CN106777157A - A kind of class gravity model microblogging Forecasting Methodology and system based on theme - Google Patents
A kind of class gravity model microblogging Forecasting Methodology and system based on theme Download PDFInfo
- Publication number
- CN106777157A CN106777157A CN201611184260.4A CN201611184260A CN106777157A CN 106777157 A CN106777157 A CN 106777157A CN 201611184260 A CN201611184260 A CN 201611184260A CN 106777157 A CN106777157 A CN 106777157A
- Authority
- CN
- China
- Prior art keywords
- microblogging
- node
- forwarding
- weight
- theme
- 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
Links
- 230000005484 gravity Effects 0.000 title claims abstract description 20
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 15
- 230000009193 crawling Effects 0.000 claims abstract description 15
- 238000007619 statistical method Methods 0.000 claims abstract description 4
- 235000010627 Phaseolus vulgaris Nutrition 0.000 claims description 19
- 244000046052 Phaseolus vulgaris Species 0.000 claims description 19
- 230000000694 effects Effects 0.000 claims description 10
- 238000013500 data storage Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000007717 exclusion Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
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
- 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
- G06F16/31—Indexing; Data structures therefor; Storage structures
- G06F16/316—Indexing structures
-
- 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
- G06F16/35—Clustering; Classification
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/01—Social networking
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of class gravity model microblogging Forecasting Methodology and system based on theme, described method is comprised the following steps：Corresponding microblogging is crawled, and corresponding microblogging forwarding relation and content of microblog are stored according to the size of time window D respectively；Microblogging to crawling carries out subject classification, again the microblogging forwarding relation for crawling is stored by microblogging theme, microblogging forwarding relational network is set up for each microblogging theme, forwarding relation in storehouse is forwarded according to each microblogging theme, the weight of each edge is calculated and the weight on side is calculated using statistical method.Described system crawls module, microblogging storehouse, forwarding relation storehouse, analysis module, projected relationship storehouse, user front end module and user's rear module including data, the present invention improves the precision of local prediction, the K batches of forwarding situation of follower can arbitrarily be predicted by the class gravity model with weight simultaneously, relation is forwarded based on different themes, prediction accuracy is improve.
Description
Technical field
The present invention relates to microblogging prediction field, specifically a kind of class gravity model microblogging Forecasting Methodology based on theme be
System.
Background technology
Microblogging is the social platform that a kind of real time information based on customer relationship is exchanged, shared, propagating, with Facebook,
The social networks such as Twitter equally have impact on the life exchange way of the mankind.In microblog, as number of users is with hundreds of millions
Level is the increase of unit quantity, the behind reflection of the magnanimity information such as substantial amounts of picture, text be people life idea, knowledge
With interesting thing.The appearance of microblogging also brings many problems except producing beneficial effect, such as bad speech without constraint
The heavy damage social life general mood such as propagate.So, the active state to microblog users is predicted, for government, enterprise's thing
Industry unit, individual have important meaning.
In existing microblogging prediction solution, the Chinese patent of Publication No. CN104933622A discloses a kind of base
In user and the microblogging Popularity prediction method and system of microblogging theme, the method includes：Obtain the microblogging in preset time period
Data and user data, according to the microblog data and the user data, obtain user property feature and microblogging theme feature,
The user property feature is normalized, user clustering is carried out with the user characteristics after treatment, and according to poly-
Class result, obtains the classification information of user；According to the microblogging theme feature and the classification information of the user, obtain user and gather
Forwarding feature of the class under the microblogging theme, and calculate weight coefficient of the user clustering under the microblogging theme；Root
According to the microblogging theme feature, the user property feature, the weight coefficient, microblogging Popularity prediction model is built, passed through
The microblogging Popularity prediction model is predicted to microblogging popularity.The weighing factor at patent utilization different time interval enters
The structure of row Popularity prediction model carries out node weights and portrays not with digraph network of the present invention based on theme forwarding relation
The scheme of same forwarding probability is different, and the present invention is not only realized to any K batches of concern under different theme forwarding relations
The prediction of person, and improve the degree of accuracy of prediction.
