CN107797997A - A kind of multilingual network public-opinion monitor supervision platform - Google Patents
A kind of multilingual network public-opinion monitor supervision platform Download PDFInfo
- Publication number
- CN107797997A CN107797997A CN201610588976.4A CN201610588976A CN107797997A CN 107797997 A CN107797997 A CN 107797997A CN 201610588976 A CN201610588976 A CN 201610588976A CN 107797997 A CN107797997 A CN 107797997A
- Authority
- CN
- China
- Prior art keywords
- information
- public sentiment
- text
- module
- public
- 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
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
A kind of multilingual network public-opinion monitor supervision platform includes public sentiment planning module, including data acquisition module, public sentiment data processing module and public sentiment displaying output module;The public sentiment planning module, once integrated using the vertical search information special to certain class in web page library, orientation point field extract needs data handled after return to user with some form again;The including data acquisition module, using integration of the META Search Engine to multiple independent search engines, calling, control and Optimum utilization;The public sentiment data processing module, using Text Mining Technology, text data is pre-processed before text message is obtained;The public sentiment shows output module, by information cluster, the processing to the special topic of network public-opinion monitoring, focus incident, emphasis people and emphasis tissue;By cluster analysis, the different types of network information is condensed together, for analyzing the propagation temperature of information of all categories.
Description
Technical field
The invention belongs to network information processing technical field, is related to a kind of extra large to internet using intelligent information processing technology
The technology that amount information is captured and analyzed and processed automatically.
Background technology
With network application popularization and communication technology progress, netizen increasingly likes the message that spreads through the internet,
Words are delivered, illustrate viewpoint of oneself etc..Network both provided platform for netizen's sounding, also understood the people for government and administrative department
Meaning provides channel.The existing certain applications of current monolingual public sentiment monitoring system, but because the network information is numerous and jumbled, in addition
The characteristics of multi-national multilingual, monitored by real-time performance public sentiment, especially multilingual public sentiment monitors or one urgently to be resolved hurrily
Technical problem.
The content of the invention
It is an object of the invention to provide a kind of multilingual public sentiment monitor supervision platform, existing monolingual public sentiment is utilized
Monitoring system, realize multilingual public sentiment monitoring.
Technical scheme is as follows:
A kind of multilingual network public-opinion monitor supervision platform, it is characterised in that:Including public sentiment planning module, including data acquisition mould
Block, public sentiment data processing module and public sentiment displaying output module;
The public sentiment planning module, once integrated using the vertical search information special to certain class in web page library,
Orientation point field extract needs data handled after return to user with some form again;
The including data acquisition module, using integration of the META Search Engine to multiple independent search engines, calling, control and excellent
Change and utilize;
The public sentiment data processing module, using Text Mining Technology, text data is entered before text message is obtained
Row pretreatment, including data cleansing, data selection, the characteristic information of text dividing, then extraction text, including keyword carry
Take, term extraction, the information extraction based on template, the concept conversion based on semantic dictionary, the grammer based on shallow parsing
Feature extraction, the semantic feature extraction based on Shallow Semantic Parsing, the text categories acquisition of information based on text classification;
The public sentiment shows output module, by information cluster, to the special topic of network public-opinion monitoring, focus incident, emphasis
People and the processing of emphasis tissue;By cluster analysis, the different types of network information is condensed together, it is of all categories for analyzing
The propagation temperature of information.
The present invention is to integrate internet information acquisition technology and information intelligent treatment technology, by internet mass information
Automatic crawl, automatic taxonomic clustering, topic detection, focus on special topic, realize the network public-opinion monitoring and Special Topics in Journalism tracking of user
Deng information requirement, the analysis results such as bulletin, report, chart are formed, masses' thought dynamic is grasped comprehensively for client, makes correct carriage
By guiding, there is provided analysis foundation.The present invention increases multilingual option in existing public sentiment monitor supervision platform technology so that user
Public opinion trend can more comprehensively be controlled.
Brief description of the drawings
Fig. 1 is the platform logic structural representation of the present invention.
Embodiment
As shown in figure 1, shown including public sentiment planning module, including data acquisition module, public sentiment data processing module and public sentiment defeated
Go out module.
The public sentiment planning module, once integrated using the vertical search information special to certain class in web page library,
Orientation point field extract needs data handled after return to user with some form again.
Vertical search engine is the professional search engine for some industry, is the subdivision and extension of search engine, is
The information special to certain class in web page library is once integrated, orientation point field extract needs data handled after again
User is returned to some form.Vertical search is the containing much information of relative universal search engine, it is inadequate inquire about inaccuracy, depth
Etc. the new search engine service pattern put forward, by for a certain specific area, a certain specific crowd or a certain particular needs
The information and the related service that there are certain values of offer are provided.
The including data acquisition module, using integration of the META Search Engine to multiple independent search engines, calling, control and excellent
Change and utilize.
META Search Engine is a kind of engine for calling other independent search engines, and herein, " member " is " total ", " surmounting "
Meaning, META Search Engine is exactly integration, calling, control and the Optimum utilization to multiple independent search engines.Draw with respect to Meta Search Engine
Hold up, the independent search engine that can be utilized turns into " source search engine ", or " searching resource ", integrates, calls, controlling and optimization is sharp
With the technology of source search engine, turn into " Meta Search Engine technology ", Meta Search Engine technology is the core of META Search Engine.
