本文關(guān)鍵詞：基于用戶行為特征及關(guān)系的在線社交網(wǎng)絡(luò)信息傳播研究與建模　出處：《華東師范大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 在線社交網(wǎng)絡(luò) 用戶行為 信息傳播 雙層網(wǎng)絡(luò)模型 傳播影響力

【摘要】：迅猛發(fā)展的在線社交網(wǎng)絡(luò)已經(jīng)成為人們獲取和分享信息的重要平臺(tái),極大改變了人類社會(huì)的信息傳播方式,在線社交網(wǎng)絡(luò)上的信息傳播也是近年來研究者們關(guān)注的熱點(diǎn)。然而現(xiàn)有的研究成果雖然取得了一定成功,但依然存在以下問題:1)受限于實(shí)際數(shù)據(jù)的缺失,信息傳播建模往往基于靜態(tài)網(wǎng)絡(luò),依賴于用戶接觸和傳播信息概率均等、用戶行為相對(duì)靜態(tài)等基本假設(shè),難以描述真實(shí)信息傳播中的復(fù)雜現(xiàn)象。2)隨著近年來信息內(nèi)容的復(fù)雜性和個(gè)體行為的多樣性,用戶具體通過哪些行為使信息得以傳播、如何準(zhǔn)確衡量用戶的影響力和傳播效率等問題,依然沒有得到普遍認(rèn)同的解釋。圍繞這些問題,本文利用大數(shù)據(jù)分析手段挖掘Twitter數(shù)據(jù),基于用戶行為特征的研究,對(duì)在線社交網(wǎng)絡(luò)中信息傳播過程進(jìn)行了系統(tǒng)描述和動(dòng)態(tài)建模分析。本文的主要研究成果和學(xué)術(shù)貢獻(xiàn)如下:1)分析了在線社交網(wǎng)絡(luò)中特有的用戶行為特征,討論了用戶傳播影響力的相關(guān)因素和評(píng)價(jià)方法。本文采集并利用了 Twitter平臺(tái)的信息數(shù)據(jù)和相關(guān)用戶數(shù)據(jù),基于用戶的信息轉(zhuǎn)發(fā)行為構(gòu)建了信息傳播網(wǎng)絡(luò),分析了其網(wǎng)絡(luò)拓?fù)浣Y(jié)構(gòu)性質(zhì)和度分布,引入了基于用戶發(fā)布或轉(zhuǎn)發(fā)信息數(shù)量的用戶活躍度指標(biāo),提出了基于等待時(shí)間和時(shí)間間隔的用戶積極度和用戶持續(xù)度指標(biāo),將轉(zhuǎn)發(fā)數(shù)量作為傳播影響力的評(píng)價(jià)指標(biāo),發(fā)現(xiàn)了用戶活躍度難以和用戶的信息傳播影響力掛鉤,而高用戶積極度和持續(xù)度則是獲得出色信息傳播影響力的必要條件,發(fā)現(xiàn)了用戶行為特征存在社區(qū)性和群體性差異。2)利用Fast-unfolding社團(tuán)劃分的方法,研究了在線社交網(wǎng)絡(luò)中用戶行為特征的社區(qū)性,解釋了網(wǎng)絡(luò)中的信息傳播機(jī)制�；贔ast-unfolding算法對(duì)Twitter信息傳播網(wǎng)絡(luò)進(jìn)行了社團(tuán)劃分,驗(yàn)證了用戶行為具有社區(qū)特性。隨后挖掘了用戶的行為特征社區(qū)性的深層作用,發(fā)現(xiàn)了信息傳播過程中的信息創(chuàng)造者、傳播促進(jìn)者、傳播支持者和信息消費(fèi)者這四類群體,并描述了他們的行為特征和先后發(fā)揮的創(chuàng)造話題、引發(fā)傳播潮流、擴(kuò)散傳播以及終結(jié)傳播的作用。3)提出了基于信息流行度和用戶關(guān)系的動(dòng)態(tài)信息傳播模型。不同于傳統(tǒng)的靜態(tài)網(wǎng)絡(luò)模型或仿真模型,本文提出了一種雙層動(dòng)態(tài)網(wǎng)絡(luò)信息傳播模型。通過隨時(shí)間變化的發(fā)布信息構(gòu)建了信息云網(wǎng)絡(luò),通過用戶的關(guān)注關(guān)系構(gòu)建了用戶關(guān)系網(wǎng)絡(luò)。綜合考慮信息流行度、信息時(shí)效性和用戶關(guān)系的影響,通過權(quán)重參數(shù)來衡量各因素的影響比例,動(dòng)態(tài)計(jì)算了某個(gè)用戶在某時(shí)對(duì)于某條信息的轉(zhuǎn)發(fā)概率,實(shí)現(xiàn)了雙層網(wǎng)絡(luò)之間的動(dòng)態(tài)聯(lián)系,根據(jù)發(fā)布信息隨時(shí)間的變化情況演化了信息轉(zhuǎn)發(fā)的整個(gè)過程。最后,基于Twitter的信息發(fā)布、轉(zhuǎn)發(fā)和用戶關(guān)注數(shù)據(jù)檢驗(yàn)了模型的可行性和結(jié)果的準(zhǔn)確性,討論了權(quán)重參數(shù)的最優(yōu)取值,模型準(zhǔn)確解釋了流行度和用戶關(guān)系在信息傳播中的動(dòng)態(tài)共同作用關(guān)系,可以用于在線社交網(wǎng)絡(luò)的信息傳播描述和預(yù)測(cè)。
[Abstract]:The rapid development of online social network has become an important platform for people to obtain and share information, greatly changed the human society of information dissemination, information dissemination focus on online social networks is also concerned by researchers in recent years. However, the existing research results have achieved some success, but there are still the following problems: 1) deletion limited by the actual data, the dissemination of information modeling are often based on the static network, depending on the user contact and dissemination of information equal probability, the basic hypothesis of user behavior is relatively static, it is difficult to describe the complex phenomena in the real.2 in information communication) with complex information content in recent years and individual behavior, through which the user specific behavior information spread, influence and spread efficiency issues such as how to accurately measure the user, still has not been generally accepted around these explanation. In this paper, using a large data analysis method of Twitter data mining, the research of user behavior feature based on the information dissemination process of online social networks is described and the dynamic modeling system. The main research results and contributions are as follows: 1) analyze the user behavior features of online social networks, discussed the related factors the user influence and evaluation methods. The acquisition and use of information data of the Twitter platform and the relevant user data, construct the information communication network based on the forwarding behavior of user information, analyzes the network topology properties and degree distribution, introduces the activity index of user number of user information published or forwarded based on the wait time and time interval of the user and the user continued positive degree index based on forward evaluation index number as the spread of the influence of the hair The user activity and information dissemination to hook the influence of users, and users of high product and duration is extremely necessary to obtain excellent information spreading influence, found the characteristics of user behavior in community and group differences of.2) by Fast-unfolding community division method, community study of user behavior in online social networks in the feature, explains the information dissemination mechanism in the network. The Fast-unfolding algorithm is partition of Twitter information transmission network based on the verified user behavior has the community characteristics. Then the effect of behavioral characteristics of deep mining community households, found in the process of information transmission and information dissemination of creators, promoters, supporters and communication these four types of information consumer groups, and describe their behavior characteristics and has the creativity of the topic, lead to the spread of the trend, the spread of the spread And the end of transmission of the.3) put forward the dynamic information model of information dissemination of popularity and user relationship. Based on static network model or simulation model is different from the traditional, this paper proposes a two-layer dynamic network information dissemination model. By changing with time release information to construct the information cloud network, through the user's attention to relationship building the user relationship network. Considering the popularity of information, information timeliness and customer relationship, through the weight parameters to measure the effect of each factor proportion, dynamic calculation of a user at a time for a forwarding probability information, realizes the dynamic relationship between the double network, according to the release of information changes with time the evolution of information forwarding of the whole process. Finally, the Twitter based information release, user data forwarding and attention to test the feasibility and accuracy of the results of the model The optimal selection of weight parameters is discussed. The model accurately explains the dynamic interaction between popularity and user relationship in information dissemination, and it can be used for information propagation description and prediction in online social networks.

