CN105468768A - System monitoring method of WeChat public sentiment - Google Patents
System monitoring method of WeChat public sentiment Download PDFInfo
- Publication number
- CN105468768A CN105468768A CN201510895594.1A CN201510895594A CN105468768A CN 105468768 A CN105468768 A CN 105468768A CN 201510895594 A CN201510895594 A CN 201510895594A CN 105468768 A CN105468768 A CN 105468768A
- Authority
- CN
- China
- Prior art keywords
- public
- information
- micro
- public sentiment
- supervision
- 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
- G06F16/958—Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking
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)
Abstract
The invention discloses a system monitoring method of WeChat public sentiment. One set of integral public sentiment supervision system is established to realize the monitoring of WeChat public sentiment propagation. Through a way that WeChat crowd funding volunteers are recruited, data is provided for a monitoring platform, a machine learning method is used for analyzing a text and a picture to judge the property of information, and finally, the propagation speed of the WeChat public sentiment in a certain regional range is evaluated in a sampling way according to the geographic information of a whistleblower.
Description
Technical field
The present invention relates to network flame detection field, particularly a kind of system monitoring method of micro-letter public sentiment.
Background technology
Along with the high speed development of network new media, the micro-letter as novel social network-i i-platform will become the fresh position of public sentiment monitoring.Till in November, 2013, the registered user of micro-letter platform breaks through 600,000,000, and public account is more than 2,000,000, and the average daily registration amount about 8000 of public account.Micro-letter is diffused information by circle of friends, has and propagates the large feature of the degree of depth.In addition, micro-letter sets up strong relation chain by Tencent QQ and telephonic communication record, propagates and has very high arrival rate and forward rate.
The micro-letter of individual is that acquaintance encloses interchange, has relative closure, is difficult to form strong public opinion field.The interactive difference of micro-letter public platform, but influence power is strong.Because public number has huge customer volume, strong to flame Spreading and diffusion ability, easily cause the diffusion of network public-opinion.But micro-letter public sentiment propagates general layout complexity, along with the fusion with other media of network, causes the blending of various public opinion platform.In addition, the not yet opening of micro-letter personal platform, directly causes the complicacy that micro-letter public sentiment is monitored.
At this, pay close attention to the flame or network public-opinion propagated in micro-letter public platform, set up micro-letter public sentiment monitoring system from management mode and technology two aspects and just seem particularly necessary.
Through finding the literature search of prior art, China Patent Publication No. is: CN101661513B, patent name is: the detection method of network hotspot and public sentiment, the present solution provides the detection method of a kind of monitoring network microblogging public sentiment in network information processing field.By the microblogging text message within the scope of collection certain hour and review information, and carry out word segmentation processing, Conceptual Projection process to the content of text of these information, eliminate the uncertainty of semantic concept, final extraction can reflect the feature of content of text.Recycle these content characteristic data and carry out cluster, form the information document set that several comprise unequal number amount, gather according to each number comprising information document and determine whether focus incident in network, the information document set of focus incident is being passed judgement on to the analysis of tendency, thus grasp netizen to the public sentiment viewpoint of this event, detect microblogging public sentiment with this.
In New Media Technology, microblogging and micro-letter are two kinds of important Information Communication forms, but but have important difference.Micro-letter has stronger social networks circle than microblogging, and information propagates in circle of friends, has stronger information accessibility and disguise; In addition, micro-letter mainly launches to propagate in mobile phone terminal mode, is difficult to carry out crawling and analyzing of information technically, has stronger Information Communication privacy.
Therefore, existing microblogging public sentiment monitoring technology is difficult to apply in micro-letter public sentiment, and mainly because micro-credit household uses mobile phone terminal, micro-letter platform does not provide the api interface of data grabber yet simultaneously, causes initiatively capturing micro-letter data very difficult.The present invention adopts a kind of passive collection and filters the method for micro-letter public sentiment data, and the management mode that network crowd raises realizes the monitoring of micro-letter public sentiment, completely different from microblogging public sentiment monitoring technology.
