本文選題：微博網(wǎng)絡(luò)　切入點(diǎn)：隱馬爾科夫理論　出處：《華南理工大學(xué)》2014年碩士論文

【摘要】：隨著社交網(wǎng)絡(luò)的蓬勃發(fā)展，信息呈現(xiàn)爆炸式的增長，我們隨之步入了大數(shù)據(jù)時(shí)代。為了更好地挖掘社交網(wǎng)絡(luò)的潛在價(jià)值，眾多學(xué)者都對之進(jìn)行了各方面的研究。那么，如何充分地利用社交網(wǎng)絡(luò)中的信息并對之進(jìn)行有效地控制和引導(dǎo)？如何深入地了解信息的擴(kuò)散機(jī)制？如何正確預(yù)測社交網(wǎng)絡(luò)中的用戶行為？對之行之有效的一個(gè)研究方向就是構(gòu)建準(zhǔn)確、可解又唯美的信息擴(kuò)散模型。 微博(Micro-blog)，作為一種新型的社交網(wǎng)絡(luò)平臺，有傳統(tǒng)社交網(wǎng)絡(luò)的共性也有其個(gè)性。目前，有關(guān)微博網(wǎng)絡(luò)的信息擴(kuò)散模型研究，綜合考慮信息內(nèi)容、用戶及網(wǎng)絡(luò)結(jié)構(gòu)的研究屈指可數(shù)。再者，既考慮信息間的“競爭關(guān)系”又考慮“合作關(guān)系”，且基于統(tǒng)計(jì)概率的多信息擴(kuò)散模型則基本沒有。鑒于此，，本文提出了微博網(wǎng)絡(luò)中基于隱馬爾科夫理論的信息擴(kuò)散模型(IDMBHMT)和基于條件隨機(jī)場的多信息擴(kuò)散模型(MIDMBCRF)。 首先，本文綜合研究了微博網(wǎng)絡(luò)信息擴(kuò)散的特點(diǎn)及影響因素、隱馬爾科夫理論、條件隨機(jī)場理論以及本文相關(guān)的特征函數(shù)定義方法（自動中文文本分類、用戶相似度度量以及多信息交互的量化方法），構(gòu)建了微博網(wǎng)絡(luò)中基于隱馬爾科夫理論的信息擴(kuò)散模型(IDMBHMT)和基于條件隨機(jī)場的多信息擴(kuò)散模型(MIDMBCRF)；其次，本文使用METIS工具對微博用戶關(guān)系網(wǎng)絡(luò)進(jìn)行子圖劃分，并基于子圖進(jìn)行模型的構(gòu)建，以此優(yōu)化模型的性能；再者，本文使用Junction tree算法將模型應(yīng)用于用戶的轉(zhuǎn)發(fā)行為預(yù)測；最后，使用新浪微博API(Application Programming Interface)抓取實(shí)驗(yàn)數(shù)據(jù)進(jìn)行仿真實(shí)驗(yàn)。 實(shí)驗(yàn)分析了兩個(gè)模型的性能影響因素：圖劃分技術(shù)提高了模型的性能，且當(dāng)子圖規(guī)模為48時(shí)，兩個(gè)模型的性能達(dá)到峰值；“多信息交互”以平均43%的概率對MIDMBCRF模型的轉(zhuǎn)發(fā)概率產(chǎn)生影響。在網(wǎng)絡(luò)規(guī)模分別為120、240和400的情況下，將IDMBHMT模型及MIDMBCRF模型分別與基于邏輯回歸的轉(zhuǎn)發(fā)行為預(yù)測模型(RPMBLR)及基于LT(Linear-Threshold)的多信息擴(kuò)散模型(MIDMBLT)進(jìn)行性能對比，四個(gè)模型的性能由高到低排序?yàn)椋篗IDMBCRF、IDMBHMT、RPMBLR、MIDMBLT。 本文所構(gòu)建的兩個(gè)信息擴(kuò)散模型，不僅可以應(yīng)用于用戶行為預(yù)測和輿論引導(dǎo)，而且其研究成果對其他相關(guān)學(xué)科研究存在借鑒意義。
[Abstract]:With the vigorous development of social network and the explosive growth of information, we have stepped into the era of big data. In order to better tap the potential value of social network, many scholars have studied it in all aspects. How to make full use of the information in the social network and effectively control and guide it? How to understand the diffusion mechanism of information in depth? How to correctly predict the behavior of users in social networks? An effective research direction is to build an accurate, solvable and beautiful information diffusion model. Weibo, as a new type of social network platform, has both the commonness and individuality of traditional social networks. There are few studies on users and network structure. Furthermore, both the "competition" and "cooperation" among information are considered, and the multi-information diffusion model based on statistical probability is largely absent. In this paper, an information diffusion model based on hidden Markov theory (IDMBHMT) and a multi-information diffusion model based on conditional random field (CRF) in Weibo network are proposed. First of all, this paper synthetically studies the characteristics of Weibo network information diffusion and its influencing factors, hidden Markov theory, conditional random field theory and the definition method of feature function (automatic Chinese text categorization). Based on the user similarity measurement and the quantization method of multi-information interaction, the information diffusion model (IDMBHMT) based on hidden Markov theory and the multi-information diffusion model based on conditional random field (CRF) in Weibo network are constructed. In this paper, we use METIS tools to partition Weibo user relationship network subgraph, and build the model based on sub-graph to optimize the performance of the model. Furthermore, this paper uses Junction tree algorithm to apply the model to user forwarding behavior prediction. Using Sina Weibo API(Application Programming Interface to capture experimental data for simulation experiments. The performance factors of the two models are analyzed experimentally. The graph partition technique improves the performance of the model, and when the size of the subgraph is 48, The performance of the two models has reached a peak. The average probability of "multi-information interaction" affects the forwarding probability of the MIDMBCRF model with an average probability of 43%. When the network size is 120240 and 400, respectively, The IDMBHMT model and the MIDMBCRF model are compared with the forward behavior prediction model (RPMBLR) based on logical regression and the multi-information diffusion model (MIDMBT) based on LTL Linear-Threshold. the performance of the four models is ranked from high to low to:: MIDMBCR / MIDMBLT. The two information diffusion models constructed in this paper can not only be applied to user behavior prediction and public opinion guidance, but also can be used for reference in other related disciplines.
【學(xué)位授予單位】：華南理工大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2014
【分類號】：TP393.092

