CN105224608A - The hot news Forecasting Methodology analyzed based on microblog data and system - Google Patents

The hot news Forecasting Methodology analyzed based on microblog data and system Download PDF

Info

Publication number
CN105224608A
CN105224608A CN201510562298.XA CN201510562298A CN105224608A CN 105224608 A CN105224608 A CN 105224608A CN 201510562298 A CN201510562298 A CN 201510562298A CN 105224608 A CN105224608 A CN 105224608A
Authority
CN
China
Prior art keywords
news
microblog
hot
topic
microblog topic
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
Application number
CN201510562298.XA
Other languages
Chinese (zh)
Other versions
CN105224608B (en
Inventor
陈健
韩超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
South China University of Technology SCUT
Original Assignee
South China University of Technology SCUT
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by South China University of Technology SCUT filed Critical South China University of Technology SCUT
Priority to CN201510562298.XA priority Critical patent/CN105224608B/en
Publication of CN105224608A publication Critical patent/CN105224608A/en
Application granted granted Critical
Publication of CN105224608B publication Critical patent/CN105224608B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G06F16/951—Indexing; Web crawling techniques

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 kind of hot news Forecasting Methodology based on microblog data analysis and system, described method comprises: the microblog users reaction information gathering news report from mainstream news website and cause at microblogging; Participle and word frequency statistics are carried out to microblogging text, calculates the TF-IDF value of word, and be converted to use vector space and describe a microblog topic; Microblog topic is classified, and statistics describes each quantizating index of microblog topic, calculate each temperature index of news; Adopt arithmetic of linearity regression to learn sample data, set up hot news forecast model, and whether the news after judging can become focus; Described system comprises data acquisition module, text analyzing processing module, data statistic analysis module and hot news prediction module.The present invention carries out multianalysis to the trend of the news of media report in microblog topic, and whether expected news and journals can become public sentiment hot, can solve hot news early prediction problem well.

Description

The hot news Forecasting Methodology analyzed based on microblog data and system
Technical field
The present invention relates to a kind of hot news Forecasting Methodology and system, especially a kind of hot news Forecasting Methodology based on microblog data analysis and system, belong to the hot news automatic Prediction field in government's public sentiment monitoring.
Background technology
Along with the fast development of Internet technology, network public-opinion more and more affects the stable development of society, and monitor network public sentiment is an important step of government's maintain social stability.Monitor one of them link as public sentiment, the prediction of hot news seems especially crucial.Microblogging changes the circulation way of traditional news media information with the propagation characteristic of its uniqueness and real-time interactive character.Especially microblogging and mobile terminal combination, enable micro-blog information be forwarded more fast or comment on, user comments a large amount of in microblog and exchange of information can quick collecting be viewpoint, thus form certain public opinion trend.The natural opening of microblogging, real-time, interactivity, magnanimity and the easy property examined, constitute the basis of hot news prediction.To judge the temperature of news in the topic amount of microblog by comprehensively analyzing news.
Traditional public sentiment hot topic is only by clicks, forward number, data such as comment number etc. judge, but this much-talked-about topic forecasting techniques can not the feature of multianalysis much-talked-about topic, cannot find the potential topic becoming focus.
Summary of the invention
The object of the invention is the defect in order to solve above-mentioned prior art, provide a kind of hot news Forecasting Methodology analyzed based on microblog data, the method carries out multianalysis to the trend of the news of media report in microblog topic, whether expected news and journals can become public sentiment hot, can solve hot news early prediction problem well.
Another object of the present invention is to provide a kind of hot news prognoses system analyzed based on microblog data.
Object of the present invention can reach by taking following technical scheme:
Based on the hot news Forecasting Methodology that microblog data is analyzed, said method comprising the steps of:
S1, the microblog users reaction information of it is reported from the collection of mainstream news website and cause at microblogging;
S2, participle and word frequency statistics are carried out to microblogging text, calculate the TF-IDF value of word, and be converted to use vector space and describe a microblog topic;
S3, microblog topic to be classified, and statistics describes each quantizating index of microblog topic, calculate each temperature index of news;
S4, employing arithmetic of linearity regression learn sample data, set up hot news forecast model, and whether can become focus according to the news after hot news forecast model judges.
As a kind of embodiment, in step S3, described microblog topic to be classified, specifically comprises:
1) add up social hotspots, calculate the attention rate of each social hotspots;
2) according to social hotspots, microblog topic is classified, calculate the degree of social concern of microblog topic.
As a kind of embodiment, in step S3, described statistics describes each quantizating index of microblog topic, be specially: three characteristic dimension extracting description microblog topic, as quantizating index, are respectively the propagation dynamics of public's response force of microblog topic, the core response force of microblog topic and microblog topic.
As a kind of embodiment, in step S3, each temperature index of described calculating news, be specially: the quantizating index according to describing microblog topic carries out multianalysis from multiple angle to the temperature of news, and three temperature indexs of news are respectively news attention rate, news influence and dissemination of news degree.
As a kind of embodiment, in step S4, described employing arithmetic of linearity regression learns sample data, sets up hot news forecast model, specifically comprises:
1) variables choice: select news temperature as dependent variable, three temperature indexs of news, as independent variable, have existing between each temperature index and news hot value and obeying linear relationship of news according to definition;
2) model specification: according to studied hot news forecasting problem, setting multiple linear regression model;
3) parameter estimation: use sample data learning procedure 2) parameter of multiple linear regression model that sets, set up hot news forecast model;
4) model testing: after hot news forecast model is set up, adopts F inspection and R to check and tests to the degree of fitting of model, conspicuousness respectively;
5) model use: the hot news forecast model of foundation is applied to prediction hot news.
As a kind of embodiment, described multiple linear regression model, as shown in the formula:
Wherein, R represents news temperature, N foc, N infand N transrepresent three temperature indexs of news, θ 1, θ 2, θ 3be the unknown parameter irrelevant with three of news temperature indexs respectively, ∈ is the random disturbance item of overall regression function.
Another object of the present invention can reach by taking following technical scheme:
Based on the hot news prognoses system that microblog data is analyzed, described system comprises,
Data acquisition module, for the microblog users reaction information of it is reported from main stream website collection and cause at microblogging;
Text analyzing processing module, for carrying out participle and word frequency statistics to microblogging text, calculates the TF-IDF value of word, and is converted to use vector space and describes a microblog topic;
Data statistic analysis module, for classifying to microblog topic, and statistics describes each quantizating index of microblog topic, calculates each temperature index of news;
Hot news prediction module, for using arithmetic of linearity regression to learn sample data, sets up hot news forecast model, and whether can become focus according to the news after hot news forecast model judges.
The present invention has following beneficial effect relative to prior art:
1, the present invention carries out multianalysis to the trend of the news of media report in microblog topic, and whether expected news and journals can become public sentiment hot, can solve hot news early prediction problem well.
2, the description of the present invention to microblog topic defines multiple (being preferably three) quantizating index, and according to describing the quantizating index of microblog topic, define the temperature index of multiple (being preferably three) news, and devise a kind of adaptive algorithm, arithmetic of linearity regression, predicts its Successful utilization in hot news.
3, the present invention is the practicality strengthening algorithm, and design achieves the hot news prognoses system analyzed based on microblog data, the algorithm of proposition is applied to actual public sentiment hot and finds.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the hot news Forecasting Methodology based on microblog data analysis of the embodiment of the present invention 1.
Fig. 2 describes the quantizating index of microblog topic, graph of a relation between the temperature index of news and news temperature in the embodiment of the present invention 1.
Fig. 3 is the structured flowchart of the hot news prognoses system based on microblog data analysis of the embodiment of the present invention 2.
Embodiment
Below in conjunction with embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention are not limited thereto.
Embodiment 1:
As depicted in figs. 1 and 2, the hot news Forecasting Methodology analyzed based on microblog data of the present embodiment, comprises the following steps:
S1, the microblog users reaction information of it is reported from the collection of mainstream news website and cause at microblogging, described news report comprises title and text, described microblog users reaction information is at the result set that microblogging is searched for using headline as keyword, described microblogging result set comprises microblog users information, microblogging text, time of origin, but does not comprise the news report of news media in microblogging;
S2, participle and word frequency statistics are carried out to microblogging text, calculate TF-IDF (termfrequency-inversedocumentfrequency) value of word, and be converted to and use vector space to describe a microblog topic;
S3, microblog topic to be classified, and describe three quantizating index of microblog topic, calculate three temperature indexs of news;
Described microblog topic to be classified, specifically comprises:
1) adding up social hotspots (by manually adding up), calculating the attention rate of each social hotspots;
2) according to social hotspots, microblog topic is classified, and calculate the degree of social concern F of microblog topic.
Described statistics describes three quantizating index of microblog topic, be extraction and describe three characteristic dimension of microblog topic as quantizating index, be respectively public's response force of microblog topic, the core response force of microblog topic, the propagation dynamics of microblog topic, three quantizating index specific explanations are as follows:
Public's response force of a, microblog topic, refer to the responsiveness causing microblogging domestic consumer after microblog topic occurs at short notice, weigh about the microblogging total amount of the domestic consumer of this topic in the short time after microblog topic can be used to occur, it is expressed as follows formula:
I p＝(N P-P min)/P ave
Wherein, N pthe microblogging total amount about the domestic consumer of this topic in the short time after topic occurs, P min, P avethe short time interior minimum microblogging amount about the domestic consumer of this topic and average microblogging amount after the much-talked-about topic generation of statistics in advance respectively;
The core response force of b, microblog topic, refer to that the responsiveness of microblogging authenticated occurs to cause in the rear short time microblog topic, weigh about the microblogging total amount of the authenticated of this topic in the short time after microblog topic can be used to occur, it is expressed as follows formula:
I v＝(N V-V min)/V ave
Wherein, N vthe microblogging total amount about the microblogging authenticated of this topic in the short time after topic occurs, V min, V avethe short time interior minimum microblogging amount about the authenticated of this topic and average microblogging amount after the much-talked-about topic generation of statistics in advance respectively;
The propagation dynamics of c, microblog topic, refer to the distribution situation paying close attention to the microblog users location of this topic after microblog topic occurs, automatically northeast, North China, Central China, south China, western five areas are divided into according to economic development level and the population characteristic whole nation, calculate each area accounts for national microblog users microblogging amount proportion about the microblogging amount of this topic, then introduce the propagation dynamics that Gini index portrays microblog topic, it is expressed as follows formula:
G = 1 - ( D E N 2 + D N 2 + D C 2 + D S 2 + D W 2 )
Wherein, D eN, D n, D c, D sand D wbe northeast after topic occurs respectively, North China, Central China, south China and western five areas account for the proportion of national microblogging total amount about the microblogging amount of this topic;
Each temperature index of described calculating news, the quantizating index be according to describing microblog topic carries out multianalysis from multiple angle to the temperature of news, three temperature indexs of news are respectively news attention rate, news influence, dissemination of news dynamics, and three temperature index specific explanations of news are as follows:
A, news attention rate, refer to that whether news be the focus of current public attention, and use the degree of social concern of microblog topic to weigh, it is expressed as follows formula:
N f o c = F + I v × l o g I p I v
Wherein, F is the degree of social concern of microblog topic, I p, I vpublic's response force and the core response force of microblog topic respectively, N foclarger explanation more easily receives the concern of the public, and the possibility becoming hot news is larger;
B, news influence, refer to that news can the ability of long lasting effect social concerns, use the potential incremental of public's response force of microblog topic to represent, it is expressed as follows formula:
N inf = I p + α × I v β
Wherein, I p, I vbe public's response force and the core response force of microblog topic respectively, α be the affecting parameters of microblog topic core response force, β be the Key Influence of microblog topic to the affecting parameters of public's influence power, N inflarger explanation topic can the concern of the long lasting effect public, and the possibility becoming hot news is larger;
C, dissemination of news degree, refer to news each department formed public opinion be evenly distributed situation, use microblog topic propagation dynamics weigh, it is expressed as follows formula:
N trans＝G
Wherein, G is the propagation dynamics of microblog topic, N translarger explanation news forms public opinion center distribution in each department is more even, and the possibility becoming hot news is larger;
S4, employing arithmetic of linearity regression learn sample data, set up hot news forecast model, and whether can become focus according to the news after hot news forecast model judges.
Described employing arithmetic of linearity regression learns sample data, and namely the hot value of news is as dependent variable, and three temperature indexs of news, as independent variable, are set up multiple linear regression model, specifically comprised:
1) variables choice, selects the hot value R of news as dependent variable, and three temperature indexs of news, as independent variable, have according to definition and to exist between the temperature index of each news and the hot value of news and to obey linear relationship;
2) model specification, according to studied hot news forecasting problem, setting multiple linear regression model:
Wherein, R represents news temperature, N foc, N infand N transrepresent three temperature indexs of news, θ 1, θ 2, θ 3be the unknown parameter irrelevant with three of news temperature indexs respectively, ∈ is the random disturbance item of overall regression function;
3) parameter estimation, uses sample data learning procedure 2) parameter of multiple linear regression model that sets, set up hot news forecast model;
4) model testing, after hot news forecast model is set up, adopts F inspection and R to check and tests to the degree of fitting of model, conspicuousness respectively;
5) model use, is applied to prediction hot news by the hot news forecast model of foundation.
Embodiment 2:
As shown in Figure 3, the hot news prognoses system analyzed based on microblog data of the present embodiment, described system comprises:
Data acquisition module, for the microblog users reaction information of it is reported from main stream website collection and cause at microblogging;
Text analyzing processing module, for carrying out participle and word frequency statistics to microblogging text, calculates the TF-IDF value of word, and is converted to use vector space and describes a microblog topic;
Data statistic analysis module, for classifying to microblog topic, and statistics describes each quantizating index of microblog topic, calculates each temperature index of news;
Hot news prediction module, for using arithmetic of linearity regression to learn sample data, sets up hot news forecast model, and whether can become focus according to the news after hot news forecast model judges.
Above-mentioned data statistic analysis module and hot news prediction module specific implementation process are with embodiment 1.
In sum, the present invention carries out multianalysis to the trend of the news of media report in microblog topic, and whether expected news and journals becomes public sentiment hot, can solve hot news early prediction problem well.
The above; be only patent preferred embodiment of the present invention; but the protection domain of patent of the present invention is not limited thereto; anyly be familiar with those skilled in the art in the scope disclosed in patent of the present invention; be equal to according to the technical scheme of patent of the present invention and patent of invention design thereof and replaced or change, all belonged to the protection domain of patent of the present invention.

Claims (7)

1., based on the hot news Forecasting Methodology that microblog data is analyzed, it is characterized in that: said method comprising the steps of:
S1, the microblog users reaction information of it is reported from the collection of mainstream news website and cause at microblogging;
S2, participle and word frequency statistics are carried out to microblogging text, calculate the TF-IDF value of word, and be converted to use vector space and describe a microblog topic;
S3, microblog topic to be classified, and statistics describes each quantizating index of microblog topic, calculate each temperature index of news;
S4, employing arithmetic of linearity regression learn sample data, set up hot news forecast model, and whether can become focus according to the news after hot news forecast model judges.
2. the hot news Forecasting Methodology analyzed based on microblog data according to claim 1, is characterized in that: in step S3, describedly to classify to microblog topic, specifically comprise:
1) add up social hotspots, calculate the attention rate of each social hotspots;
2) according to social hotspots, microblog topic is classified, calculate the degree of social concern of microblog topic.
3. the hot news Forecasting Methodology analyzed based on microblog data according to claim 1, it is characterized in that: in step S3, described statistics describes each quantizating index of microblog topic, be specially: three characteristic dimension extracting description microblog topic, as quantizating index, are respectively the propagation dynamics of public's response force of microblog topic, the core response force of microblog topic and microblog topic.
4. the hot news Forecasting Methodology analyzed based on microblog data according to claim 3, it is characterized in that: in step S3, each temperature index of described calculating news, be specially: the quantizating index according to describing microblog topic carries out multianalysis from multiple angle to the temperature of news, and three temperature indexs of news are respectively news attention rate, news influence and dissemination of news degree.
5. according to claim 4 based on microblog data analyze hot news Forecasting Methodology, it is characterized in that: in step S4, described employing arithmetic of linearity regression learns sample data, sets up hot news forecast model, specifically comprises:
1) variables choice: select news temperature as dependent variable, three temperature indexs of news, as independent variable, have existing between each temperature index and news hot value and obeying linear relationship of news according to definition;
2) model specification: according to studied hot news forecasting problem, setting multiple linear regression model;
3) parameter estimation: use sample data learning procedure 2) parameter of multiple linear regression model that sets, set up hot news forecast model;
4) model testing: after hot news forecast model is set up, adopts F inspection and R to check and tests to the degree of fitting of model, conspicuousness respectively;
5) model use: the hot news forecast model of foundation is applied to prediction hot news.
6. according to claim 5 based on microblog data analyze hot news Forecasting Methodology, it is characterized in that: described multiple linear regression model, as shown in the formula:
Wherein, R represents news temperature, N foc, N infand N transrepresent three temperature indexs of news, θ 1, θ 2, θ 3be the unknown parameter irrelevant with three of news temperature indexs respectively, ε is the random disturbance item of overall regression function.
7., based on the hot news prognoses system that microblog data is analyzed, it is characterized in that: described system comprises,
Data acquisition module, for the microblog users reaction information of it is reported from main stream website collection and cause at microblogging;
Text analyzing processing module, for carrying out participle and word frequency statistics to microblogging text, calculates the TF-IDF value of word, and is converted to use vector space and describes a microblog topic;
Data statistic analysis module, for classifying to microblog topic, and statistics describes each quantizating index of microblog topic, calculates each temperature index of news;
Hot news prediction module, for using arithmetic of linearity regression to learn sample data, sets up hot news forecast model, and whether can become focus according to the news after hot news forecast model judges.
CN201510562298.XA 2015-09-06 2015-09-06 Hot news prediction technique and system based on microblog data analysis Active CN105224608B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201510562298.XA CN105224608B (en) 2015-09-06 2015-09-06 Hot news prediction technique and system based on microblog data analysis

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201510562298.XA CN105224608B (en) 2015-09-06 2015-09-06 Hot news prediction technique and system based on microblog data analysis

Publications (2)

Publication Number Publication Date
CN105224608A true CN105224608A (en) 2016-01-06
CN105224608B CN105224608B (en) 2019-04-09

Family

ID=54993576

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201510562298.XA Active CN105224608B (en) 2015-09-06 2015-09-06 Hot news prediction technique and system based on microblog data analysis

Country Status (1)

Country Link
CN (1) CN105224608B (en)

Cited By (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105809554A (en) * 2016-02-07 2016-07-27 重庆邮电大学 Prediction method of hot topics participated by users in social networks
CN105824806A (en) * 2016-06-13 2016-08-03 腾讯科技（深圳）有限公司 Quality evaluation method and device for public accounts
CN106097111A (en) * 2016-06-20 2016-11-09 重庆房慧科技有限公司 A kind of public opinion prediction method based on the big data of intelligence community network
CN107066537A (en) * 2017-03-06 2017-08-18 广州神马移动信息科技有限公司 Hot news generation method, equipment, electronic equipment
CN107203632A (en) * 2017-06-01 2017-09-26 中国人民解放军国防科学技术大学 Topic Popularity prediction method based on similarity relation and cooccurrence relation
CN107391712A (en) * 2017-07-28 2017-11-24 王亚迪 A kind of network public opinion trend prediction analysis method
CN107506870A (en) * 2017-09-06 2017-12-22 国家电网公司 A kind of electric service hotspot prediction method based on hot word
CN107704477A (en) * 2016-08-08 2018-02-16 中华电信股份有限公司 Multimedia content classification system and method
CN107783948A (en) * 2017-10-10 2018-03-09 湖北文理学院 A kind of vocabulary social network analysis method based on social networks principle
CN107870957A (en) * 2016-09-28 2018-04-03 郑州大学 A kind of popular microblogging Forecasting Methodology based on information gain and BP neural network
CN108038790A (en) * 2017-11-24 2018-05-15 东华大学 A kind of Study on Trend system of inside and outside data fusion
CN108205589A (en) * 2017-12-29 2018-06-26 成都优易数据有限公司 A kind of temperature iterative calculation method
CN109214562A (en) * 2018-08-24 2019-01-15 国网山东省电力公司电力科学研究院 A kind of power grid scientific research hotspot prediction and method for pushing based on RNN
CN109446329A (en) * 2018-11-08 2019-03-08 大连瀚闻资讯有限公司 A kind of hot spot recognition methods of the analysis of public opinion
CN109977393A (en) * 2017-12-28 2019-07-05 中国科学院计算技术研究所 A kind of popular news prediction technique and system based on content controversial
CN110598151A (en) * 2019-09-09 2019-12-20 河南牧业经济学院 Method and system for judging news spreading effect
CN110674447A (en) * 2019-09-26 2020-01-10 上海烨睿信息科技有限公司 Information importance judging method, device, computer terminal and storage medium
CN112417253A (en) * 2020-12-28 2021-02-26 时间知道(北京)文化科技有限公司 Multi-dimensional public opinion monitoring system and method
CN114880588A (en) * 2022-06-13 2022-08-09 四川封面传媒科技有限责任公司 News popularity prediction method based on knowledge graph

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103116605A (en) * 2013-01-17 2013-05-22 上海交通大学 Method and system of microblog hot events real-time detection based on detection subnet
CN103345524A (en) * 2013-07-19 2013-10-09 中国地质大学（武汉） Method and system for detecting microblog hot topics
CN103745000A (en) * 2014-01-24 2014-04-23 福州大学 Hot topic detection method of Chinese micro-blogs

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103116605A (en) * 2013-01-17 2013-05-22 上海交通大学 Method and system of microblog hot events real-time detection based on detection subnet
CN103345524A (en) * 2013-07-19 2013-10-09 中国地质大学（武汉） Method and system for detecting microblog hot topics
CN103745000A (en) * 2014-01-24 2014-04-23 福州大学 Hot topic detection method of Chinese micro-blogs

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
KAI CHEN ETC,: ""Cost-effective node monitoring for online hot event detection in sina weibo microblogging"", 《INTERNATIONAL CONFERENCE ON WORLD WIDE WEB COMPANION》 *
姚海波: ""一种微博热点话题检测与趋势预测"", 《中国优秀硕士学位论文全文数据库》 *

Cited By (27)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105809554A (en) * 2016-02-07 2016-07-27 重庆邮电大学 Prediction method of hot topics participated by users in social networks
CN105809554B (en) * 2016-02-07 2020-03-17 重庆邮电大学 Prediction method for user participating in hot topics in social network
CN105824806B (en) * 2016-06-13 2018-10-23 腾讯科技（深圳）有限公司 A kind of quality evaluating method and device of public's account
CN105824806A (en) * 2016-06-13 2016-08-03 腾讯科技（深圳）有限公司 Quality evaluation method and device for public accounts
CN106097111A (en) * 2016-06-20 2016-11-09 重庆房慧科技有限公司 A kind of public opinion prediction method based on the big data of intelligence community network
CN107704477B (en) * 2016-08-08 2020-09-22 中华电信股份有限公司 Multimedia content classification system and method
CN107704477A (en) * 2016-08-08 2018-02-16 中华电信股份有限公司 Multimedia content classification system and method
CN107870957A (en) * 2016-09-28 2018-04-03 郑州大学 A kind of popular microblogging Forecasting Methodology based on information gain and BP neural network
CN107066537A (en) * 2017-03-06 2017-08-18 广州神马移动信息科技有限公司 Hot news generation method, equipment, electronic equipment
CN107203632A (en) * 2017-06-01 2017-09-26 中国人民解放军国防科学技术大学 Topic Popularity prediction method based on similarity relation and cooccurrence relation
CN107391712A (en) * 2017-07-28 2017-11-24 王亚迪 A kind of network public opinion trend prediction analysis method
CN107506870A (en) * 2017-09-06 2017-12-22 国家电网公司 A kind of electric service hotspot prediction method based on hot word
CN107783948A (en) * 2017-10-10 2018-03-09 湖北文理学院 A kind of vocabulary social network analysis method based on social networks principle
CN107783948B (en) * 2017-10-10 2020-10-13 湖北文理学院 Vocabulary social network analysis method based on social network principle
CN108038790A (en) * 2017-11-24 2018-05-15 东华大学 A kind of Study on Trend system of inside and outside data fusion
CN108038790B (en) * 2017-11-24 2021-10-15 东华大学 Situation analysis system with internal and external data fusion
CN109977393A (en) * 2017-12-28 2019-07-05 中国科学院计算技术研究所 A kind of popular news prediction technique and system based on content controversial
CN108205589A (en) * 2017-12-29 2018-06-26 成都优易数据有限公司 A kind of temperature iterative calculation method
CN108205589B (en) * 2017-12-29 2022-02-15 成都优易数据有限公司 Heat iterative calculation method
CN109214562A (en) * 2018-08-24 2019-01-15 国网山东省电力公司电力科学研究院 A kind of power grid scientific research hotspot prediction and method for pushing based on RNN
CN109446329A (en) * 2018-11-08 2019-03-08 大连瀚闻资讯有限公司 A kind of hot spot recognition methods of the analysis of public opinion
CN110598151A (en) * 2019-09-09 2019-12-20 河南牧业经济学院 Method and system for judging news spreading effect
CN110674447A (en) * 2019-09-26 2020-01-10 上海烨睿信息科技有限公司 Information importance judging method, device, computer terminal and storage medium
CN112417253B (en) * 2020-12-28 2021-10-15 时间知道(北京)文化科技有限公司 Multi-dimensional public opinion monitoring system and method
CN112417253A (en) * 2020-12-28 2021-02-26 时间知道(北京)文化科技有限公司 Multi-dimensional public opinion monitoring system and method
CN114880588A (en) * 2022-06-13 2022-08-09 四川封面传媒科技有限责任公司 News popularity prediction method based on knowledge graph
CN114880588B (en) * 2022-06-13 2024-04-26 四川封面传媒科技有限责任公司 News heat prediction method based on knowledge graph

Also Published As

Publication number Publication date
CN105224608B (en) 2019-04-09

Similar Documents

Publication Publication Date Title
CN105224608A (en) The hot news Forecasting Methodology analyzed based on microblog data and system
Lee et al. Rapid intensification and the bimodal distribution of tropical cyclone intensity
CN103458042B (en) A kind of microblog advertisement user detection method
JP5615857B2 (en) Analysis apparatus, analysis method, and analysis program
CN104657425A (en) Topic management type network public opinion evaluation management system and method
CN104933622A (en) Microblog popularity degree prediction method based on user and microblog theme and microblog popularity degree prediction system based on user and microblog theme
CN111538888A (en) Network public opinion intensity evolution analysis system based on active monitoring engine and big data
CN103399891A (en) Method, device and system for automatic recommendation of network content
CN104408157A (en) Funnel type data gathering, analyzing and pushing system and method for online public opinion
CN103336766A (en) Short text garbage identification and modeling method and device
Guo [Retracted] Financial Development and Carbon Emissions: Analyzing the Role of Financial Risk, Renewable Energy Electricity, and Human Capital for China
CN108021651A (en) Network public opinion risk assessment method and device
Fotuhi et al. Phase I monitoring of social networks based on Poisson regression profiles
CN105550275A (en) Microblog forwarding quantity prediction method
Bodnar et al. Using large-scale social media networks as a scalable sensing system for modeling real-time energy utilization patterns
CN104933475A (en) Network forwarding behavior prediction method and apparatus
Raza et al. EWMA and DEWMA control charts for Poisson‐Exponential distribution: conditional median approach for censored data
Yu et al. Rumor identification with maximum entropy in micronet
Fawzy et al. Data fusion for data prediction: an iot-based data prediction approach for smart cities
Pan et al. A novel probabilistic modeling framework for wind speed with highlight of extremes under data discrepancy and uncertainty
Yu et al. Research on situational perception of power grid business based on user portrait
Dan et al. Study of bot detection on Sina-Weibo based on machine learning
CN106156232A (en) A kind of monitoring method and apparatus of spreading network information
CN108038790B (en) Situation analysis system with internal and external data fusion
CN110782332A (en) Intelligent credit assessment dynamic tracing 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
GR01 Patent grant
GR01 Patent grant