Relational network, in the forwarding relation of different themes type, Duo Zhongji are forwarded for the various grades of microbloggings of layer relation
The accuracy of the prediction of layer relation is not high, it is impossible to realize to any K batches of forwarding situation prediction of follower.
The content of the invention
It is an object of the invention to overcome the deficiencies in the prior art, there is provided a kind of class gravity model microblogging based on theme is pre-
Method and system is surveyed, at least to realize carrying out any K degree bean vermicelli forwarding prediction, improve the effect of accuracy and precision of prediction.
The purpose of the present invention is achieved through the following technical solutions：A kind of class gravity model microblogging based on theme is pre-
Survey method, it is comprised the following steps：
S1：Microblogging is crawled, and corresponding microblogging forwarding relation and content of microblog are stored according to the size of time window D respectively；
S2：Subject classification is carried out to the content of microblog for crawling using existing topic model；
S3：Microblogging forwarding relation is stored according to different subject classifications respectively；
S4：Based on the forwarding relation of different themes classification, digraph network is set up；
S5：Node number M in statistics digraph network, and give the weight of each node 1/M；
S6：Count the total N that is forwarded of microblogging of each microblog users issue, and each microblog users it is corresponding each
The quantity n of bean vermicelli forwarding1,n2,n3…ni, the initial weight for calculating the corresponding every directed edge of each bean vermicelli is：
S7：The weight of selected node according in the weight distribution of directed edge to the node for paying close attention to the node, it is used to update
Pay close attention to the weight of each node of the node；
S8：According to the weight for updating the later node weights corresponding directed edge of calculating；
S9：Bad execution S7~S8 steps are followed, until the weight of each node restrains；
S10：The node weights k of the K degree beans vermicelli of microblogging to be measured is obtained as needed1,k2,…kn；
S11：Calculate microblogging to be measured to a selected gravitational index for K degree beans vermicelli：
Wherein, M is the node weights of microblog users to be measured, and m is a selected node weights for K degree beans vermicelli, and r is M to m
A route all directed edges weight sum inverse, G sets according to actual needs；
Directed edge in the step S1 refers to the unidirectional side for pointing to follower by the person of being concerned under same subject classification.
Network node in the step S2 is to be related to forward the follower under the same subject classification of microblogging, described
Node number M is to be related to forward the follower's number under the same subject of microblogging.
Described K degree beans vermicelli are the K crowdes of user of concern forwarding microblogging, and K crowdes of user is closed by paying close attention to K-1 crowdes of user
Note the forwarding microblogging.
In the S5, the microblogging number forwarded according to follower accounts for the ratio of the microblogging the being forwarded sum of the person's of being concerned issue
It is allocated weight.
By setting a threshold value in the step S7, whether the rate of change of each node is judged less than the threshold value, if so,
Then stop iteration.
Since a setting value, pass a test described G G value of the prediction effect under finding optimum prediction effect,
Then the G values under using the G values under optimum prediction effect as selected particular topic.
A kind of class gravity model microblogging forecasting system based on theme, it crawls module, microblogging storehouse, forwarding pass including data
It is storehouse, analysis module, projected relationship storehouse, user front end module and user's rear module, the data crawl module for micro-
Rich crawls；The microblogging storehouse is used to store the content of microblog for crawling；The forwarding relation storehouse crawls module for data storage
The microblogging forwarding relation for crawling；The analysis module is used to carry out subject classification to the content of microblog for crawling, to forwarding relation storehouse
In forwarding relation carry out statistical analysis, set up corresponding figure network, and weight and the weight on side in calculating network node；Institute
Projected relationship storehouse is stated for preserving the forwarding information of forecasting of the different themes microblogging of analysis module generation；The user front end module
Provide the user interface and facilitate its typing microblog users information to be measured；User's rear module calls the function of analysis module to enter
Row analysis, the information according to user input is predicted the outcome, and is supplied to specific website to be called after the storage that predicts the outcome.