【學(xué)位授予單位】：華東師范大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：G206;TP393.09

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 Bruce Antelman;李雯;;社交網(wǎng)絡(luò)[J];高校圖書館工作;2008年01期

2 ;基于位置的手機(jī)社交網(wǎng)絡(luò)“貝多”正式發(fā)布[J];中國(guó)新通信;2008年06期

3 曹增輝;;社交網(wǎng)絡(luò)更偏向于用戶工具[J];信息網(wǎng)絡(luò);2009年11期

4 ;美國(guó):印刷企業(yè)青睞社交網(wǎng)絡(luò)營(yíng)銷新方式[J];中國(guó)包裝工業(yè);2010年Z1期

5 李智惠;柳承燁;;韓國(guó)移動(dòng)社交網(wǎng)絡(luò)服務(wù)的類型分析與促進(jìn)方案[J];現(xiàn)代傳播(中國(guó)傳媒大學(xué)學(xué)報(bào));2010年08期

6 賈富;;改變一切的社交網(wǎng)絡(luò)[J];互聯(lián)網(wǎng)天地;2011年04期

7 譚拯;;社交網(wǎng)絡(luò):連接與發(fā)現(xiàn)[J];廣東通信技術(shù);2011年07期

8 陳一舟;;社交網(wǎng)絡(luò)的發(fā)展趨勢(shì)[J];傳媒;2011年12期

9 殷樂;;全球社交網(wǎng)絡(luò)新態(tài)勢(shì)及文化影響[J];新聞與寫作;2012年01期

10 許麗;;社交網(wǎng)絡(luò):孤獨(dú)年代的集體狂歡[J];上海信息化;2012年09期

相關(guān)會(huì)議論文 前10條

1 趙云龍;李艷兵;;社交網(wǎng)絡(luò)用戶的人格預(yù)測(cè)與關(guān)系強(qiáng)度研究[A];第七屆（2012）中國(guó)管理學(xué)年會(huì)商務(wù)智能分會(huì)場(chǎng)論文集（選編）[C];2012年

2 宮廣宇;李開軍;;對(duì)社交網(wǎng)絡(luò)中信息傳播的分析和思考——以人人網(wǎng)為例[A];首屆華中地區(qū)新聞與傳播學(xué)科研究生學(xué)術(shù)論壇獲獎(jiǎng)?wù)撐腫C];2010年

3 楊子鵬;喬麗娟;王夢(mèng)思;楊雪迎;孟子冰;張禹;;社交網(wǎng)絡(luò)與大學(xué)生焦慮緩解[A];心理學(xué)與創(chuàng)新能力提升——第十六屆全國(guó)心理學(xué)學(xué)術(shù)會(huì)議論文集[C];2013年

4 畢雪梅;;體育虛擬社區(qū)中的體育社交網(wǎng)絡(luò)解析[A];第九屆全國(guó)體育科學(xué)大會(huì)論文摘要匯編(4)[C];2011年

5 杜p，

本文編號(hào)：1376434