CN103885993A - Public opinion monitoring method and device for microblog - Google Patents

Public opinion monitoring method and device for microblog Download PDF

Info

Publication number
CN103885993A
CN103885993A CN201210566545.XA CN201210566545A CN103885993A CN 103885993 A CN103885993 A CN 103885993A CN 201210566545 A CN201210566545 A CN 201210566545A CN 103885993 A CN103885993 A CN 103885993A
Authority
CN
China
Prior art keywords
bloger
forwarding
microblogging
monitored
module
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
Application number
CN201210566545.XA
Other languages
Chinese (zh)
Inventor
宋毅强
梁肖
于晓明
杨建武
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.)
Peking University
Peking University Founder Group Co Ltd
Beijing Founder Electronics Co Ltd
Original Assignee
Peking University
Peking University Founder Group Co Ltd
Beijing Founder Electronics Co Ltd
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 Peking University, Peking University Founder Group Co Ltd, Beijing Founder Electronics Co Ltd filed Critical Peking University
Priority to CN201210566545.XA priority Critical patent/CN103885993A/en
Publication of CN103885993A publication Critical patent/CN103885993A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/95Retrieval from the web
    • G06F16/958Organisation or management of web site content, e.g. publishing, maintaining pages or automatic linking

Abstract

The invention provides a public opinion monitoring method for microblog. The method includes: determining the source blogger of to-be-monitored microblog; performing depth-first traversal on the source blogger and forwarding bloggers of the to-be-monitored microblog; acquiring the follower number of the forwarding bloggers and the forwarding times of to-be-monitored microblog; setting importance of the forwarding bloggers according to the follower number and the forwarding times. The invention further provides a public opinion monitoring device for microblog. The device comprises a determining module, a traverse module, an acquiring module and a setting module, wherein the determining module is used for determining the source blogger of the to-be-monitored microblog, the traverse module is used for performing depth-first traversal on the source blogger and forwarding bloggers of the to-be-monitored microblog, the acquiring module is used for acquiring the follower number of the forwarding bloggers and the forwarding times of to-be-monitored microblog, and the setting module is used for setting the importance of the forwarding bloggers according to the follower number and the forwarding times. By the method and the device, public opinion monitoring difficulty is lowered, and public opinion analyzing accuracy is increased.