The beneficial effects of the invention are as follows：Then the present invention carries out difference by crawling microblogging according to the content of microblog for crawling
Subject classification, based under different subject classification forwarding relations, count all node numbers and simultaneously give each node identical
After initial weight, the forwarding situation based on identical initial weight and node calculates the initial weight of corresponding each edge, utilizes
The initial weight of each edge and corresponding node weights update all node weights, then set up any by class gravity model
Node contacts between 2 points, while being portrayed the forwarding probability of different nodes using the node weights with weight, are improve
The precision of local prediction, while the K batches of forwarding situation of follower can arbitrarily be predicted by the class gravity model with weight,
Compared to the K batches of forwarding situation of follower is predicted by the iterative calculation of the layer of level one by one, forecasting efficiency is improve, and be based on
Different theme forwarding relations, improves prediction accuracy.
Brief description of the drawings
Fig. 1 is that the method for the present invention performs flow chart of steps.
Specific embodiment
Technical scheme is described in further detail below in conjunction with the accompanying drawings, but protection scope of the present invention is not limited to
It is as described below.
As shown in figure 1, a kind of class gravity model microblogging Forecasting Methodology based on theme, it is comprised the following steps：
S1：Microblogging is crawled, and corresponding microblogging forwarding relation and content of microblog are stored according to the size of time window D respectively；
S2：Subject classification is carried out to the content of microblog for crawling using existing topic model；
S3：Microblogging forwarding relation is stored according to different subject classifications respectively；
S4：Based on the forwarding relation of different themes classification, digraph network is set up；
S5：Node number M in statistics digraph network, and give the weight of each node 1/M；
S6：Count the total N that is forwarded of microblogging of each microblog users issue, and each microblog users it is corresponding each
The quantity n of bean vermicelli forwarding1,n2,n3…ni, the initial weight for calculating the corresponding every directed edge of each bean vermicelli is：
S7：The weight of selected node according in the weight distribution of directed edge to the node for paying close attention to the node, it is used to update
Pay close attention to the weight of each node of the node；
S8：According to the weight for updating the later node weights corresponding directed edge of calculating；
S9：Bad execution S7~S8 steps are followed, until the weight of each node restrains；
S10：The node weights k of the K degree beans vermicelli of microblogging to be measured is obtained as needed1,k2,…kn；
S11：Calculate microblogging to be measured to a selected gravitational index for K degree beans vermicelli：
Wherein, M is the node weights of microblog users to be measured, and m is a selected node weights for K degree beans vermicelli, and r is M to m
A route all directed edges weight sum inverse, G sets according to actual needs；
Directed edge in the step S1 refers to the unidirectional side for pointing to follower by the person of being concerned under same subject classification.
Network node in the step S2 is to be related to forward the follower under the same subject classification of microblogging, described
Node number M is to be related to forward the follower's number under the same subject of microblogging.
Described K degree beans vermicelli are the K crowdes of user of concern forwarding microblogging, and K crowdes of user is closed by paying close attention to K-1 crowdes of user
Note the forwarding microblogging.
In the S5, the microblogging number forwarded according to follower accounts for the ratio of the microblogging the being forwarded sum of the person's of being concerned issue
It is allocated weight.
By setting a threshold value in the step S7, whether the rate of change of each node is judged less than the threshold value, if so,
Then stop iteration.
Since a setting value, pass a test described G G value of the prediction effect under finding optimum prediction effect,
Then the G values under using the G values under optimum prediction effect as selected particular topic, are used to improve the extensive of different themes prediction
Ability.
A kind of class gravity model microblogging forecasting system based on theme, it crawls module, microblogging storehouse, forwarding pass including data
It is storehouse, analysis module, projected relationship storehouse, user front end module and user's rear module, the data crawl module for micro-
Rich crawls；The microblogging storehouse is used to store the content of microblog for crawling；The forwarding relation storehouse crawls module for data storage
The microblogging forwarding relation for crawling；The analysis module is used to carry out subject classification to the content of microblog for crawling, to forwarding relation storehouse
In forwarding relation carry out statistical analysis, set up corresponding figure network, and weight and the weight on side in calculating network node；Institute
Projected relationship storehouse is stated for preserving the forwarding information of forecasting of the different themes microblogging of analysis module generation；The user front end module
Provide the user interface and facilitate its typing microblog users information to be measured；User's rear module calls the function of analysis module to enter
Row analysis, the information according to user input is predicted the outcome, and is supplied to specific website to be called after the storage that predicts the outcome.