Based on this, a kind of public sentiment detection system method for micro-letter is provided just to seem particularly necessary.
Summary of the invention
For solving above-mentioned prior art Problems existing, the object of the present invention is to provide a kind of system monitoring method of micro-letter public sentiment, being realized the monitoring that micro-letter public sentiment is propagated by the public sentiment supervision system setting up complete set.The mode adopting the micro-believers of recruit network to raise volunteer provides data to monitoring platform, the method re-using machine learning, to analyze the character that text and image data judge information, finally assesses the prevalence of micro-letter public sentiment in certain territorial scope according to the geography information sample mode of informant.
For achieving the above object, technical scheme of the present invention is:
A system monitoring method for micro-letter public sentiment, comprises the steps:
Step one, the micro-letter public sentiment supervision public number established authority, the pattern utilizing the network promotion and volunteer crowd to raise carrys out micro-letter supervision platform of Erecting and improving.Common micro-credit household first registers public sentiment supervision public number, then provides suspicious micro-letter public sentiment link information to public sentiment supervision public number, raises enforcement mechanisms to manage public sentiment supervision public number platform with the network crowd of a kind of " everybody supervision ".
Step 2, set up public sentiment supervision public number background intelligent analytic system, by information filtering with analyze the linking point excavating network public-opinion.Micro-credit household can supervise public number to public sentiment and send information, and in this transmission is suspicious public sentiment link information.First adopt programming technique obtain crowd raise user the text message sent out, can obtain simultaneously crowd raise user the pictorial information sent out, secondly, the mode of Word Intelligent Segmentation is adopted to analyze the text message of report, OCR image-recognizing method is used to judge pictorial information, finally the form of a theme and content links is formed to micro-letter message that each crowd raises user's report, the sorting technique of machine learning is used to determine the probability belonging to public feelings information, and be that every bar data add label that is optimum or malice, if there is conviction, attitude, suggestion and mood etc. performance too unusual and run counter to lowest permissible level of virtue and be unfavorable for social development all will be sticked the label of malice, if be conducive to social progress will be sticked optimum label.
Step 3, raise micro-letter geographical attribute of user according to crowd, the mode of random sampling is adopted to assess the propagation condition of a certain public feelings information, first randomly draw a public feelings information with machine, then analyze his hop count, comment number of times and viewing number of times, then will carry out analysis propagation condition to it.Extract the essential information of public sentiment user, wherein the most important thing is the geographical location information of its GPS, its geography information is determined in position public sentiment released news by machine behind location, the sampling instances of certain public sentiment in certain geographic range can be judged according to public sentiment supervision platform background analysis, use the program in supervision platform, information is repeatedly decomposed, and then the geographic Location Classification of each information is assembled the situation understanding sampling with this, finally infer population distribution according to arbitrary sampling method with the probability of sampling, the prevalence of certain public feelings information in region, local is assessed with this.
Step 4, adjusted by real example mode, optimize supervision the machine learning of platform backstage parameter.Concrete real example statistical method is as follows: recruit a large amount of university student and raise user as micro-believers, public number a large amount of of micro-letters is provided to micro-letter supervision by the public number, supervise all kinds of public number public feelings information of initiating again, analyzed by back-end data, optimize the parameter of machine learning gradually, when each public number is initiated public feelings information, then back-end data is analyzed, machine is optimized study, repeatedly learns to optimize with this, thus effectively realize adjustment, optimize supervision platform backstage machine.
The beneficial effect that the present invention reaches is: the system monitoring method of this kind of micro-letter public sentiment, is realized the monitoring of propagating micro-letter public sentiment by the public sentiment supervision system setting up complete set.The mode adopting recruit network micro-believers to raise volunteer provides data to monitoring platform, and the method re-using machine learning is to analyze text and image data is sentenced
The character of disconnected information, finally assesses the prevalence of micro-letter public sentiment in certain territorial scope according to the geography information sample mode of informant, and structure is simple, is easy to promote.
Accompanying drawing explanation
Accompanying drawing is used to provide a further understanding of the present invention, and forms a part for instructions, together with embodiments of the present invention for explaining the present invention, is not construed as limiting the invention.