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 王洋;西寶;;評估危機(jī)信息傳播有效性的模糊人工神經(jīng)網(wǎng)絡(luò)方法[J];哈爾濱工程大學(xué)學(xué)報(bào);2010年08期

2 許曉東;肖銀濤;朱士瑞;;微博社區(qū)的謠言傳播仿真研究[J];計(jì)算機(jī)工程;2011年10期

3 陳琳;王箭;;三種中文文本自動分類算法的比較和研究[J];計(jì)算機(jī)與現(xiàn)代化;2012年02期

4 李棟;徐志明;李生;劉挺;王秀文;;在線社會網(wǎng)絡(luò)中信息擴(kuò)散[J];計(jì)算機(jī)學(xué)報(bào);2014年01期

5 徐志明;李棟;劉挺;李生;王剛;袁樹侖;;微博用戶的相似性度量及其應(yīng)用[J];計(jì)算機(jī)學(xué)報(bào);2014年01期

6 陳慧娟;鄭嘯;陳欣;;微博網(wǎng)絡(luò)信息傳播研究綜述[J];計(jì)算機(jī)應(yīng)用研究;2014年02期

7 史文國;王瑜;;移動社會網(wǎng)絡(luò)信息傳播模型構(gòu)建與top-k節(jié)點(diǎn)挖掘[J];計(jì)算機(jī)應(yīng)用研究;2012年08期

8 王萍;;社會化網(wǎng)絡(luò)的信息擴(kuò)散研究[J];情報(bào)雜志;2009年10期

9 周苗苗;許成;劉曉波;;社會網(wǎng)絡(luò)上的謠言傳播模型[J];青島大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年04期

10 鄭蕾;李生紅;;基于微博網(wǎng)絡(luò)的信息傳播模型[J];通信技術(shù);2012年02期

本文編號：1686247