The above is only the preferred embodiment of the present invention, it should be understood that the present invention is not limited to described herein
Form, is not to be taken as the exclusion to other embodiment, and can be used for various other combinations, modification and environment, and can be at this
In the text contemplated scope, it is modified by the technology or knowledge of above-mentioned teaching or association area.And those skilled in the art are entered
Capable change and change does not depart from the spirit and scope of the present invention, then all should be in the protection domain of appended claims of the present invention
It is interior.
Claims (8)
1. a kind of class gravity model microblogging Forecasting Methodology based on theme, it is characterised in that it is comprised the following steps：
S1：Microblogging is crawled, and corresponding microblogging forwarding relation and content of microblog are stored according to the size of time window D respectively；
S2：Subject classification is carried out to the content of microblog for crawling using existing topic model；
S3：Microblogging forwarding relation is stored according to different subject classifications respectively；
S4：Based on the forwarding relation of different themes classification, digraph network is set up；
S5：Node number M in statistics digraph network, and give the weight of each node 1/M；
S6：Count the total N that the microblogging of each microblog users issue is forwarded, and corresponding each bean vermicelli of each microblog users
The quantity n of forwarding1,n2,n3…ni, the initial weight for calculating the corresponding every directed edge of each bean vermicelli is：
S7：The weight of selected node according in the weight distribution of directed edge to the node for paying close attention to the node, it is used to update concern
The weight of each node of the node；
S8：According to the weight for updating the later node weights corresponding directed edge of calculating；
S9：Bad execution S7~S8 steps are followed, until the weight of each node restrains；
S10：The node weights k of the K degree beans vermicelli of microblogging to be measured is obtained as needed1,k2,…kn；
S11：Calculate microblogging to be measured to a selected gravitational index for K degree beans vermicelli：
Wherein, M is the node weights of microblog users to be measured, and m is a selected node weights for K degree beans vermicelli, and r is the one of M to m
The inverse of the weight sum of all directed edges of bar route, G sets according to actual needs.
2. a kind of class gravity model microblogging Forecasting Methodology based on theme according to claim 1, it is characterised in that：It is described
Directed edge in step S1 refers to the unidirectional side for pointing to follower by the person of being concerned under same subject classification.
3. a kind of class gravity model microblogging Forecasting Methodology based on theme according to claim 1, it is characterised in that：It is described
Network node in step S2 is the follower being related under the same subject classification of forwarding microblogging, and described node number M is
It is related to forward the follower's number under the same subject of microblogging.
4. a kind of class gravity model microblogging Forecasting Methodology based on theme according to claim 1, it is characterised in that：It is described
K degree beans vermicelli be K crowd concern forwarding microblogging user, K crowdes of user criticize user to be concerned about the forwarding micro- by paying close attention to K-1
It is rich.
5. a kind of class gravity model microblogging Forecasting Methodology based on theme according to claim 1, it is characterised in that：It is described
In S5, the ratio that the microblogging number forwarded according to follower accounts for the microblogging the being forwarded sum of the person's of being concerned issue is allocated power
Weight.
6. a kind of class gravity model microblogging Forecasting Methodology based on theme according to claim 1, it is characterised in that：It is described
By setting a threshold value in step S7, whether the rate of change of each node is judged less than the threshold value, if so, then stopping iteration.
7. a kind of class gravity model microblogging Forecasting Methodology based on theme according to claim 1, it is characterised in that：It is described
G since a setting value, pass a test G value of the prediction effect under finding optimum prediction effect, then with optimal pre-
The G values surveyed under effect are used as the G values under selected particular topic.
