CN104915397A - Method and device for predicting microblog propagation tendencies - Google Patents
Method and device for predicting microblog propagation tendencies Download PDFInfo
- Publication number
- CN104915397A CN104915397A CN201510284821.7A CN201510284821A CN104915397A CN 104915397 A CN104915397 A CN 104915397A CN 201510284821 A CN201510284821 A CN 201510284821A CN 104915397 A CN104915397 A CN 104915397A
- Authority
- CN
- China
- Prior art keywords
- communication process
- predicted
- microblogging
- feature
- training data
- 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
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Abstract
The invention provides a method and a device for predicting microblog propagation tendencies, and the method and the device are used for solving the problem that a method for predicting the microblog propagation tendencies in the prior art is lower in accuracy. The method comprises the following steps of acquiring essential attribute characters and propagation process characters of to-be-predicted microblogs; calculating similarities between the essential attribute characters and the propagation process characters of the to-be-predicted microblogs and essential attribute characters and propagation process characters of training data, and classifying data of the to-be-predicted microblogs to obtain propagation process categories that the to-be-predicted microblogs belong to, wherein the propagation process categories are obtained by the similarity cluster of the propagation process characters of the training data; selecting corresponding regression models for the classified to-be-predicted microblogs; predicting the propagation tendencies of the to-be-predicted microblogs, wherein the regression models are regression models established in advance according to the various training data. According to the scheme, the accuracy of predicting the microblog propagation tendencies is enhanced.
Description
Technical field
The present invention relates to communication technical field, particularly relate to a kind of microblogging and propagate trend forecasting method and device.
Background technology
At present, along with traditional society's economic activity is to socialization, networking future development, take social media as carrier, to happen suddenly, focus incident is focus Social Public Feelings becomes focal point.Relating in national security, social stability, the burst of the social people's livelihood, the fermentation of sensitive event and communication process, microblogging all serves important promotion even guidance quality effect.Popularity prediction is the important means of maintaining network public sentiment safety, makes predicting fast and accurately Twitter message popularity and microblogging communication mode, can find the microblogging that may cause large-scale outbreak early, takes precautions against harmful information diffusion ahead of time and propagates.
Social networks is the complication system of various dimensions, influences each other and interact frequently between node.In social networks, Information Communication and user group's behavior generally all have accumulate gradually, mixed culture fermentation is to the feature of instantaneous burst, and such process is not linear, the simple superposition of not single factor effect forms, a series of slight change on many factors often, when combined action makes whole system reach certain critical conditions, occur emerging in large numbers phenomenon, the outburst of microblogging is that social network information emerges in large numbers a kind of form of expression of phenomenon in content aspect.
Microblogging under this system features background is propagated trend forecasting method and is usually carried out in microblogging forwarding feature mining and message propagation tendency modelling two.Based on the event popularity Forecasting Methodology (application number: 201410334425.6) propose and a kind ofly carry out event Popularity prediction to the method that Poisson process modeling is carried out in the forwarding behavior of key user on microblogging propagation chain of poisson process model in social networks.But, the method needs to forward chain to the microblogging regained one's integrity by forwarding relation, in actual applications, crawl the multiple difficulties such as longer when complete forwarding chain has faced and social networks shielding, restriction, in addition, the method also needs the identification each user being carried out to key user and non-key user, and time complexity is high, and the accuracy of modeling process too relies on the accuracy of key user's method of discrimination, make its accuracy lower.Microblogging transfer amount forecast model generation method and microblogging transfer amount Forecasting Methodology (application number: first the method 201410157342.4) proposed carries out classification to microblogging transfer amount, then the essential characteristic of every bar microblogging is extracted, set up the many disaggregated models between essential characteristic and transfer amount classification, and then according to each transfer amount classification, set up the regression model between essential characteristic and microblogging transfer amount, many disaggregated models of training and regression model is finally utilized to carry out the transfer amount of microblogging to be predicted, the method does not consider the dynamic trend of communication process, a lot of starting condition microblogging similar with content causes final transfer amount to there is greatest differences due to the difference of the factors such as communication process participant, microblogging essential characteristic is only relied on to carry out forecasting accuracy to the final transfer amount of microblogging lower.