The public sentiment data processing module, using Text Mining Technology, text data is entered before text message is obtained
Row pretreatment, including data cleansing, data selection, the characteristic information of text dividing, then extraction text, including keyword carry
Take, term extraction, the information extraction based on template, the concept conversion based on semantic dictionary, the grammer based on shallow parsing
Feature extraction, the semantic feature extraction based on Shallow Semantic Parsing, the text categories acquisition of information based on text classification.
Text mining is a complex art, design data excavation, natural language processing, computational linguistics, information retrieval
And the multiple fields such as classification, information management.The data source that text mining goes out is text data, can be web page, text text
The electronic document of the forms such as part, word and excel files, pdf document.
The public sentiment shows output module, by information cluster, to the special topic of network public-opinion monitoring, focus incident, emphasis
People and the processing of emphasis tissue;By cluster analysis, the different types of network information is condensed together, it is of all categories for analyzing
The propagation temperature of information.
Information cluster is that one group of sample is divided into some classifications according to similar, makes to belong between same category of sample
Distance is as small as possible, and the distance of different classes of sample room is as big as possible, is polymerize according to similitude.
Information cluster of the present invention uses Bayesian Clustering algorithm.Bayesian Clustering algorithm is the layer of a typical cluster formula
Secondary clustering algorithm, using posterior probability as maximized object function, there is extraordinary Clustering Effect.
Claims (1)
- A kind of 1. multilingual network public-opinion monitor supervision platform, it is characterised in that:Including public sentiment planning module, including data acquisition module, Public sentiment data processing module and public sentiment displaying output module;The public sentiment planning module, once integrated, oriented using the vertical search information special to certain class in web page library Point field extract needs data handled after return to user with some form again;The including data acquisition module, using integration of the META Search Engine to multiple independent search engines, calling, control and optimization profit With;The public sentiment data processing module, using Text Mining Technology, text data is carried out before text message is obtained pre- Processing, including data cleansing, data selection, the characteristic information of text dividing, then extraction text, including keyword extraction, art Language extraction, the information extraction based on template, the concept conversion based on semantic dictionary, the grammar property based on shallow parsing carry Take, the semantic feature extraction based on Shallow Semantic Parsing, the text categories acquisition of information based on text classification;The public sentiment shows output module, by information cluster, to the special topic of network public-opinion monitoring, focus incident, emphasis people and The processing of emphasis tissue;By cluster analysis, the different types of network information is condensed together, for analyzing information of all categories Propagation temperature.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610588976.4A CN107797997A (en) | 2016-09-06 | 2016-09-06 | A kind of multilingual network public-opinion monitor supervision platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610588976.4A CN107797997A (en) | 2016-09-06 | 2016-09-06 | A kind of multilingual network public-opinion monitor supervision platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107797997A true CN107797997A (en) | 2018-03-13 |
Family
ID=61527602
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610588976.4A Pending CN107797997A (en) | 2016-09-06 | 2016-09-06 | A kind of multilingual network public-opinion monitor supervision platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107797997A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109710767A (en) * | 2019-01-02 | 2019-05-03 | 山东省科学院情报研究所 | Multilingual big data service platform |
-
2016
- 2016-09-06 CN CN201610588976.4A patent/CN107797997A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109710767A (en) * | 2019-01-02 | 2019-05-03 | 山东省科学院情报研究所 | Multilingual big data service platform |
CN109710767B (en) * | 2019-01-02 | 2022-08-30 | 山东省科学院情报研究所 | Multilingual big data service platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Al-Radaideh et al. | Application of rough set-based feature selection for Arabic sentiment analysis | |
Sheu | Semantic computing | |
Alami et al. | Cybercrime profiling: Text mining techniques to detect and predict criminal activities in microblog posts | |
KR20130022042A (en) | System for detecting and tracking topic based on topic opinion and social-influencer and method thereof | |
Sharma et al. | Polarity detection at sentence level | |
Yue et al. | Analysis of the combination of natural language processing and search engine technology | |
KR102334236B1 (en) | Method and application of meaningful keyword extraction from speech-converted text data | |
US20220083549A1 (en) | Generating query answers from a user's history | |
Bagalkotkar et al. | A novel technique for efficient text document summarization as a service | |
CN104991909B (en) | A kind of dictionary method for auto constructing for specific software history codes storehouse | |
Chang et al. | A tracking and summarization system for online Chinese news topics | |
Aliprandi et al. | CAPER: Collaborative information, acquisition, processing, exploitation and reporting for the prevention of organised crime | |
Kumar et al. | A summarization on text mining techniques for information extracting from applications and issues | |
Colace et al. | A query expansion method based on a weighted word pairs approach | |
Wohlgenannt | Leveraging and balancing heterogeneous sources of evidence in ontology learning | |
WO2012091541A1 (en) | A semantic web constructor system and a method thereof | |
CN107797997A (en) | A kind of multilingual network public-opinion monitor supervision platform | |
Vaseeharan et al. | Review on sentiment analysis of twitter posts about news headlines using machine learning approaches and naïve bayes classifier | |
Khan | Addressing big data problems using semantics and natural language understanding | |
Wang et al. | Multi-emotion category improving embedding for sentiment classification | |
Hajjem et al. | Building comparable corpora from social networks | |
Kannan et al. | Text document clustering using statistical integrated graph based sentence sensitivity ranking algorithm | |
Ko | Unstructured Data Processing Using Keyword-Based Topic-Oriented Analysis | |
Han et al. | A framework for detecting key topics in social networks | |
Cherichi et al. | Big data analysis for event detection in microblogs |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180313 |
|
WD01 | Invention patent application deemed withdrawn after publication |