8. a kind of class gravity model microblogging forecasting system based on theme, it is characterised in that：It crawls module, microblogging including data
Storehouse, forwarding relation storehouse, analysis module, projected relationship storehouse, user front end module and user's rear module, the data crawl module
For being crawled to microblogging；The microblogging storehouse is used to store the content of microblog for crawling；The forwarding relation storehouse is used for data storage
Crawl the microblogging forwarding relation that module is crawled；The analysis module is used to carry out subject classification to the content of microblog for crawling, to turning
Forwarding relation in hair relation storehouse carries out statistical analysis, sets up corresponding figure network, and the weight in calculating network node and side
Weight；The projected relationship storehouse is used for the forwarding information of forecasting of the different themes microblogging for preserving analysis module generation；The use
Family front-end module provides the user interface and facilitates its typing microblog users information to be measured；User's rear module calls analysis mould
The function of block is analyzed, and the information according to user input is predicted the outcome, and specific website is supplied to after the storage that predicts the outcome
It is called.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611184260.4A CN106777157B (en) | 2016-12-20 | 2016-12-20 | Topic-based gravity-like model microblog prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611184260.4A CN106777157B (en) | 2016-12-20 | 2016-12-20 | Topic-based gravity-like model microblog prediction method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106777157A true CN106777157A (en) | 2017-05-31 |
| CN106777157B CN106777157B (en) | 2023-04-07 |
Family
ID=58894049
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611184260.4A Active CN106777157B (en) | 2016-12-20 | 2016-12-20 | Topic-based gravity-like model microblog prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106777157B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110162592A (en) * | 2019-05-24 | 2019-08-23 | 东北大学 | A kind of news keyword extracting method based on the improved TextRank of gravitation |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662956A (en) * | 2012-03-05 | 2012-09-12 | 西北工业大学 | Method for identifying opinion leaders in social network based on topic link behaviors of users |
| CN103412872A (en) * | 2013-07-08 | 2013-11-27 | 西安交通大学 | Micro-blog social network information recommendation method based on limited node drive |
| CN103577593A (en) * | 2013-11-14 | 2014-02-12 | 中国科学院声学研究所 | Method and system for video aggregation based on microblog hot topics |
| CN103617279A (en) * | 2013-12-09 | 2014-03-05 | 南京邮电大学 | Method for achieving microblog information spreading influence assessment model on basis of Pagerank method |
| CN103617486A (en) * | 2013-11-21 | 2014-03-05 | 中国电子科技集团公司第十五研究所 | Method and system for conducting dynamic graphical monitoring on complex service processes |
| CN104123352A (en) * | 2014-07-10 | 2014-10-29 | 西安理工大学 | Method for measuring influence of users on topic hierarchy for MicroBlog |
| CN104537096A (en) * | 2015-01-09 | 2015-04-22 | 哈尔滨工程大学 | Microblog message influence measuring method based on microblog message propagation tree |
| US20150120721A1 (en) * | 2013-10-25 | 2015-04-30 | Marketwire L.P. | Systems and Methods for Dynamically Determining Influencers in a Social Data Network Using Weighted Analysis |
| CN104933622A (en) * | 2015-03-12 | 2015-09-23 | 中国科学院计算技术研究所 | Microblog popularity degree prediction method based on user and microblog theme and microblog popularity degree prediction system based on user and microblog theme |
| CN105893637A (en) * | 2016-06-24 | 2016-08-24 | 四川大学 | Link prediction method in large-scale microblog heterogeneous information network |
-
2016
- 2016-12-20 CN CN201611184260.4A patent/CN106777157B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102662956A (en) * | 2012-03-05 | 2012-09-12 | 西北工业大学 | Method for identifying opinion leaders in social network based on topic link behaviors of users |
| CN103412872A (en) * | 2013-07-08 | 2013-11-27 | 西安交通大学 | Micro-blog social network information recommendation method based on limited node drive |