Summary of the invention
The invention provides a kind of microblogging and propagate trend forecasting method and device, for solving problem lower to the method accuracy of microblogging propagation trend prediction in prior art.
According to an aspect of the present invention, provide a kind of microblogging and propagate trend forecasting method, comprising: the base attribute feature and the communication process feature that obtain microblogging to be predicted; Calculate the base attribute feature of microblogging to be predicted and training data, the similarity of communication process feature, microblogging to be predicted is classified according to communication process classification according to the similarity calculated, obtain the communication process classification belonging to microblogging to be predicted, communication process classification is obtained by the communication process characteristic similarity cluster of training data; Communication process classification according to microblogging to be predicted selects corresponding regression model, and regression model is in advance according to the regression model that training data is set up; The propagation trend of regression model to microblogging to be predicted according to selecting is predicted.
Wherein, above-mentioned communication process feature comprises: the forwarding data feature in the content characteristic in the communication process of microblog data, the communication process of microblog data and the user characteristics in microblog data communication process.
Further, said method also comprises:
Before the base attribute feature obtaining microblogging to be predicted and communication process feature, set up the content characteristic in the propagation of training data, forwarding data feature and the essential characteristic of user characteristics and training data and the linear regression model (LRM) of communication process feature respectively according to the communication process classification of training data.
Wherein, the propagation trend of regression model to microblogging to be predicted according to selecting is predicted, comprising:
Predict according to the spread scope of regression model to the number of the content keyword of microblogging to be predicted, the transfer amount of microblogging to be predicted and microblogging to be predicted selected successively.
Wherein, above-mentioned base attribute feature, comprising: the attribute of the user that posts and the attribute of content of microblog.
According to another aspect of the present invention, providing a kind of microblogging and propagate trend prediction device, comprising: acquisition module, for obtaining base attribute feature and the communication process feature of microblogging to be predicted; Sort module, for calculating the base attribute feature of microblogging to be predicted and training data, the similarity of communication process feature, microblogging to be predicted is classified according to instruction communication process classification according to the similarity calculated, obtain the communication process classification belonging to microblogging to be predicted, communication process classification is obtained by the communication process characteristic similarity cluster of training data; Selection module, selects corresponding regression model for the communication process classification according to microblogging to be predicted, and it is in advance according to the regression model that training data is set up that training returns; Prediction module, for predicting according to the propagation trend of regression model to microblogging to be predicted selected.
Wherein, above-mentioned communication process feature comprises: the forwarding data feature in the content characteristic in the communication process of microblog data, the communication process of microblog data and the user characteristics in microblog data communication process.
Further, said apparatus also comprises: set up module, for before the base attribute feature obtaining microblogging to be predicted and communication process feature, set up the content characteristic in the propagation of training data, forwarding data feature and the essential characteristic of user characteristics and training data and the linear regression model (LRM) of communication process feature respectively according to the communication process classification of training data.
Wherein, above-mentioned prediction module is used for: predict according to the spread scope of regression model to the number of the content keyword of microblogging to be predicted, the transfer amount of microblogging to be predicted and microblogging to be predicted selected successively.
Wherein, above-mentioned base attribute feature, comprising: the attribute of the user that posts and the attribute of content of microblog.
The scheme that the embodiment of the present invention provides, has taken into full account the dynamic factor of microblogging communication process, predicts that microblogging propagates trend based on the multiple communication process feature in microblogging communication process, improves the accuracy that microblogging propagates trend prediction.
Accompanying drawing explanation
In order to be illustrated more clearly in the embodiment of the present invention or technical scheme of the prior art, be briefly described to the accompanying drawing used required in embodiment or description of the prior art below, apparently, accompanying drawing in the following describes is only some embodiments of the present invention, for those of ordinary skill in the art, under the prerequisite not paying creative work, other accompanying drawing can also be obtained according to these accompanying drawings.
