CN107391712A - A kind of network public opinion trend prediction analysis method - Google Patents
A kind of network public opinion trend prediction analysis method Download PDFInfo
- Publication number
- CN107391712A CN107391712A CN201710633501.7A CN201710633501A CN107391712A CN 107391712 A CN107391712 A CN 107391712A CN 201710633501 A CN201710633501 A CN 201710633501A CN 107391712 A CN107391712 A CN 107391712A
- Authority
- CN
- China
- Prior art keywords
- public opinion
- network public
- network
- analysis method
- keyword
- 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
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
Abstract
The invention discloses a kind of network public opinion trend prediction analysis method, this method includes：Establish keyword database；Network public opinion is obtained, the network public opinion contains the keyword in the keyword database；Obtain the public opinion temperature curve of the network public opinion；The public opinion temperature curve is carried out making second dervative.The present invention first establishes keyword database, then the keyword in the database carries out the screening and tracking of network public opinion, and the temperature containing the network public opinion for having the keyword in the keyword database is carried out to make public opinion temperature curve, and opinion is predicted according to the growth of public opinion temperature, so as to preferably supervise public opinion.
Description
Technical field
The present invention relates to network public opinion technical field, and in particular to a kind of network public opinion trend prediction analysis method.
Background technology
Network has become the important medium for influenceing civil order, tissue interests and personal reputation.By to network public-opinion
It is monitored, has found that it is likely that the public sentiment event for influenceing social development, tissue interests and personal reputation in time, and tackle ahead of time,
Thing through that must be faced as entity and individual of organizations at different levels.
Publication No. CN105608200A Chinese patent literature discloses a kind of network public opinion trend prediction analysis method,
Comprise the following steps, step S101：Agriculture products system, network public opinion information is crawled, by pre-processing index needed for acquisition
Time series；Step S102：Model is established, candidate family is established in the time series acquired；Step S103：Choose most
Excellent model, selection optimal models is compared from the candidate family of foundation；Step S104：Network public opinion trend prediction analysis, is based on
The optimal models of selection is predicted analysis to network public opinion trend.After the above method, the patent lag parameter it is adjustable
Performance enough flexibly adapts to actual demand, while introduces the criterion that MVE is used as model selection, improves to specific public sentiment
The predictive ability of development trend fluctuation.Finally, model can be modified by new data, is created for long-term tracking prediction
May.But the patent have ignored the change of public opinion intension, so as to be modified according to intension to model.
Document " the network public-opinion observation index architectural study based on subject classification, journal of information, 2012, height holds real etc. " will
The network public-opinion early warning monitoring based on event for being difficult to observe be converted to be easy to observation based on the classificatory network of different themes
Public sentiment monitors+defined network public-opinion Intrusion Index, network public-opinion Trend index and network public-opinion accumulation 3 indexes of index, point
The concrete meaning and calculating means of each index are not given, and the finally integrated use to various indexes is discussed.But should
Document is only to illustrate that index is obtained and influenceed, and does not inform the prediction for how carrying out opinion really.
The content of the invention
It is an object of the invention to provide a kind of network public opinion trend prediction analysis method, network public opinion provided by the invention
Trend prediction analysis method, screening public opinion can be carried out according to keyword, and public opinion is predicted according to the growth of public opinion temperature
Trend, so as to preferably supervise public opinion.
To achieve the above object, the present invention provides a kind of network public opinion trend prediction analysis method, and this method includes：
Establish keyword database；
Network public opinion is obtained, the network public opinion contains the keyword in the keyword database；
Obtain the public opinion temperature curve of the network public opinion；
The public opinion temperature curve is carried out making second dervative.
Optionally, the keyword database includes the first sensitive word word bank and negative word word bank and the second sensitive lexon
Storehouse and certainly lexon storehouse；The network public opinion is simultaneously including the keyword in the first sensitive word word bank and negative word word bank
And/or include the second sensitive word word bank and the certainly keyword in lexon storehouse simultaneously.
Optionally, the obtaining step of the public opinion temperature curve for obtaining the network public opinion includes：Using Markov
Model carries out obtaining the public opinion temperature curve；Wherein, the abscissa of the public opinion temperature curve is the time, and ordinate is forwarding
Number, frequency of reading and comment number sum.
Optionally, the public opinion temperature curve is discrete curve, and interval time is 1 second, is used between adjacent discrete curve
Straight line is connected.