| US20150120721A1 (en) * | 2013-10-25 | 2015-04-30 | Marketwire L.P. | Systems and Methods for Dynamically Determining Influencers in a Social Data Network Using Weighted Analysis |
| CN103577593A (en) * | 2013-11-14 | 2014-02-12 | 中国科学院声学研究所 | Method and system for video aggregation based on microblog hot topics |
| CN103617486A (en) * | 2013-11-21 | 2014-03-05 | 中国电子科技集团公司第十五研究所 | Method and system for conducting dynamic graphical monitoring on complex service processes |
| CN103617279A (en) * | 2013-12-09 | 2014-03-05 | 南京邮电大学 | Method for achieving microblog information spreading influence assessment model on basis of Pagerank method |
| CN104123352A (en) * | 2014-07-10 | 2014-10-29 | 西安理工大学 | Method for measuring influence of users on topic hierarchy for MicroBlog |
| CN104537096A (en) * | 2015-01-09 | 2015-04-22 | 哈尔滨工程大学 | Microblog message influence measuring method based on microblog message propagation tree |
| CN104933622A (en) * | 2015-03-12 | 2015-09-23 | 中国科学院计算技术研究所 | Microblog popularity degree prediction method based on user and microblog theme and microblog popularity degree prediction system based on user and microblog theme |
| CN105893637A (en) * | 2016-06-24 | 2016-08-24 | 四川大学 | Link prediction method in large-scale microblog heterogeneous information network |
Non-Patent Citations (2)
| Title |
|---|
| 简国明 等: "微博用户及消息的影响力研究与建模", 《佛山科学技术学院学报(自然科学版)》 * |
| 罗知林 等: "一个基于随机森林的微博转发预测算法", 《计算机科学》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110162592A (en) * | 2019-05-24 | 2019-08-23 | 东北大学 | A kind of news keyword extracting method based on the improved TextRank of gravitation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106777157B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10430464B1 (en) | Scalable graph propagation for knowledge expansion | |
| CN103150374B (en) | Method and system for identifying abnormal microblog users | |
| Zaman et al. | A bayesian approach for predicting the popularity of tweets | |
| Li et al. | How the government’s punishment and individual’s sensitivity affect the rumor spreading in online social networks | |
| CN109558951A (en) | A kind of fraud account detection method, device and its storage medium | |
| Hoang et al. | Virality and susceptibility in information diffusions | |
| Zhang et al. | An optimized Nash nonlinear grey Bernoulli model based on particle swarm optimization and its application in prediction for the incidence of Hepatitis B in Xinjiang, China | |
| CN106250403A (en) | Customer loss Forecasting Methodology and device | |
| CN110266745A (en) | Information flow recommended method, device, equipment and storage medium based on depth network | |
| CN104636801A (en) | Transmission line audible noise prediction method based on BP neural network optimization | |
| CN106850314A (en) | A kind of method and apparatus for determining user property model and customer attribute information | |
| CN107895038A (en) | A kind of link prediction relation recommends method and device | |
| Liao et al. | Devrank: Mining influential developers in github | |
| CN106789338B (en) | Method for discovering key people in dynamic large-scale social network | |
| CN105869022A (en) | Application popularity prediction method and apparatus | |
| US10742627B2 (en) | System and method for dynamic network data validation | |
| CN107480227A (en) | A kind of information-pushing method based on big data | |
| Sun et al. | A tent marine predators algorithm with estimation distribution algorithm and Gaussian random walk for continuous optimization problems | |
| CN109635192A (en) | Magnanimity information temperature seniority among brothers and sisters update method and platform towards micro services | |
| Liang et al. | An improved genetic algorithm for service selection under temporal constraints in cloud computing | |
| CN106777157A (en) | A kind of class gravity model microblogging Forecasting Methodology and system based on theme | |
| CN106600071A (en) | Topic-based microblog forwarding prediction method and system | |
| Zhou et al. | A dynamic logistic regression for network link prediction | |
| Bandara et al. | Churn prediction methodologies in the telecommunications sector: A survey | |
| CN109033288A (en) | A kind of intelligent terminal security level classification method based on BP neural network |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |