CN107562722A - Internet public feelings monitoring analysis system based on big data - Google Patents
Internet public feelings monitoring analysis system based on big data Download PDFInfo
- Publication number
- CN107562722A CN107562722A CN201710693741.6A CN201710693741A CN107562722A CN 107562722 A CN107562722 A CN 107562722A CN 201710693741 A CN201710693741 A CN 201710693741A CN 107562722 A CN107562722 A CN 107562722A
- Authority
- CN
- China
- Prior art keywords
- module
- network information
- credit
- public
- class
- 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.)
- Withdrawn
Links
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of internet public feelings monitoring analysis system based on big data, including：Network Information Gathering module, website credit evaluation module, network information sorting module, credit calculate order module, public sentiment trend analysis module and assessment result output module.Public sentiment monitoring system provided by the invention, based on Network Capture public feelings information, classification processing is carried out to the information of acquisition according to keyword, and overall judgement is carried out to public sentiment according to Sentiment orientation, treatment effeciency is high, assesses the real-time for comprehensively, being advantageous to public sentiment monitoring, reliability.
Description
Technical field
The present invention relates to technical field of information processing, more particularly to a kind of internet public feelings monitoring analysis based on big data
System.
Background technology
Network public-opinion monitoring refers to by collecting to network various information, classifying, integrating, technical finesse, then the shape such as screening
One process of the real-time statistical reports such as paired network hotspot, dynamic, netizen's opinion.
With the fast development of internet, the network media has goed deep into the day of people as a kind of new information mode of propagation
Often life.Online friend's speech enlivens oneself and reaches unprecedented degree, whether domestic or international major event, can horse back shape
Into Internet public opinion, viewpoint, propagating thought are expressed by this network, and then produce huge pressure from public opinion, reaches any portion
The stage that door, mechanism can not all ignore.It can be said that internet turns into the distribution centre of ideology and culture information and putting for public opinion
Big device.
Network public-opinion be by having of being held to some focuses, focal issue in actual life of the public of transmission on Internet compared with
Strong influence power, tendentious speech and viewpoint, mainly by BBS forums, blog, news follow-up post, be posted etc. and to realize and be subject to strong
Change.Now, information propagation interacts unprecedented fast with opinion, and the expression demand of network public opinion is also increasingly polynary.If guiding is not good at,
Negative network public-opinion will form larger threat to social public security.For related governmental departments, how to strengthen to network
The timely monitoring of public opinion, effectively guiding, with the positive neutralizing to network public opinion crisis of dieing, to maintaining social stability, promoting country
Development has important practical significance, and creates harmonious society and should have an intension.
The content of the invention
Based on technical problem existing for background technology, the present invention proposes a kind of internet public feelings monitoring based on big data
Analysis system.
A kind of internet public feelings monitoring analysis system based on big data proposed by the present invention, including：
Network Information Gathering module, for according to default theme collecting network information；
Website credit evaluation module, its internal preset have website credit appraisal model, and for being tested and assessed according to website credit
Model is assessed each website and assigns credit value；
Network information sorting module, it is connected with Network Information Gathering module, it obtains Network Information Gathering module collection
The network information, and keyword extraction is carried out to the network information, then carrying out cluster to the network information according to keyword obtains much
In an info class；
Credit calculates order module, and it connects network information sorting module, Network Information Gathering module and website letter respectively
With evaluation module, it is counted to the network information source web included in each info class, calculates the net that each info class includes
The credit value sum of network information source website believes weights as class, and believes that weights are ranked up to each info class according to class；
Public sentiment trend analysis module, it calculates order module with network information sorting module and credit respectively and is connected, its root
It is that each info class assigns a Sentiment orientation value according to keyword, then according to default emotion assessment models combination Sentiment orientation value
The emotion value of each info class of weight computing is believed with class, and calculates info class emotion value sum as theme emotion value；Public sentiment is inclined to
Theme emotion value compared with default tendency threshold value, public sentiment tendency is assessed according to comparative result by analysis module；
Assessment result output module, it connects credit and calculates order module and the analysis of public opinion module respectively, and it is by credit meter
Assessment table is made in the ranking results for calculating order module, and each info class is distinguished according to keyword in assessment table；Assessment result is defeated
Go out module output assessment table and public sentiment tendency.