Fig. 1 is the process flow diagram of the microblogging propagation trend forecasting method that the embodiment of the present invention 1 provides;
The process flow diagram setting up regression model that Fig. 2 provides for the embodiment of the present invention 2;
Fig. 3 is the process flow diagram of the propagation trend prediction of the microblogging to be predicted that the embodiment of the present invention 2 provides;
The structured flowchart of Fig. 4 to be the present invention be microblogging that embodiment 3 provides propagates trend prediction device.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, be clearly and completely described the technical scheme in the embodiment of the present invention, obviously, described embodiment is only the present invention's part embodiment, instead of whole embodiments.Based on the embodiment in the present invention, the every other embodiment that those of ordinary skill in the art obtain under the prerequisite of not making creative work, all belongs to the scope of protection of the invention.
Embodiment 1
Present embodiments provide a kind of microblogging and propagate trend forecasting method, as shown in Figure 1, the method comprises the steps:
Step 101: obtain the base attribute feature of microblogging to be predicted and each communication process feature;
Wherein, above-mentioned base attribute feature, comprise: the attribute of the user that posts and the attribute of content of microblog, user property of posting comprises whether user adds V, user's bean vermicelli number, user post number, content of microblog attribute comprise whether containing URL (Uniform Resource Locator, URL(uniform resource locator)), whether containing picture, whether containing video, contained keyword number and ratio and contained emotion word number and ratio.
Wherein, the communication process feature of microblogging comprises: the forwarding data feature in the content characteristic in the communication process of microblog data, the communication process of microblog data and the user characteristics in microblog data communication process.
Wherein, content characteristic comprises following information:
Content keyword: participle, statistics word frequency are carried out to content of microblog, calculates keyword feature vector;
Content substance word: extract the entity word in content keyword, forms entity word proper vector;
Entity Connection Density: according to knowing the external knowledge storehouses such as net, Connection Density between computational entity word, computing method are, first the entity word figure that word is summit, cooccurrence relation is even limit is formed, co-occurrence once then connects limit weight and adds 1, and Connection Density is the ratio of company's limit quantity between entity word and full-mesh Tu Lianbian quantity; This index shows the mutual relationship tightness degree of the inter-entity that content of microblog relates to, and more closely represent and more more appear at together future, the probability deriving new topic is larger, and the probability that microblogging obtains more forwardings is also larger;
Content keyword rate of change: remove rubbish and reply (as promoted link and advertisement link) and reply (as " laughing a great ho-ho " and emoticon) without notional word, get front 100 replies of microblogging, content is joined content of microblog Computed-torque control keyword feature vector, calculate the increment comparing the i-th-1 day content of microblog for i-th day;
Content substance word rate of change: the computing method of content substance word rate of change, extracts the entity word in the content keyword of every day, forms entity word proper vector, calculates the increment comparing entity contained by the i-th-1 day content of microblog for i-th day;
Quantative attribute:
Day transfer amount: terminate from the time of posting to observation, the hop count of every day;
Transfer amount growth rate: calculate the increment comparing the i-th-1 day transfer amount for i-th day; Show that microblogging continues to be concerned degree, speedup is larger, shows that transfer amount increases faster;
Saturation degree: saturation degree summation is 1, calculating degree of reaching capacity respectively is the time of 10% to 100%, with 10% for step-length;
User characteristics:
To post user's bean vermicelli number: calculate the increment comparing user's bean vermicelli sum of posting for the i-th-1 day for i-th day, increase faster, show have V user to add microblogging repeating process, microblogging more likely obtains more exposure, also more likely obtains more hop count;
To post customer relationship network Connection Density: first formed to post user for summit, pay close attention to is the concern relational network connecting limit, calculate the Connection Density of the user that posts, Connection Density is higher shows that between microblogging participant, relation is tightr, be shown to be one and ardent inner circle of people is discussed, or be that waterborne troops forwards mutually to improve forward rate.
Step 102: calculate the base attribute feature of microblogging to be predicted and training data, the similarity of communication process feature, according to the communication process classification of the similarity calculated according to training data, microblogging to be predicted is classified, obtain the communication process classification belonging to microblogging to be predicted;
Wherein, the communication process classification of training data is obtained by the communication process characteristic similarity cluster of training data;
Step 103: the communication process classification according to microblogging to be predicted selects corresponding regression model;
Wherein, training returns is in advance according to the regression model that training data is set up;
Step 104: the propagation trend of regression model to microblogging to be predicted according to selecting is predicted.
In this step 104: the propagation trend corresponding according to all kinds of microblog data of regression model to microblogging to be predicted selected is predicted, specifically can comprise: predict according to the spread scope of regression model to the number of the content keyword of microblogging to be predicted, the transfer amount of microblogging to be predicted and microblogging to be predicted selected successively.
Before above-mentioned steps 101, also need to set up regression model according to the microblogging of known forwarding Trend value, also comprise based on this said method:
Before the base attribute feature obtaining microblogging to be predicted and communication process feature, obtain base attribute feature and the communication process feature of known microblogging (i.e. training data); According to the base attribute feature of known microblogging and each propagation characteristic, cluster is carried out to the data of known microblogging, obtain the communication process classification of known microblogging; The content characteristic of microblog data, the forwarding data feature of microblog data and the essential characteristic of microblog data and known microblogging and the linear regression model (LRM) of communication process feature is set up respectively according to the communication process classification of known microblogging.
The microblogging that the present embodiment provides propagates trend forecasting method, by the microblogging with similar propagation process feature is gathered into a message bunch, then modeling is carried out to the communication process of message bunch, when avoiding the communication process modeling to single message, micro-blog information amount is low, the problems such as the over-fitting that model is easily subject to abnormity point interference and brings, forecasting accuracy is improved while raising counting yield, and to microblogging communication process trend with propagate reason and have good explanatory.Simultaneously, for existing method longer, computation complexity is high, accuracy is low problem consuming time, the microblogging of the present embodiment propagates trend forecasting method, accurately can find that microblogging propagates reason, propagates trend from propagation scale, propagating contents, spread scope three dimension full forecast microbloggings.
Embodiment 2
The present embodiment is propagated trend forecasting method by open more ins and outs to microblogging provided by the invention and is further detailed.
The process flow diagram setting up regression model that Fig. 2 provides for the embodiment of the present invention 2.As shown in Figure 2, this flow process relates to following process:
Data Collection: the essential characteristic and the communication process feature that obtain known transfer amount microblogging, because the essential characteristic of microblogging and communication process feature are defined, in embodiment 1 so place repeats no more.
Communication process cluster: respectively cluster is carried out to the propagation trend of microblogging according to microblogging communication process feature, preferably, K-means clustering algorithm can be adopted to carry out cluster, also other clustering algorithms in prior art can be adopted to classify, and wherein, number of clusters can be chosen by precision of prediction based on the actual application requirements, 5 classes are chosen in the present embodiment, i.e. 5 ranks, as shown in Figure 2, C1 to C5 level;
Model training: for each classification of content characteristic cluster result, sets up the linear regression model (LRM) of a content keyword numerical value and microblogging essential characteristic and communication process feature, learning model parameter; For each classification of quantative attribute cluster result, set up the linear regression model (LRM) of transfer amount (adding up of day transfer amount) and microblogging essential characteristic and communication process feature, learning model parameter; For each classification of user characteristics cluster result, set up the linear regression model (LRM) of post user's bean vermicelli number and microblogging essential characteristic and communication process feature, learning model parameter;
Fig. 3 is the process flow diagram of the propagation trend prediction of the microblogging to be predicted that the embodiment of the present invention 2 provides, and as shown in Figure 3, this flow process comprises following process:
Propagate trend prediction:
Calculate microblogging essential characteristic to be predicted; Calculate microblogging to be predicted from the time of posting 0 to the communication process eigenwert in i-1 each time interval, i is predicted time point;
Calculate microblogging to be predicted and the similarity of known microblogging in essential characteristic and above-mentioned three class communication process features respectively, classify;
Utilize all kinds of regression models trained, predict that microblogging to be predicted institute obtainable content keyword number, transfer amount, spread scope etc. propagate Trend value.
Embodiment 3
Present embodiments provide a kind of microblogging and propagate trend prediction device, this device propagates trend forecasting method for the microblogging realizing above-described embodiment 1 and embodiment 2 and provide, Fig. 4 is the structured flowchart of this device, and as shown in Figure 4, this device 40 comprises following ingredient:
Acquisition module 41, for obtaining the base attribute feature of microblogging to be predicted and each communication process feature;
Sort module 42, for calculating the base attribute feature of microblogging to be predicted and training data, the similarity of communication process feature, according to the communication process classification of the similarity calculated according to training data, microblogging to be predicted is classified, obtain the communication process classification belonging to microblogging to be predicted, the communication process classification of training data is obtained by the communication process characteristic similarity cluster of training data;
Wherein, base attribute feature comprises: the attribute of the user that posts and the attribute of content of microblog.Communication process feature comprises: the forwarding data feature in the content characteristic in the communication process of microblog data, the communication process of microblog data and the user characteristics in microblog data communication process.
Select module 43, select corresponding regression model for the communication process classification according to described microblogging to be predicted, it is in advance according to the regression model that described training data is set up that described training returns;
Prediction module 44, for predicting according to the propagation trend of regression model to microblogging to be predicted selected.
Further, said apparatus 40 can also comprise: set up module, for before the base attribute feature obtaining microblogging to be predicted and communication process feature, set up the content characteristic in the propagation of training data, forwarding data feature and the essential characteristic of user characteristics and training data and the linear regression model (LRM) of communication process feature respectively according to the communication process classification of training data.
Wherein, above-mentioned prediction module 43 for: predict according to the spread scope of the regression model selected to the corresponding number of content keyword, the transfer amount of microblogging to be predicted and the microblogging to be predicted of all kinds of microblog data of microblogging to be predicted successively.
The above; be only the specific embodiment of the present invention, but protection scope of the present invention is not limited thereto, is anyly familiar with those skilled in the art in the technical scope that the present invention discloses; the change that can expect easily or replacement, all should be encompassed within protection scope of the present invention.Therefore, protection scope of the present invention should be as the criterion with the protection domain of described claim.
Claims (10)
1. microblogging propagates a trend forecasting method, it is characterized in that, comprising:
Obtain base attribute feature and the communication process feature of microblogging to be predicted;
Calculate the base attribute feature of described microblogging to be predicted and training data, the similarity of communication process feature, described microblogging to be predicted is classified according to communication process classification according to the similarity calculated, obtain the communication process classification belonging to described microblogging to be predicted, described communication process classification is obtained by the communication process characteristic similarity cluster of training data;
Communication process classification according to described microblogging to be predicted selects corresponding regression model, and described recurrence is in advance according to the regression model that described training data is set up;
The propagation trend of regression model to described microblogging to be predicted according to selecting is predicted.
2. method according to claim 1, is characterized in that, described communication process feature comprises:
Forwarding data feature in content characteristic in the communication process of microblog data, the communication process of microblog data and the user characteristics in microblog data communication process.
3. method according to claim 2, is characterized in that, described method also comprises:
Before the base attribute feature obtaining microblogging to be predicted and communication process feature, set up the content characteristic in the propagation of described training data, forwarding data feature and the essential characteristic of user characteristics and described training data and the linear regression model (LRM) of communication process feature respectively according to the communication process classification of described training data.
4. method according to claim 1, is characterized in that, the described propagation trend of regression model to described microblogging to be predicted according to selecting is predicted, comprising:
Predict according to the spread scope of regression model to the number of the content keyword of described microblogging to be predicted, the transfer amount of described microblogging to be predicted and described microblogging to be predicted selected successively.
5. the method according to Claims 1 to 4 any one, is characterized in that, described base attribute feature, comprising:
To post the attribute of user and the attribute of content of microblog.
6. microblogging propagates a trend prediction device, it is characterized in that, comprising:
Acquisition module, for obtaining base attribute feature and the communication process feature of microblogging to be predicted;
Sort module, for calculating the base attribute feature of described microblogging to be predicted and training data, the similarity of communication process feature, described microblogging to be predicted is classified according to communication process classification according to the similarity calculated, obtain the communication process classification belonging to described microblogging to be predicted, described communication process classification is obtained by the communication process characteristic similarity cluster of training data;
Select module, select corresponding regression model for the communication process classification according to described microblogging to be predicted, it is in advance according to the regression model that described training data is set up that described training returns;
Prediction module, for predicting according to the propagation trend of regression model to described microblogging to be predicted selected.
7. device according to claim 6, is characterized in that, described communication process feature comprises:
Forwarding data feature in content characteristic in the communication process of microblog data, the communication process of microblog data and the user characteristics in microblog data communication process.
8. device according to claim 7, is characterized in that, described device also comprises:
Set up module, for before the base attribute feature obtaining microblogging to be predicted and communication process feature, set up the content characteristic in the propagation of described training data, forwarding data feature and the essential characteristic of user characteristics and described training data and the linear regression model (LRM) of communication process feature respectively according to the communication process classification of described training data.
9. device according to claim 6, is characterized in that, described prediction module is used for:
Predict according to the spread scope of regression model to the number of the content keyword of described microblogging to be predicted, the transfer amount of described microblogging to be predicted and described microblogging to be predicted selected successively.
10. the device according to claim 6 ~ 9 any one, is characterized in that, described base attribute feature, comprising:
To post the attribute of user and the attribute of content of microblog.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510284821.7A CN104915397A (en) | 2015-05-28 | 2015-05-28 | Method and device for predicting microblog propagation tendencies |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510284821.7A CN104915397A (en) | 2015-05-28 | 2015-05-28 | Method and device for predicting microblog propagation tendencies |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104915397A true CN104915397A (en) | 2015-09-16 |
Family
ID=54084460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510284821.7A Pending CN104915397A (en) | 2015-05-28 | 2015-05-28 | Method and device for predicting microblog propagation tendencies |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104915397A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105245380A (en) * | 2015-10-21 | 2016-01-13 | 腾讯科技（深圳）有限公司 | Message transmission mode identifying method and device |
| CN105488599A (en) * | 2015-12-29 | 2016-04-13 | 杭州数梦工场科技有限公司 | Method and device of prediction of article popularity |
| CN105653518A (en) * | 2015-12-25 | 2016-06-08 | 北京理工大学 | Specific group discovery and expansion method based on microblog data |
| 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 |
| CN106257459A (en) * | 2016-08-03 | 2016-12-28 | 哈尔滨工程大学 | A kind of micro-blog information propagation prediction method based on key user |
| CN106557551A (en) * | 2016-10-27 | 2017-04-05 | 西南石油大学 | Scale forecast method and system is propagated based on the microblogging that microblogging affair clustering is modeled |
| CN106570158A (en) * | 2016-10-27 | 2017-04-19 | 西南石油大学 | Micro-blog similarity statistic modeling-based micro-blog spread scale prediction method |
| CN106940732A (en) * | 2016-05-30 | 2017-07-11 | 国家计算机网络与信息安全管理中心 | A kind of doubtful waterborne troops towards microblogging finds method |
| CN107229689A (en) * | 2017-05-19 | 2017-10-03 | 四川新网银行股份有限公司 | A kind of method that microblogging public sentiment risk is studied and judged |
| CN107545033A (en) * | 2017-07-24 | 2018-01-05 | 清华大学 | A kind of computational methods based on the knowledge base entity classification for representing study |
| 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 |
| CN109657139A (en) * | 2018-12-10 | 2019-04-19 | 北京大学 | Analogy method, device and the equipment that network event is propagated |
| CN109981343A (en) * | 2019-02-18 | 2019-07-05 | 国家计算机网络与信息安全管理中心 | Microblogging spread and epidemic degree prediction technique and device based on propagating accelerated degree |
| CN111858934A (en) * | 2015-12-04 | 2020-10-30 | 杭州数梦工场科技有限公司 | Method and device for predicting article popularity |
| CN112102960A (en) * | 2020-11-20 | 2020-12-18 | 中国传媒大学 | Dynamics-based delay cross information propagation analysis method and system |
| CN112348279A (en) * | 2020-11-18 | 2021-02-09 | 武汉大学 | Information propagation trend prediction method and device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120042020A1 (en) * | 2010-08-16 | 2012-02-16 | Yahoo! Inc. | Micro-blog message filtering |
| CN102394798A (en) * | 2011-11-16 | 2012-03-28 | 北京交通大学 | Multi-feature based prediction method of propagation behavior of microblog information and system thereof |
| CN103258248A (en) * | 2013-05-21 | 2013-08-21 | 中国科学院计算技术研究所 | Method, device and system for predicting microblog fashion trend |
| CN103984701A (en) * | 2014-04-16 | 2014-08-13 | 北京邮电大学 | Micro-blog forwarding quantity prediction model generation method and micro-blog forwarding quantity prediction method |
| CN104182457A (en) * | 2014-07-14 | 2014-12-03 | 上海交通大学 | Poisson-process-model-based method for predicting event popularity in social network |
-
2015
- 2015-05-28 CN CN201510284821.7A patent/CN104915397A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120042020A1 (en) * | 2010-08-16 | 2012-02-16 | Yahoo! Inc. | Micro-blog message filtering |
| CN102394798A (en) * | 2011-11-16 | 2012-03-28 | 北京交通大学 | Multi-feature based prediction method of propagation behavior of microblog information and system thereof |
| CN103258248A (en) * | 2013-05-21 | 2013-08-21 | 中国科学院计算技术研究所 | Method, device and system for predicting microblog fashion trend |
| CN103984701A (en) * | 2014-04-16 | 2014-08-13 | 北京邮电大学 | Micro-blog forwarding quantity prediction model generation method and micro-blog forwarding quantity prediction method |
| CN104182457A (en) * | 2014-07-14 | 2014-12-03 | 上海交通大学 | Poisson-process-model-based method for predicting event popularity in social network |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105245380A (en) * | 2015-10-21 | 2016-01-13 | 腾讯科技（深圳）有限公司 | Message transmission mode identifying method and device |
| CN111858934A (en) * | 2015-12-04 | 2020-10-30 | 杭州数梦工场科技有限公司 | Method and device for predicting article popularity |
| CN105653518A (en) * | 2015-12-25 | 2016-06-08 | 北京理工大学 | Specific group discovery and expansion method based on microblog data |
| CN105488599A (en) * | 2015-12-29 | 2016-04-13 | 杭州数梦工场科技有限公司 | Method and device of prediction of article popularity |
| CN105488599B (en) * | 2015-12-29 | 2020-03-06 | 杭州数梦工场科技有限公司 | Method and device for predicting article popularity |
| CN106940732A (en) * | 2016-05-30 | 2017-07-11 | 国家计算机网络与信息安全管理中心 | A kind of doubtful waterborne troops towards microblogging finds method |
| 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 |
| CN106257459B (en) * | 2016-08-03 | 2019-11-01 | 哈尔滨工程大学 | A kind of micro-blog information propagation prediction method based on key user |
| CN106257459A (en) * | 2016-08-03 | 2016-12-28 | 哈尔滨工程大学 | A kind of micro-blog information propagation prediction method based on key user |
| 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 |
| CN106570158A (en) * | 2016-10-27 | 2017-04-19 | 西南石油大学 | Micro-blog similarity statistic modeling-based micro-blog spread scale prediction method |
| CN106557551A (en) * | 2016-10-27 | 2017-04-05 | 西南石油大学 | Scale forecast method and system is propagated based on the microblogging that microblogging affair clustering is modeled |
| CN107229689A (en) * | 2017-05-19 | 2017-10-03 | 四川新网银行股份有限公司 | A kind of method that microblogging public sentiment risk is studied and judged |
| CN107545033A (en) * | 2017-07-24 | 2018-01-05 | 清华大学 | A kind of computational methods based on the knowledge base entity classification for representing study |
| CN107545033B (en) * | 2017-07-24 | 2020-12-01 | 清华大学 | Knowledge base entity classification calculation method based on representation learning |
| CN109657139A (en) * | 2018-12-10 | 2019-04-19 | 北京大学 | Analogy method, device and the equipment that network event is propagated |
| CN109657139B (en) * | 2018-12-10 | 2021-10-22 | 北京大学 | Simulation method, device and equipment for network event propagation |
| CN109981343A (en) * | 2019-02-18 | 2019-07-05 | 国家计算机网络与信息安全管理中心 | Microblogging spread and epidemic degree prediction technique and device based on propagating accelerated degree |
| CN112348279A (en) * | 2020-11-18 | 2021-02-09 | 武汉大学 | Information propagation trend prediction method and device, electronic equipment and storage medium |
| CN112348279B (en) * | 2020-11-18 | 2024-04-05 | 武汉大学 | Information propagation trend prediction method, device, electronic equipment and storage medium |
| CN112102960A (en) * | 2020-11-20 | 2020-12-18 | 中国传媒大学 | Dynamics-based delay cross information propagation analysis method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104915397A (en) | Method and device for predicting microblog propagation tendencies | |
| CN107515873B (en) | Junk information identification method and equipment | |
| CN103678613B (en) | Method and device for calculating influence data | |
| CN106886518B (en) | Microblog account number classification method | |
| CN103150374A (en) | Method and system for identifying abnormal microblog users | |
| CN102609475A (en) | Method for monitoring content of microblog and monitoring system | |
| CN105488092A (en) | Time-sensitive self-adaptive on-line subtopic detecting method and system | |
| CN105550275B (en) | A kind of microblogging transfer amount prediction technique | |
| CN109685153A (en) | A kind of social networks rumour discrimination method based on characteristic aggregation | |
| CN112199608A (en) | Social media rumor detection method based on network information propagation graph modeling | |
| CN103823890A (en) | Microblog hot topic detection method and device aiming at specific group | |
| CN111191099B (en) | User activity type identification method based on social media | |
| CN104731958A (en) | User-demand-oriented cloud manufacturing service recommendation method | |
| CN107527240A (en) | A kind of operator's industry product Praise effect identification system and method | |
| CN106204297A (en) | A kind of recognition methods closing social propagation opinion leader and device | |
| CN110297990A (en) | The associated detecting method and system of crowdsourcing marketing microblogging and waterborne troops | |
| CN106126519A (en) | The methods of exhibiting of media information and server | |
| CN111242218B (en) | Cross-social network user identity recognition method fusing user multi-attribute information | |
| Liao et al. | GRBMC: An effective crowdsourcing recommendation for workers groups | |
| CN105468669A (en) | Adaptive microblog topic tracking method fusing with user relationship | |
| CN106411704A (en) | Distributed junk short message recognition method | |
| Hou et al. | Research on the behaviour and law of quantity growth of followers based on WeChat official account | |
| CN116015939A (en) | Advanced persistent threat interpretation method based on atomic technology template | |
| Wang et al. | Emotion-based Independent Cascade model for information propagation in online social media | |
| CN107767278B (en) | Method and device for constructing community hierarchy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20150916 |