Optionally, after the described pair of public opinion temperature curve carries out making second dervative step, methods described also includes：If
The second dervative is all higher than numerical value M in continuous time period t, then judges the network public opinion for popular public opinion.
Optionally, the M is zero.
Optionally, if being all higher than numerical value M in continuous time period t in the described second dervative, the network carriage is judged
After for the step of popular public opinion, methods described also includes：Going to manual analysis and carry out judgement the network public opinion is
It is no to forbid.
The invention has the advantages that：
The present invention first establishes keyword database, and then the keyword in the database carries out the screening of network public opinion
And tracking, and the temperature containing the network public opinion for having the keyword in the keyword database is carried out to make public opinion temperature song
Line, and opinion is predicted according to the growth of public opinion temperature, so as to preferably supervise public opinion.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of the exemplary embodiment of method one provided by the invention.
Embodiment
Following examples are used to illustrate the present invention, but are not limited to the scope of the present invention.
Fig. 1 is the schematic flow sheet of the exemplary embodiment of method one provided by the invention.As shown in figure 1, this method includes
Following steps.
Step 100：Establish keyword database.The keyword database can be some it is pornographic, anti-party it is antisocial with
And there is agitative word, for example, Taiwan, is returned, pornographic, nude etc..Forbid the word of implication except can directly distinguish
Outside language, some words must be combined with other words, such as have ardent love for the motherland, with hating motherland, the meaning is complete on the contrary, still two
The non-word that can directly forbid of word in person, therefore, the keyword database can include the first sensitive word word bank
With negative word word bank and the second sensitive word word bank and affirmative lexon storehouse；It is quick that the network public opinion can include described first simultaneously
Feel lexon storehouse and keyword in negative word word bank and/or include simultaneously in the second sensitive word word bank and certainly lexon storehouse
Keyword, in this situation, such as the network public opinion containing words such as hatred motherland can be found.
Step 200：Network public opinion is obtained, the network public opinion contains the keyword in the keyword database.The network
Public opinion can come from microblogging, webpage, QQ and wechat chat record etc..
Step 300：Obtain the public opinion temperature curve of the network public opinion.The public opinion temperature for obtaining the network public opinion
The obtaining step of curve can include：Carry out obtaining the public opinion temperature curve using Markov model；Wherein, the public opinion
The abscissa of temperature curve is the time, and ordinate is hop count, frequency of reading and comment number sum.The public opinion temperature is bent
Line can be discrete curve, and interval time is 1 second, is connected between adjacent discrete curve using straight line.
Step 400：The public opinion temperature curve is carried out making second dervative.Control for public opinion temperature should be appropriate, such as
Fruit is only propagated in a small range, then should be allowed, people is required for an approach given vent to after all, does not cause to instigate on a large scale
Property, therefore, after the described pair of public opinion temperature curve carries out making second dervative step, methods described can also include：If should
Second dervative is all higher than numerical value M in continuous time period t, then judges the network public opinion for popular public opinion, the M is preferably
Zero.If being all higher than numerical value M in continuous time period t in the described second dervative, judge the network public opinion for popular public opinion
The step of after, methods described can also include：The network public opinion is gone into manual analysis and carries out determining whether to forbid,
And after carrying out screening public opinion using program, artificial screening should be also carried out, to prevent public opinion supervision excessive, it is living to reduce society
Power.
Although above with general explanation and specific embodiment, the present invention is described in detail, at this
On the basis of invention, it can be made some modifications or improvements, this will be apparent to those skilled in the art.Therefore,
These modifications or improvements without departing from theon the basis of the spirit of the present invention, belong to the scope of protection of present invention.
Claims (7)
- A kind of 1. network public opinion trend prediction analysis method, it is characterised in that this method includes：Establish keyword database；Network public opinion is obtained, the network public opinion contains the keyword in the keyword database；Obtain the public opinion temperature curve of the network public opinion；The public opinion temperature curve is carried out making second dervative.
- 2. network public opinion trend prediction analysis method according to claim 1, it is characterised in that the keyword database Including the first sensitive word word bank and negative word word bank and the second sensitive word word bank and affirmative lexon storehouse；The network public opinion is simultaneously Include including the keyword in the first sensitive word word bank and negative word word bank and/or simultaneously the second sensitive word word bank and Certainly the keyword in lexon storehouse.