Description

For public sentiment method for supervising and the device of microblogging
Technical field
The present invention relates to public sentiment monitoring field, in particular to public sentiment method for supervising and device for microblogging.
Background technology
In portal website, it is millions of to several ten million bars that the microblogging data volume of every day reaches, various microblogging data are numerous and complicated mixed and disorderly, and a network public-opinion event only experiences shorter a period of time from source to great outburst, though have certain ageing, but its influence power is very large, microblogging is affecting the change of social politics and economy to a certain extent, in view of this, the monitoring of microblogging is become to network public-opinion and detect and study a considerable part, but how from existing a large amount of microblogging data, extract valuable data, the research of personnel to public sentiment event directs study, become extremely urgent thing.
Unified warehouse-in post analysis after the data that existing software returns web data or open platform capture.Analyst carries out association to the mass data in database, therefrom obtains character relation and microblogging and forwards relation, and database is huge, and the ratio that useless data account for is too high, and Useful Information ratio is little, has increased the difficulty of analyzing.
Summary of the invention
The present invention aims to provide public sentiment method for supervising and the device for microblogging, to solve the above problems.
In an embodiment of the present invention, provide a kind of public sentiment method for supervising for microblogging, having comprised: the source bloger who determines monitored microblogging; From the forwarding bloger of the monitored microblogging of source bloger's depth-first traversal; Obtain and forward bloger's bean vermicelli number and the hop count about monitored microblogging thereof; According to its bean vermicelli number and hop count, the importance degree that forwards bloger is set.
In an embodiment of the present invention, provide a kind of public sentiment supervising device for microblogging, having comprised: determination module, for determining the source bloger of monitored microblogging; Spider module, for the forwarding bloger from the monitored microblogging of source bloger's depth-first traversal; Acquisition module, forwards bloger's bean vermicelli number and the hop count about monitored microblogging thereof for obtaining; Module is set, for the importance degree that forwards bloger being set according to its bean vermicelli number and hop count.
The public sentiment method for supervising for microblogging of the above embodiment of the present invention and device are because determined the emphasis bloger of microblogging repeating process, so reduced monitoring parameter, reduce significantly monitor data, reduced the difficulty of the analysis of public opinion, improved the analysis of public opinion accuracy rate.
Brief description of the drawings
Accompanying drawing described herein is used to provide a further understanding of the present invention, forms the application's a part, and schematic description and description of the present invention is used for explaining the present invention, does not form inappropriate limitation of the present invention.In the accompanying drawings:
Fig. 1 shows according to the process flow diagram of the public sentiment method for supervising for microblogging of the embodiment of the present invention;
Fig. 2 shows according to the schematic diagram of the public sentiment supervising device for microblogging of the embodiment of the present invention.
Embodiment
Below with reference to the accompanying drawings and in conjunction with the embodiments, describe the present invention in detail.
Fig. 1 shows according to the process flow diagram of the public sentiment method for supervising for microblogging of the embodiment of the present invention, comprising:
Step S10, determines the source bloger of monitored microblogging;
Step S20, from the forwarding bloger of the monitored microblogging of source bloger's depth-first traversal;
Step S30, obtains and forwards bloger's bean vermicelli number and the hop count about monitored microblogging thereof;
Step S40, arranges according to its bean vermicelli number and hop count the importance degree that forwards bloger.
Inventor is this from media discovery afterwards by analysis to microblogging, and a network public-opinion event then so will be through some individuals' relay and comment to a large amount of propagation from source.If in route of transmission, when a certain individual of information process, there is diffusion, define so this bloger and have contribution for Information Communication, in a certain network event route of transmission, must some bloger produce very important effect to this information, if the bloger who only this part is played a significant role analyzes, can analyze whole network public-opinion event.
Unified warehouse-in post analysis after the data that prior art is returned web data or open platform capture, and this method is determined the importance degree that forwards bloger from these data, thereby the only microblogging data analysis to important bloger, so reduced monitoring parameter, reduce significantly monitor data, reduce the difficulty of the analysis of public opinion, improved the analysis of public opinion accuracy rate.
Preferably, pass up to source bloger by the forward-path of monitored microblogging.Upwards trace back to as much as possible the source bloger of top layer by forward-path, if interrupt in source, the bloger who only traces back to one or more top layers, can carry out follow-up traversal analysis as source bloger respectively using the bloger of the one or more top layer.
Preferably, comprise from the forwarding bloger of the monitored microblogging of source bloger's depth-first traversal: from current forwarding bloger's microblogging space, find monitored microblogging; Obtain the forwarding list of monitored microblogging; All forwarding blogers on traversal forwarding list.Look up from vertical, whole traversal is degree of depth traversal, and to current level, all forwarding blogers on traversal forwarding list, this is equivalent to range traversal.Whole ergodic process is the algorithmic language of standard, repeats no more here.
Forwarding list is the core component of microblogging propagation trajectories, and the formation of whole propagation trajectories namely realizes by forwarding list, supposes to have an original microblogging A of microblogging, as microblogging B, and C, when D has forwarded A, the forwarding list of microblogging A is B-C-D; If E, F has forwarded B, and the forwarding list of B is E-F so, starts just to have formed some propagation trajectories so from A, and wherein two is exactly A-B-E and A-B-F.