In the accompanying drawings:
Fig. 1 is the one-piece construction schematic diagram described in the embodiment of the present invention;
Embodiment
Below in conjunction with embodiment, the preferred embodiments of the present invention are described, should be appreciated that preferred embodiment described herein is only for instruction and explanation of the present invention, is not intended to limit the present invention.
As shown in Figure 1: a kind of system monitoring method of micro-letter public sentiment, the micro-letter public sentiment supervision public number comprise the steps: step one, establishing authority, the pattern utilizing the network promotion and volunteer crowd to raise carrys out micro-letter supervision platform of Erecting and improving.Common micro-credit household first registers public sentiment supervision public number, then provides suspicious micro-letter public sentiment link information to public sentiment supervision public number, raises enforcement mechanisms to manage public sentiment supervision public number platform with the network crowd of a kind of " everybody supervision ".
Step 2, set up public sentiment supervision public number background intelligent analytic system, by information filtering with analyze the linking point excavating network public-opinion.Micro-credit household can supervise public number to public sentiment and send information, and in this transmission is suspicious public sentiment link information.First adopt programming technique obtain crowd raise user the text message sent out, can obtain simultaneously crowd raise user the pictorial information sent out, secondly, the mode of Word Intelligent Segmentation is adopted to analyze the text message of report, OCR image-recognizing method is used to judge pictorial information, the generation around intermediary social event such as can be detected when Word Intelligent Segmentation, development and change, as the common people of main body to the social governor as object, enterprise, individual and other various organizations and politics thereof, society, the orientation of the aspects such as morals produces and the meaning no harm of the social attitude held, simultaneously when using OCR image recognition, whether the information that can detect in picture hinders
And social development, whether touch lowest permissible level of virtue, whether personal attack etc. is caused to other people, finally the form of a theme and content links is formed to micro-letter message that each crowd raises user's report, the sorting technique of machine learning is used to determine the probability belonging to public feelings information, and be that every bar data add label that is optimum or malice, if there is conviction, attitude, suggestion and mood etc. performance too unusual and run counter to lowest permissible level of virtue and be unfavorable for social development all will be sticked the label of malice, if be conducive to social progress will be sticked optimum label.
Step 3, raise micro-letter geographical attribute of user according to crowd, the mode of random sampling is adopted to assess the propagation condition of a certain public feelings information, first randomly draw a public feelings information with machine, then analyze his hop count, comment number of times and viewing number of times, then will carry out analysis propagation condition to it.Extract the essential information of public sentiment user, wherein the most important thing is the geographical location information of its GPS, its geography information is determined in position public sentiment released news by machine behind location, the sampling instances of certain public sentiment in certain geographic range can be judged according to public sentiment supervision platform background analysis, use the program in supervision platform, information is repeatedly decomposed, and then the geographic Location Classification of each information is assembled the situation understanding sampling with this, finally infer population distribution according to arbitrary sampling method with the probability of sampling, the prevalence of certain public feelings information in region, local is assessed with this.
Step 4, adjusted by real example mode, optimize supervision the machine learning of platform backstage parameter.Concrete real example statistical method is as follows: recruit a large amount of university student and raise user as micro-believers, public number a large amount of of micro-letters is provided to micro-letter supervision by the public number, supervise all kinds of public number public feelings information of initiating again, analyzed by back-end data, optimize the parameter of machine learning gradually, when each public number is initiated public feelings information, then back-end data is analyzed, machine is optimized study, repeatedly learns to optimize with this, thus effectively realize adjustment, optimize supervision platform backstage machine.
Experimental example:
Utilize the inventive method to carry out real example checking in public number of 500 micro-letters, 2000 suspicious micro-letter public sentiment links can be intercepted and captured every day, find that the accuracy rate of public sentiment monitoring is close to 75% through equipment analysis and artificial judgment.Find after continuing experiment in 15 days that micro-letter public sentiment monitoring system misses alert rate lower than 20%.
The above, be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, and any change of expecting without creative work or replacement, all should be encompassed within protection scope of the present invention.Therefore, the protection domain that protection scope of the present invention should limit with claims is as the criterion.
Claims (1)
1. a system monitoring method for micro-letter public sentiment, comprises the steps:
Step one, the micro-letter public sentiment supervision public number established authority, the pattern utilizing the network promotion and volunteer crowd to raise carrys out micro-letter supervision platform of Erecting and improving.Common micro-credit household first registers public sentiment supervision public number, then provides suspicious micro-letter public sentiment link information to public sentiment supervision public number, raises enforcement mechanisms to manage public sentiment supervision public number platform with the network crowd of a kind of " everybody supervision ";
Step 2, set up public sentiment supervision public number background intelligent analytic system, by information filtering with analyze the linking point excavating network public-opinion.Micro-credit household can supervise public number to public sentiment and send information, and in this transmission is suspicious public sentiment link information.First adopt programming technique obtain crowd raise user the text message sent out, can obtain simultaneously crowd raise user the pictorial information sent out, secondly, the mode of Word Intelligent Segmentation is adopted to analyze the text message of report, OCR image-recognizing method is used to judge pictorial information, finally the form of a theme and content links is formed to micro-letter message that each crowd raises user's report, the sorting technique of machine learning is used to determine the probability belonging to public feelings information, and be that every bar data add label that is optimum or malice, if there is conviction, attitude, suggestion and mood etc. performance too unusual and run counter to lowest permissible level of virtue and be unfavorable for social development all will be sticked the label of malice, if be conducive to social progress will be sticked optimum label
Step 3, raise micro-letter geographical attribute of user according to crowd, the mode of random sampling is adopted to assess the propagation condition of a certain public feelings information, first randomly draw a public feelings information with machine, then analyze his hop count, comment number of times and viewing number of times, then will carry out analysis propagation condition to it.Extract the essential information of public sentiment user, wherein the most important thing is the geographical location information of its GPS, its geography information is determined in position public sentiment released news by machine behind location, the sampling instances of certain public sentiment in certain geographic range can be judged according to public sentiment supervision platform background analysis, use the program in supervision platform, information is repeatedly decomposed, and then the geographic Location Classification of each information is assembled the situation understanding sampling with this, finally infer population distribution according to arbitrary sampling method with the probability of sampling, the prevalence of certain public feelings information in region, local is assessed with this.
Step 4, adjusted by real example mode, optimize supervision the machine learning of platform backstage parameter.Concrete real example statistical method is as follows: recruit a large amount of university student and raise user as micro-believers, public number a large amount of of micro-letters is provided to micro-letter supervision by the public number, supervise all kinds of public number public feelings information of initiating again, analyzed by back-end data, optimize the parameter of machine learning gradually, when each public number is initiated public feelings information, then back-end data is analyzed, machine is optimized study, repeatedly learns to optimize with this, thus effectively realize adjustment, optimize supervision platform backstage machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510895594.1A CN105468768A (en) | 2015-12-07 | 2015-12-07 | System monitoring method of WeChat public sentiment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510895594.1A CN105468768A (en) | 2015-12-07 | 2015-12-07 | System monitoring method of WeChat public sentiment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105468768A true CN105468768A (en) | 2016-04-06 |
Family
ID=55606468
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510895594.1A Pending CN105468768A (en) | 2015-12-07 | 2015-12-07 | System monitoring method of WeChat public sentiment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105468768A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372173A (en) * | 2016-08-31 | 2017-02-01 | 广西德高仕安全技术有限公司 | File management method based on wechat public service platform |
| CN106528869A (en) * | 2016-12-05 | 2017-03-22 | 深圳大图科创技术开发有限公司 | Topic detection apparatus |
| 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 |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982381A (en) * | 2012-12-06 | 2013-03-20 | 湖南蚁坊软件有限公司 | Microblog propagation influence area managing system and microblog propagation influence area managing method |
| CN103092950A (en) * | 2013-01-15 | 2013-05-08 | 重庆邮电大学 | Online public opinion geographical location real time monitoring system and method |
| CN104063456A (en) * | 2014-06-25 | 2014-09-24 | 红麦聚信(北京)软件技术有限公司 | We media transmission atlas analysis method and device based on vector query |
| CN104504141A (en) * | 2015-01-04 | 2015-04-08 | 青岛农业大学 | Two-dimensional code type chemical toxicity information building and searching method |
| CN104933093A (en) * | 2015-05-19 | 2015-09-23 | 武汉泰迪智慧科技有限公司 | Regional public opinion monitoring and decision-making auxiliary system and method based on big data |
-
2015
- 2015-12-07 CN CN201510895594.1A patent/CN105468768A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102982381A (en) * | 2012-12-06 | 2013-03-20 | 湖南蚁坊软件有限公司 | Microblog propagation influence area managing system and microblog propagation influence area managing method |
| CN103092950A (en) * | 2013-01-15 | 2013-05-08 | 重庆邮电大学 | Online public opinion geographical location real time monitoring system and method |
| CN104063456A (en) * | 2014-06-25 | 2014-09-24 | 红麦聚信(北京)软件技术有限公司 | We media transmission atlas analysis method and device based on vector query |
| CN104504141A (en) * | 2015-01-04 | 2015-04-08 | 青岛农业大学 | Two-dimensional code type chemical toxicity information building and searching method |
| CN104933093A (en) * | 2015-05-19 | 2015-09-23 | 武汉泰迪智慧科技有限公司 | Regional public opinion monitoring and decision-making auxiliary system and method based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 幸运这回: "微信舆情监控解决方案", 《百度文库》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372173A (en) * | 2016-08-31 | 2017-02-01 | 广西德高仕安全技术有限公司 | File management method based on wechat public service platform |
| CN106528869A (en) * | 2016-12-05 | 2017-03-22 | 深圳大图科创技术开发有限公司 | Topic detection apparatus |
| 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 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Forelle et al. | Political bots and the manipulation of public opinion in Venezuela | |
| Zannettou et al. | Disinformation warfare: Understanding state-sponsored trolls on Twitter and their influence on the web | |
| Blondel et al. | A survey of results on mobile phone datasets analysis | |
| Chhabra et al. | Phi. sh/$ ocial: the phishing landscape through short urls | |
| CN109600752B (en) | Deep clustering fraud detection method and device | |
| CN108924333B (en) | Fraud telephone identification method, device and system | |
| CN106791220B (en) | Method and system for preventing telephone fraud | |
| Avvenuti et al. | Ears (earthquake alert and report system) a real time decision support system for earthquake crisis management | |
| Elmas et al. | Ephemeral astroturfing attacks: The case of fake twitter trends | |
| Oentaryo et al. | On profiling bots in social media | |
| CN104933093A (en) | Regional public opinion monitoring and decision-making auxiliary system and method based on big data | |
| CN103415004B (en) | A kind of method and device detecting junk short message | |
| WO2017193997A1 (en) | Short message filtering method and system | |
| CN103763124A (en) | Internet user behavior analyzing and early-warning system and method | |
| CN104301896A (en) | Intelligent fraud short message monitor and alarm system and method | |
| CN103955505A (en) | Micro-blog-based real-time event monitoring method and system | |
| Wei et al. | The fragility of twitter social networks against suspended users | |
| CN101389074B (en) | Short message monitoring method ensuring identity of sender based social network mechanism | |
| US20150113651A1 (en) | Spammer group extraction apparatus and method | |
| Echeverria et al. | The ‘star wars’ botnet with> 350k twitter bots | |
| CN103369486A (en) | System and method for preventing fraud SMS (Short message Service) message | |
| CN106899948B (en) | Pseudo base station discovery method, system, terminal and server | |
| CN102567101A (en) | Multi-process management system for recognizing and monitoring pornographic images of WAP (wireless application protocol) mobile phone media | |
| CN106911675B (en) | A kind of mobile phone Malware method for early warning and device | |
| CN105468768A (en) | System monitoring method of WeChat public sentiment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160406 |