- 3. network public opinion trend prediction analysis method according to claim 1, it is characterised in that described to obtain the network The obtaining step of the public opinion temperature curve of public opinion includes：Carry out obtaining the public opinion temperature curve using Markov model；Its In, the abscissa of the public opinion temperature curve is the time, and ordinate is hop count, frequency of reading and comment number sum.
- 4. network public opinion trend prediction analysis method according to claim 3, it is characterised in that the public opinion temperature curve For discrete curve, interval time is 1 second, is connected between adjacent discrete curve using straight line.
- 5. network public opinion trend prediction analysis method according to claim 1, it is characterised in that in described pair of public opinion heat Line of writing music is carried out after making second dervative step, and methods described also includes：If the second dervative is big in continuous time period t In numerical value M, then judge the network public opinion for popular public opinion.
- 6. network public opinion trend prediction analysis method according to claim 5, it is characterised in that the M is zero.
- 7. network public opinion trend prediction analysis method according to claim 5, it is characterised in that if being led in the described second order Number is all higher than numerical value M in continuous time period t, then after judging the network public opinion for the step of popular public opinion, methods described Also include：The network public opinion is gone into manual analysis and carries out determining whether to forbid.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710633501.7A CN107391712A (en) | 2017-07-28 | 2017-07-28 | A kind of network public opinion trend prediction analysis method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710633501.7A CN107391712A (en) | 2017-07-28 | 2017-07-28 | A kind of network public opinion trend prediction analysis method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107391712A true CN107391712A (en) | 2017-11-24 |
Family
ID=60341603
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710633501.7A Pending CN107391712A (en) | 2017-07-28 | 2017-07-28 | A kind of network public opinion trend prediction analysis method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107391712A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992478A (en) * | 2017-11-30 | 2018-05-04 | 百度在线网络技术（北京）有限公司 | The method and apparatus for determining focus incident |
| CN109408620A (en) * | 2018-10-11 | 2019-03-01 | 杭州安恒信息技术股份有限公司 | A kind of method, apparatus, equipment and the storage medium of network public opinion trend prediction |
| CN113590925A (en) * | 2020-04-30 | 2021-11-02 | 中国移动通信集团北京有限公司 | User determination method, device, equipment and computer storage medium |
| CN113626722A (en) * | 2020-05-08 | 2021-11-09 | 国家广播电视总局广播电视科学研究院 | Public opinion guiding method, device, equipment and computer readable storage medium |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194001A (en) * | 2011-05-17 | 2011-09-21 | 杭州电子科技大学 | Internet public opinion crisis early-warning method |
| KR101346868B1 (en) * | 2012-11-08 | 2014-02-07 | 경희대학교 산학협력단 | Method for estimating election based on population statistics of selected voter by hour |
| CN103699626A (en) * | 2013-12-20 | 2014-04-02 | 华南理工大学 | Method and system for analysing individual emotion tendency of microblog user |
| CN104573016A (en) * | 2015-01-12 | 2015-04-29 | 武汉泰迪智慧科技有限公司 | System and method for analyzing vertical public opinions based on industry |
| 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 |
| CN105224608A (en) * | 2015-09-06 | 2016-01-06 | 华南理工大学 | The hot news Forecasting Methodology analyzed based on microblog data and system |
| CN105608200A (en) * | 2015-12-28 | 2016-05-25 | 湖南蚁坊软件有限公司 | Network public opinion tendency prediction analysis method |
| CN105740228A (en) * | 2016-01-25 | 2016-07-06 | 云南大学 | Internet public opinion analysis method |
| CN106599065A (en) * | 2016-11-16 | 2017-04-26 | 北京化工大学 | Food safety online public opinion early warning system based on Storm distributed framework |
| CN106651030A (en) * | 2016-12-21 | 2017-05-10 | 重庆邮电大学 | Method for predicting user participation behavior of hot topic by improved RBF neural network |
-
2017
- 2017-07-28 CN CN201710633501.7A patent/CN107391712A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102194001A (en) * | 2011-05-17 | 2011-09-21 | 杭州电子科技大学 | Internet public opinion crisis early-warning method |