The preferred embodiment is utilized Depth Priority Algorithm, first in a public sentiment event, and the microblogging that can select a quilt extensively to relay.Get the forwarding list of these microblogging data, this list is joined in a set, then obtain corresponding bloger by the microblogging forwarding, then utilize breadth First algorithm to obtain the micro-blog information that this bloger issues by bloger's name, and obtain original microblogging be again forwarded list and hop count under this bloger, so just can get the bloger relevant to original microblogging and forwarding information by recurrence.
Preferably, according to its bean vermicelli number and hop count, the importance degree that forwards bloger being set comprises: Weight=α * nFllower+ β * nRetweet is set; Wherein, weight represents importance degree, and nFllower represents bean vermicelli number, and α represents the default weight of nFllower, and nRetweet represents hop count, and β represents the default weight of nRetweet.α and β can be arranged artificially by user, thereby determine the significance level of bean vermicelli number and the significance level of hop count, to meet better user's individual demand.α=0.2 is for example set, β=0.8, illustrate in the repeating process of a microblogging, the number of times again forwarding is more, this bloger's influence power is larger, nRetweet is generally a numerical value less than nFllower, only has in bean vermicelli list nRetweet when someone repeatedly forwards same microblogging to be just likely greater than nFllower.
Preferably, this method also comprises: determine that its importance degree is greater than the forwarding bloger of preset value; Definite forwarding bloger is set to emphasis bloger.For example, get front 1/3 the people emphasis bloger in propagating as this.This method is mainly concentrated and is found emphasis bloger in microblogging context of detection, and the microblogging that obtains emphasis bloger is related to colony, and the propagation diffusion path of an event is detected.It is more valuable that this preferred embodiment research finds that the microblogging data that collect round emphasis bloger and round can be than extensive collection, is more conducive to research.
Fig. 2 shows according to the schematic diagram of the public sentiment supervising device for microblogging of the embodiment of the present invention, comprising:
Determination module 10, for determining the source bloger of monitored microblogging;
Spider module 20, for the forwarding bloger from the monitored microblogging of source bloger's depth-first traversal;
Acquisition module 30, forwards bloger's bean vermicelli number and the hop count about monitored microblogging thereof for obtaining;
Module 40 is set, for the importance degree that forwards bloger being set according to its bean vermicelli number and hop count.
This device has reduced the difficulty of the analysis of public opinion, has improved the analysis of public opinion accuracy rate.
Preferably, determination module passes up to source bloger by the forward-path of monitored microblogging.
Preferably, spider module comprises: search module, find monitored microblogging for the microblogging space of the forwarding bloger from current; List block, for obtaining the forwarding list of monitored microblogging; List traversal module, for traveling through all forwarding blogers on forwarding list.
Preferably, module is set Weight=α * nFllower+ β * nRetweet is set; Wherein, weight represents importance degree, and nFllower represents bean vermicelli number, and α represents the default weight of nFllower, and nRetweet represents hop count, and β represents the default weight of nRetweet.
Preferably, this device also comprises: comparison module, for determining that its importance degree is greater than the forwarding bloger of preset value; Screening module, is set to emphasis bloger for definite forwarding bloger.
A preferred embodiment of the present invention builds acquisition system framework, and the process of taking is as follows:
1, the id of a popular microblogging w0 of input
2, gather the forwarding microblogging on the forward-path of this microblogging.The bloger's information getting is put into array a[i] in, i indicates i bloger.
3, traversal array a[i].Gather the microblogging that j bloger issues, the value of j is [0, i], and this bloger has a microblogging to forward w0 surely.Suppose that this microblogging is v0.Record the bean vermicelli number of bloger j at this.
4, get the forwarding list of microblogging v0 and forward number, repeating step 2.
In a microblogging public sentiment event diffusion, conventionally there is concentrated bursting point, the emphasis bloger that the bloger at bursting point place is this event.Emphasis bloger can determine in the following way.
In the process gathering at microblogging, good friend's number of obtaining bloger is with bean vermicelli number, by bean vermicelli number number can know bloger's influence power size, bean vermicelli number is more, bloger's influence power is larger, bean vermicelli number is fewer, bloger's influence power is less.If the bloger's who obtains bean vermicelli number is nFllower.In this bloger's microblogging, the relay number that source microblogging is relayed is again assumed to be nRetweet.So just can show that this bloger is a weighting multiplier value for the forwarding contribution of source microblogging, is made as weight.
Weight=α*nFllower+β*nRetweet
Just can calculate bloger's influence power by the size of weight.Wherein α ∈ [0,1], β ∈ [0,1], alpha+beta=1.
By such calculating, get the bloger that a collection of contribution margin is larger and join emphasis bloger set as emphasis bloger.
As can be seen from the above description, the present invention is according to microblogging network monitor personnel's needs, there is object, gather targetedly associated microblogging, and can gather the bloger colony being associated with certain event, analyze the differentiation that just can easily find the propagation trajectories of microblogging and propagate along propagation trajectories from the microblogging collecting.
Obviously, those skilled in the art should be understood that, above-mentioned of the present invention each module or each step can realize with general calculation element, they can concentrate on single calculation element, or be distributed on the network that multiple calculation elements form, alternatively, they can be realized with the executable program code of calculation element, thereby, they can be stored in memory storage and be carried out by calculation element, or they are made into respectively to each integrated circuit modules, or the multiple modules in them or step are made into single integrated circuit module to be realized.Like this, the present invention is not restricted to any specific hardware and software combination.
The foregoing is only the preferred embodiments of the present invention, be not limited to the present invention, for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any amendment of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.