Preferably, public sentiment trend analysis module judges each keyword part of speech in each info class, and according to each keyword part of speech
Calculate the info class Sentiment orientation value.
Preferably, the radiometer of commendatory term and derogatory term in public sentiment trend analysis module keyword according to corresponding to info class
Calculate the info class Sentiment orientation value.
In a kind of internet public feelings monitoring analysis system based on big data proposed by the present invention, network information sorting module
The network information of Network Information Gathering module collection is obtained, and keyword extraction is carried out to the network information, then by keyword phase
The same network information carries out cluster and obtains info class.So as to which the analysis of the network information to be converted to the analysis work of info class, letter
Change the workload of network information monitoring, avoided redundancy of effort, be advantageous to improve the efficient and real-time of public sentiment monitoring.
In the present invention, the website in network information source is assessed in real time by website credit evaluation module, is advantageous to
The reliability in network information source is grasped, is judged so as to improve network information authenticity, it is each to calculate order module calculating for credit
The class letter weights of info class lay the foundation.Public sentiment trend analysis module reference class when calculating Sentiment orientation believes weights, improves
The confidence level of Sentiment orientation result of calculation, so as to improve the confidence level of whole public sentiment monitoring.
Internet public feelings monitoring analysis system provided by the invention based on big data, based on Network Capture public feelings information,
Classification processing is carried out to the information of acquisition according to keyword, and overall judgement, treatment effeciency are carried out to public sentiment according to Sentiment orientation
Height, assess the real-time for comprehensively, being advantageous to public sentiment monitoring, reliability.
Brief description of the drawings
Fig. 1 is a kind of functional module frame of the internet public feelings monitoring analysis system based on big data proposed by the present invention
Figure.
Embodiment
Reference picture 1, a kind of internet public feelings monitoring analysis system based on big data proposed by the present invention, including：Network
Information collection module, website credit evaluation module, network information sorting module, credit calculate order module, public sentiment trend analysis
Module and assessment result output module.
Network Information Gathering module is used for according to default theme collecting network information.Specifically, theme is by staff
It is manually entered, or, the information that Network Information Gathering module inputs according to staff carries out simplifying extraction theme.
Website credit evaluation module, its internal preset have website credit appraisal model, and for being tested and assessed according to website credit
Model is assessed each website and assigns credit value.In present embodiment, credit value can be issued according on the website
Information through carrying out really degree confirmation is assessed.For example, 10 can be randomly selected from the website has had been acknowledged true journey
The information evaluation website credit value of angle value, the website credit value are that 10 information truth degree values obtain average.
Network information sorting module is connected with Network Information Gathering module.Network information sorting module obtains the network information and received
Collect the network information of module collection, and keyword extraction is carried out to the network information, then enter the keyword identical network information
Row cluster, an info class is no less than to obtain.In present embodiment, info class is marked with keyword to distinguish.
Credit calculating order module connects network information sorting module, Network Information Gathering module and website credit and commented respectively
Estimate module.Credit calculates order module and the network information source web included in each info class is counted, and calculates each information
The credit value sum for the network information source web that class includes believes weights as the class of the info class, and believes weights to each according to class
Info class is ranked up.
Public sentiment trend analysis module calculates order module with network information sorting module and credit respectively and is connected.Public sentiment is inclined to
Analysis module judges each keyword part of speech in each info class, and calculates the info class Sentiment orientation value according to each keyword part of speech.
Specifically, the ratio calculation of commendatory term and derogatory term information in public sentiment trend analysis module keyword according to corresponding to info class
Class Sentiment orientation value.When the ratio of commendatory term number and derogatory term number in keyword corresponding to info class is more than 1, then the information
The Sentiment orientation value of class is positive number；When the ratio of commendatory term number and derogatory term number in keyword corresponding to info class is less than 1,
Then the Sentiment orientation value of the info class is negative.
In present embodiment, public sentiment trend analysis module is that each info class assigns a Sentiment orientation value according to keyword
Afterwards, the emotion value of each info class of weight computing is believed according to default emotion assessment models combination Sentiment orientation value and class, and calculated
Info class emotion value sum is as theme emotion value.
Assessment result output module connects credit and calculates order module and the analysis of public opinion module respectively, and credit is calculated and arranged by it
Assessment table is made in the ranking results of sequence module, and each info class is distinguished according to keyword in assessment table；Assessment result exports mould
Table and public sentiment tendency are assessed in block output.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art the invention discloses technical scope in, technique according to the invention scheme and its
Inventive concept is subject to equivalent substitution or change, should all be included within the scope of the present invention.
Claims (1)
- A kind of 1. internet public feelings monitoring analysis system based on big data, it is characterised in that including：Network Information Gathering module, for according to default theme collecting network information；Website credit evaluation module, its internal preset have website credit appraisal model, and for according to website credit appraisal model Each website is assessed and assigns credit value；Network information sorting module, it is connected with Network Information Gathering module, it obtains the network of Network Information Gathering module collection Information, and keyword extraction is carried out to the network information, then carrying out cluster to the network information according to keyword obtains no less than one Individual info class；Credit calculates order module, and it connects network information sorting module, Network Information Gathering module and website credit and commented respectively Estimate module, it is counted to the network information source web included in each info class, calculates the network letter that each info class includes The credit value sum for ceasing source web believes weights as class, and believes that weights are ranked up to each info class according to class；Public sentiment trend analysis module, it calculates order module with network information sorting module and credit respectively and is connected, and it is according to pass Keyword is that each info class assigns a Sentiment orientation value, then according to default emotion assessment models combination Sentiment orientation value and class Believe the emotion value of each info class of weight computing, and calculate info class emotion value sum as theme emotion value；Public sentiment trend analysis Theme emotion value compared with default tendency threshold value, public sentiment tendency is assessed according to comparative result by module；Assessment result output module, it connects credit and calculates order module and the analysis of public opinion module respectively, and credit is calculated and arranged by it Assessment table is made in the ranking results of sequence module, and each info class is distinguished according to keyword in assessment table；Assessment result exports mould Table and public sentiment tendency are assessed in block output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710693741.6A CN107562722A (en) | 2017-08-14 | 2017-08-14 | Internet public feelings monitoring analysis system based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710693741.6A CN107562722A (en) | 2017-08-14 | 2017-08-14 | Internet public feelings monitoring analysis system based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107562722A true CN107562722A (en) | 2018-01-09 |
Family
ID=60975381
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710693741.6A Withdrawn CN107562722A (en) | 2017-08-14 | 2017-08-14 | Internet public feelings monitoring analysis system based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107562722A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108595472A (en) * | 2018-03-07 | 2018-09-28 | 合肥工业大学 | A kind of government website public sentiment monitoring system based on semantic analysis |
| CN109492105A (en) * | 2018-11-10 | 2019-03-19 | 上海文军信息技术有限公司 | A kind of text sentiment classification method based on multiple features integrated study |
| CN112949691A (en) * | 2021-02-02 | 2021-06-11 | 山东寻声网络科技有限公司 | Public opinion monitoring system for enterprise |
| CN114676745A (en) * | 2022-01-18 | 2022-06-28 | 北京国信网联科技有限公司 | Big data intelligent analysis system |
| CN116775974A (en) * | 2023-06-29 | 2023-09-19 | 中咨高技术咨询中心有限公司 | Information screening method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744877A (en) * | 2013-12-20 | 2014-04-23 | 潘大庆 | Public opinion monitoring application system deployed in internet and application method |
| CN105975642A (en) * | 2016-07-15 | 2016-09-28 | 合肥指南针电子科技有限责任公司 | Public opinion monitoring method based on network big data |
| CN106126558A (en) * | 2016-06-16 | 2016-11-16 | 东软集团股份有限公司 | A kind of public sentiment monitoring method and device |
| CN106202048A (en) * | 2016-07-15 | 2016-12-07 | 合肥指南针电子科技有限责任公司 | A kind of public sentiment monitoring system |
| CN106227772A (en) * | 2016-07-15 | 2016-12-14 | 合肥指南针电子科技有限责任公司 | A kind of public sentiment monitoring system based on semantic analysis |
-
2017
- 2017-08-14 CN CN201710693741.6A patent/CN107562722A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103744877A (en) * | 2013-12-20 | 2014-04-23 | 潘大庆 | Public opinion monitoring application system deployed in internet and application method |
| CN106126558A (en) * | 2016-06-16 | 2016-11-16 | 东软集团股份有限公司 | A kind of public sentiment monitoring method and device |
| CN105975642A (en) * | 2016-07-15 | 2016-09-28 | 合肥指南针电子科技有限责任公司 | Public opinion monitoring method based on network big data |
| CN106202048A (en) * | 2016-07-15 | 2016-12-07 | 合肥指南针电子科技有限责任公司 | A kind of public sentiment monitoring system |
| CN106227772A (en) * | 2016-07-15 | 2016-12-14 | 合肥指南针电子科技有限责任公司 | A kind of public sentiment monitoring system based on semantic analysis |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108595472A (en) * | 2018-03-07 | 2018-09-28 | 合肥工业大学 | A kind of government website public sentiment monitoring system based on semantic analysis |
| CN109492105A (en) * | 2018-11-10 | 2019-03-19 | 上海文军信息技术有限公司 | A kind of text sentiment classification method based on multiple features integrated study |
| CN109492105B (en) * | 2018-11-10 | 2022-11-15 | 上海五节数据科技有限公司 | Text emotion classification method based on multi-feature ensemble learning |
| CN112949691A (en) * | 2021-02-02 | 2021-06-11 | 山东寻声网络科技有限公司 | Public opinion monitoring system for enterprise |
| CN114676745A (en) * | 2022-01-18 | 2022-06-28 | 北京国信网联科技有限公司 | Big data intelligent analysis system |
| CN116775974A (en) * | 2023-06-29 | 2023-09-19 | 中咨高技术咨询中心有限公司 | Information screening method |
| CN116775974B (en) * | 2023-06-29 | 2024-02-23 | 中咨高技术咨询中心有限公司 | Information screening method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107562722A (en) | Internet public feelings monitoring analysis system based on big data | |
| Dahal et al. | Topic modeling and sentiment analysis of global climate change tweets | |
| US10810317B2 (en) | Sensitive data classification | |
| CN104899267B (en) | A kind of integrated data method for digging of social network sites account similarity | |
| CN106940732A (en) | A kind of doubtful waterborne troops towards microblogging finds method | |
| CN101408883B (en) | Method for collecting network public feelings viewpoint | |
| CN105426762B (en) | A kind of static detection method that android application programs are malicious | |
| CN103324745B (en) | Text garbage recognition methods and system based on Bayesian model | |
| CN103793503A (en) | Opinion mining and classification method based on web texts | |
| CN107729919A (en) | In-depth based on big data technology is complained and penetrates analysis method | |
| CN103886108B (en) | The feature selecting and weighing computation method of a kind of unbalanced text set | |
| CN103077190A (en) | Hot event ranking method based on order learning technology | |
| CN101908055B (en) | Method for setting information classification threshold for optimizing lam percentage and information filtering system using same | |
| CN105319071A (en) | Diesel engine fuel oil system fault diagnosis method based on least square support vector machine | |
| CN107341183A (en) | A kind of Website classification method based on darknet website comprehensive characteristics | |
| CN103678512A (en) | Data stream merge sorting method under dynamic data environment | |
| CN107438083B (en) | Detection method for phishing site and its detection system under a kind of Android environment | |
| CN103927297A (en) | Evidence theory based Chinese microblog credibility evaluation method | |
| CN106446124B (en) | A kind of Website classification method based on cyberrelationship figure | |
| CN107885849A (en) | A kind of moos index analysis system based on text classification | |
| CN107809370B (en) | User recommendation method and device | |
| CN106681989A (en) | Method for predicting microblog forwarding probability | |
| CN107679069A (en) | Method is found based on a kind of special group of news data and related commentary information | |
| CN104572877A (en) | Detection method and detection system of game public opinion | |
| CN111639706A (en) | Personal risk portrait generation method based on image set and related equipment |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180109 |