| KR101346868B1 (en) * | 2012-11-08 | 2014-02-07 | 경희대학교 산학협력단 | Method for estimating election based on population statistics of selected voter by hour |
| CN103699626A (en) * | 2013-12-20 | 2014-04-02 | 华南理工大学 | Method and system for analysing individual emotion tendency of microblog user |
| CN104573016A (en) * | 2015-01-12 | 2015-04-29 | 武汉泰迪智慧科技有限公司 | System and method for analyzing vertical public opinions based on industry |
| 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 |
| CN105224608A (en) * | 2015-09-06 | 2016-01-06 | 华南理工大学 | The hot news Forecasting Methodology analyzed based on microblog data and system |
| CN105608200A (en) * | 2015-12-28 | 2016-05-25 | 湖南蚁坊软件有限公司 | Network public opinion tendency prediction analysis method |
| CN105740228A (en) * | 2016-01-25 | 2016-07-06 | 云南大学 | Internet public opinion analysis method |
| CN106599065A (en) * | 2016-11-16 | 2017-04-26 | 北京化工大学 | Food safety online public opinion early warning system based on Storm distributed framework |
| CN106651030A (en) * | 2016-12-21 | 2017-05-10 | 重庆邮电大学 | Method for predicting user participation behavior of hot topic by improved RBF neural network |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107992478A (en) * | 2017-11-30 | 2018-05-04 | 百度在线网络技术（北京）有限公司 | The method and apparatus for determining focus incident |
| CN109408620A (en) * | 2018-10-11 | 2019-03-01 | 杭州安恒信息技术股份有限公司 | A kind of method, apparatus, equipment and the storage medium of network public opinion trend prediction |
| CN113590925A (en) * | 2020-04-30 | 2021-11-02 | 中国移动通信集团北京有限公司 | User determination method, device, equipment and computer storage medium |
| CN113626722A (en) * | 2020-05-08 | 2021-11-09 | 国家广播电视总局广播电视科学研究院 | Public opinion guiding method, device, equipment and computer readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wang et al. | A bibliometric analysis of climate change adaptation based on massive research literature data | |
| CN107391712A (en) | A kind of network public opinion trend prediction analysis method | |
| Dirksen et al. | The consistency of visual sewer inspection data | |
| KR101907041B1 (en) | Apparatus and method for managing risk based on prediction on social web media | |
| Han et al. | Intelligent decision model of road maintenance based on improved weight random forest algorithm | |
| Juhola et al. | The ability of Nordic countries to adapt to climate change: assessing adaptive capacity at the regional level | |
| Mclafferty | Disease cluster detection methods: recent developments and public health implications | |
| Martínez-Codina et al. | Pressure as a predictor of occurrence of pipe breaks in water distribution networks | |
| CN105224608A (en) | The hot news Forecasting Methodology analyzed based on microblog data and system | |
| Eng et al. | Predicting the likelihood of altered streamflows at ungauged rivers across the conterminous United States | |
| CN109635283B (en) | Public safety event pre-warning method based on mining citizen complaint text | |
| CN103399891A (en) | Method, device and system for automatic recommendation of network content | |
| Wang et al. | Evaluating the competitiveness of enterprise’s technology based on LDA topic model | |
| KR102020551B1 (en) | Method and Apparatus for Recommending Restaurant Based on Mobile Context Information | |
| Yang et al. | A web sentiment analysis method on fuzzy clustering for mobile social media users | |
| CN104346425A (en) | Method and system of hierarchical internet public sentiment indication system | |
| Zhou et al. | A joint-adaptive np control chart with multiple dependent state sampling scheme | |
| Tomal | Analysing the coupling coordination degree of socio-economic-infrastructural development and its obstacles: The case study of Polish rural municipalities | |
| Yan et al. | Ecological risk assessment from the viewpoint of surface water pollution in Xiamen City, China | |
| Won et al. | Early and real-time detection of seasonal influenza onset | |
| Kahraman et al. | Fuzzy process accuracy index to evaluate risk assessment of drought effects in Turkey | |
| Yakar | A multicriteria decision making–based methodology to identify accident-prone road sections | |
| Qin et al. | An enhanced even swaps method based on prospect theory with hesitant fuzzy linguistic information and its application to the selection of emergency logistics plans under the COVID-19 pandemic outbreak | |
| TW201640383A (en) | Internet events automatic collection and analysis method and system thereof | |
| Ji et al. | Microblog credibility indicators regarding misinformation of genetically modified food on Weibo |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171124 |