Claims (10)

1. for a public sentiment method for supervising for microblogging, it is characterized in that, comprising:
Determine the source bloger of monitored microblogging;
From the forwarding bloger of monitored microblogging described in the bloger's depth-first traversal of described source;
Obtain described forwarding bloger's bean vermicelli number and the hop count about described monitored microblogging thereof;
Described forwarding bloger's importance degree is set according to bean vermicelli number described in it and described hop count.
2. method according to claim 1, is characterized in that, passes up to described source bloger by the forward-path of described monitored microblogging.
3. method according to claim 1, is characterized in that, comprises from the forwarding bloger of monitored microblogging described in the bloger's depth-first traversal of described source:
From current described forwarding bloger's microblogging space, find described monitored microblogging;
Obtain the forwarding list of described monitored microblogging;
Travel through all forwarding blogers on described forwarding list.
4. method according to claim 1, is characterized in that, the importance degree that described forwarding bloger is set according to bean vermicelli number described in it and described hop count comprises:
Weight=α * nFllower+ β * nRetweet is set;
Wherein, weight represents described importance degree, and nFllower represents described bean vermicelli number, and α represents the default weight of nFllower, and nRetweet represents described hop count, and β represents the default weight of nRetweet.
5. method according to claim 4, is characterized in that, also comprises:
Determine that its importance degree is greater than the described forwarding bloger of preset value;
Described definite forwarding bloger is set to emphasis bloger.
6. for a public sentiment supervising device for microblogging, it is characterized in that, comprising:
Determination module, for determining the source bloger of monitored microblogging;
Spider module, for the forwarding bloger from monitored microblogging described in the bloger's depth-first traversal of described source;
Acquisition module, for obtaining described forwarding bloger's bean vermicelli number and the hop count about described monitored microblogging thereof;
Module is set, for described forwarding bloger's importance degree is set according to bean vermicelli number described in it and described hop count.
7. device according to claim 6, is characterized in that, described determination module passes up to described source bloger by the forward-path of described monitored microblogging.
8. device according to claim 6, is characterized in that, described spider module comprises:
Search module, find described monitored microblogging for the microblogging space of the described forwarding bloger from current;
List block, for obtaining the forwarding list of described monitored microblogging;
List traversal module, for traveling through all forwarding blogers on described forwarding list.
9. device according to claim 6, is characterized in that, the described module that arranges arranges Weight=α * nFllower+ β * nRetweet; Wherein, weight represents described importance degree, and nFllower represents described bean vermicelli number, and α represents the default weight of nFllower, and nRetweet represents described hop count, and β represents the default weight of nRetweet.
10. device according to claim 9, is characterized in that, also comprises:
Comparison module, for determining that its importance degree is greater than the described forwarding bloger of preset value;
Screening module, is set to emphasis bloger for described definite forwarding bloger.
CN201210566545.XA 2012-12-24 2012-12-24 Public opinion monitoring method and device for microblog Pending CN103885993A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201210566545.XA CN103885993A (en) 2012-12-24 2012-12-24 Public opinion monitoring method and device for microblog

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201210566545.XA CN103885993A (en) 2012-12-24 2012-12-24 Public opinion monitoring method and device for microblog

Publications (1)

Publication Number Publication Date
CN103885993A true CN103885993A (en) 2014-06-25

Family

ID=50954888

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201210566545.XA Pending CN103885993A (en) 2012-12-24 2012-12-24 Public opinion monitoring method and device for microblog

Country Status (1)

Country Link
CN (1) CN103885993A (en)

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104092598A (en) * 2014-07-03 2014-10-08 厦门欣欣信息有限公司 Message propagation path extraction method and system
CN104954236A (en) * 2015-06-19 2015-09-30 百度在线网络技术(北京)有限公司 Method and device for generating information of propagation path for theme event
CN105447196A (en) * 2015-12-31 2016-03-30 深圳中泓在线股份有限公司 Key blogger tracking confirmation method and device
CN105701100A (en) * 2014-11-26 2016-06-22 上海高研明鉴信息技术有限公司 Automatic recording method, device and system of internet information forwarding process
CN106484846A (en) * 2016-09-30 2017-03-08 广州特道信息科技有限公司 A kind of monitoring method of network public-opinion big data
CN107222381A (en) * 2016-03-21 2017-09-29 北大方正集团有限公司 The propagation path of microblog data determines method and apparatus
CN108268662A (en) * 2018-02-09 2018-07-10 平安科技(深圳)有限公司 Social graph generation method, electronic device and storage medium based on the H5 pages
CN109508416A (en) * 2018-11-09 2019-03-22 四川大学 Microblogging public sentiment event temperature and prediction of the development trend method based on number of reviews
CN109670046A (en) * 2018-11-12 2019-04-23 平安科技(深圳)有限公司 A kind of public sentiment monitoring method, storage medium and terminal device
CN109948024A (en) * 2019-03-12 2019-06-28 安徽新华学院 A kind of public sentiment monitoring method and system based on microblogging

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102214212A (en) * 2011-05-20 2011-10-12 西北工业大学 Method for ordering microblog network node weights based on multi-link
CN102831130A (en) * 2011-06-16 2012-12-19 富士通株式会社 Device and method for publishing specific information on internet

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102214212A (en) * 2011-05-20 2011-10-12 西北工业大学 Method for ordering microblog network node weights based on multi-link
CN102831130A (en) * 2011-06-16 2012-12-19 富士通株式会社 Device and method for publishing specific information on internet

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
于洪 等: "微博中节点影响力度量与传播路径模式研究", 《通信学报》 *
熊小兵 等: "新浪微博话题流行度预测技术研究", 《信息工程大学学报》 *

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104092598A (en) * 2014-07-03 2014-10-08 厦门欣欣信息有限公司 Message propagation path extraction method and system
CN105701100B (en) * 2014-11-26 2019-07-12 上海高研明鉴信息技术有限公司 Internet information repeating process automatic record method, apparatus and system
CN105701100A (en) * 2014-11-26 2016-06-22 上海高研明鉴信息技术有限公司 Automatic recording method, device and system of internet information forwarding process
CN104954236B (en) * 2015-06-19 2018-02-27 百度在线网络技术(北京)有限公司 The method and apparatus of the information of the event that is the theme generation propagation path
CN104954236A (en) * 2015-06-19 2015-09-30 百度在线网络技术(北京)有限公司 Method and device for generating information of propagation path for theme event
CN105447196B (en) * 2015-12-31 2019-03-05 深圳中泓在线股份有限公司 A kind of emphasis bloger tracks confirmation method and device
CN105447196A (en) * 2015-12-31 2016-03-30 深圳中泓在线股份有限公司 Key blogger tracking confirmation method and device
CN107222381A (en) * 2016-03-21 2017-09-29 北大方正集团有限公司 The propagation path of microblog data determines method and apparatus
CN107222381B (en) * 2016-03-21 2020-03-06 北大方正集团有限公司 Microblog data propagation path determining method and device
CN106484846A (en) * 2016-09-30 2017-03-08 广州特道信息科技有限公司 A kind of monitoring method of network public-opinion big data
CN108268662A (en) * 2018-02-09 2018-07-10 平安科技(深圳)有限公司 Social graph generation method, electronic device and storage medium based on the H5 pages
WO2019153493A1 (en) * 2018-02-09 2019-08-15 平安科技(深圳)有限公司 H5 page-based social media map generation method, electronic device, and storage medium
CN108268662B (en) * 2018-02-09 2020-11-10 平安科技(深圳)有限公司 Social graph generation method based on H5 page, electronic device and storage medium
CN109508416A (en) * 2018-11-09 2019-03-22 四川大学 Microblogging public sentiment event temperature and prediction of the development trend method based on number of reviews
CN109508416B (en) * 2018-11-09 2021-11-23 四川大学 Microblog public sentiment event popularity and development trend prediction method based on comment quantity
CN109670046A (en) * 2018-11-12 2019-04-23 平安科技(深圳)有限公司 A kind of public sentiment monitoring method, storage medium and terminal device
CN109948024A (en) * 2019-03-12 2019-06-28 安徽新华学院 A kind of public sentiment monitoring method and system based on microblogging

Similar Documents

Publication Publication Date Title
CN103885993A (en) Public opinion monitoring method and device for microblog
CN104933093B (en) The monitoring of regional public sentiment and decision support system (DSS) based on big data and method
Ostermann et al. A conceptual workflow for automatically assessing the quality of volunteered geographic information for crisis management
Wang et al. Sample surveying to estimate the mean of a heterogeneous surface: reducing the error variance through zoning
Budak et al. Structural trend analysis for online social networks
CN103458042B (en) A kind of microblog advertisement user detection method
CN109829089A (en) Social network user method for detecting abnormality and system based on association map
CN104424231B (en) The processing method and processing device of multidimensional data
CN105426502A (en) Social network based person information search and relational network drawing method
Uddin et al. On diversifying source selection in social sensing
CN110362818A (en) Microblogging rumour detection method and system based on customer relationship structure feature
Ballatore Google chemtrails: A methodology to analyze topic representation in search engine results
TW201426360A (en) System and method of analysing text stream message
Saikia et al. Land-use/land-cover change and fragmentation in the Nameri Tiger Reserve, India
CN103812872A (en) Network water army behavior detection method and system based on mixed Dirichlet process
CN104216889B (en) Data dissemination analyzing and predicting method and system based on cloud service
CN104572757A (en) Microblog group processing method and device
CN103258027A (en) Context awareness service platform based on intelligent terminal
CN104408083A (en) Socialized media analyzing system
CN105095988A (en) Method and system for detecting social network information explosion
CN103440328B (en) A kind of user classification method based on mouse behavior
CN109597926A (en) A kind of information acquisition method and system based on social media emergency event
Zhao et al. Sportsense: Real-time detection of NFL game events from Twitter
CN104063456B (en) Based on vector query from broadcasting media atlas analysis method and apparatus
CN112765313B (en) False information detection method based on original text and comment information analysis algorithm

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

Application publication date: 20140625

RJ01 Rejection of invention patent application after publication