion tendency recognition based public opinion detection method | |
| CN103324700A (en) | Noumenon concept attribute learning method based on Web information | |
| CN103177036A (en) | Method and system for label automatic extraction | |
| CN111914087A (en) | Public opinion analysis method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |