發(fā)布時間：2018-04-02 13:10

  本文選題：微博　切入點(diǎn)：熱點(diǎn)事件　出處：《西南大學(xué)》2017年碩士論文

【摘要】：在微博平臺上,涉及生活、人際交往等各種信息以前所未有的速度增長,并呈幾何級增長式傳播。社會上許多突發(fā)性話題,往往在微博平臺上首發(fā),并快速傳播,迅速成為熱點(diǎn),引起廣泛的社會共鳴,進(jìn)而波及傳統(tǒng)媒體,產(chǎn)生巨大的社會影響。微博平臺上的熱點(diǎn)事件檢測技術(shù),對于最新社會熱點(diǎn)發(fā)現(xiàn)、網(wǎng)絡(luò)民意及時感知、輿情檢測、應(yīng)急處理等方面都具有積極的現(xiàn)實(shí)意義。用戶通過微博平臺對熱點(diǎn)事件表達(dá)自己的觀點(diǎn)和抒發(fā)自己的情感,互相交流討論,形成了海量情感文本信息,通過對這些情感文本信息進(jìn)行分析處理,可以挖掘出其背后隱藏的有價值信息。本文對現(xiàn)有關(guān)于微博熱點(diǎn)事件檢測和情感分析的研究進(jìn)行分析,指出了微博上進(jìn)行相關(guān)研究所遇到的問題,其一是利用微博標(biāo)簽屬性建模來獲取熱點(diǎn)事件時,對不含標(biāo)簽的微博文本處理和子事件檢測問題;其二是微博情感分析中網(wǎng)絡(luò)流行語獲取和其情感極性判定的問題。在此基礎(chǔ)上,本文提出了TH-LDA模型來解決微博熱點(diǎn)事件檢測,基于詞典和網(wǎng)絡(luò)流行語情感極性特征的情感分析方法,研究工作主要包含以下內(nèi)容:(1)提出了TH-LDA模型,將微博中可用于檢測和分析微博文本主題的話題標(biāo)簽(Hashtag)、時間因素(Time)與主題模型LDA相結(jié)合,實(shí)現(xiàn)熱點(diǎn)事件檢測,利用此模型對同屬于一個熱點(diǎn)事件的不含標(biāo)簽的微博文本進(jìn)行檢索,得到更為全面的同一熱點(diǎn)事件的微博文本集合,同時實(shí)現(xiàn)熱點(diǎn)事件中子事件的檢測,進(jìn)而能夠更好地對事件的演化發(fā)展進(jìn)行追蹤。(2)提出了網(wǎng)絡(luò)流行語過濾規(guī)則(Network Catchwords Filter Rule,簡稱NCF規(guī)則)來構(gòu)建網(wǎng)絡(luò)流行語詞典和網(wǎng)絡(luò)流行語情感詞典。根據(jù)網(wǎng)絡(luò)流行語詞典獲取微博文本中的網(wǎng)絡(luò)流行語,利用網(wǎng)絡(luò)流行語情感詞典對網(wǎng)絡(luò)流行語的情感極性進(jìn)行判定。(3)實(shí)現(xiàn)微博的情感分析。結(jié)合已構(gòu)建的基礎(chǔ)情感詞典、表情符號詞典和網(wǎng)絡(luò)流行語情感詞典,并融合網(wǎng)絡(luò)流行語的情感極性特征對微博情感極性進(jìn)行判定。實(shí)驗(yàn)結(jié)果表明,TH-LDA模型能夠更準(zhǔn)確地獲取同一事件中不含標(biāo)簽的微博文本信息,實(shí)現(xiàn)了熱點(diǎn)事件中子事件的檢測,也能更好地追蹤熱點(diǎn)事件演化發(fā)展;NCF規(guī)則能夠構(gòu)建較完善的網(wǎng)絡(luò)流行語詞典,網(wǎng)絡(luò)流行語的情感極性特征對微博的情感極性判定起到了很好的矯正作用,實(shí)驗(yàn)驗(yàn)證了該方法的有效性。
[Abstract]:On the platform of Weibo, all kinds of information, such as life and interpersonal communication, are growing at an unprecedented speed, and spread in a geometric growth mode.Many sudden social topics often start on the platform of Weibo and spread rapidly, which quickly become a hot spot, and cause widespread social resonance, and then spread to traditional media, which has a huge social impact.The hot spot detection technology on Weibo platform has positive practical significance for the newest social hot spot discovery, the network public opinion timely perception, the public opinion detection, the emergency treatment and so on.Through Weibo platform, users express their views and express their feelings on hot issues, exchange and discuss with each other, forming a vast amount of emotional text information, through the analysis and processing of these emotional text information,You can dig out the valuable information hidden behind it.This paper analyzes the existing research on Weibo hot spot event detection and emotion analysis, and points out the problems encountered in the relevant research on Weibo.This paper deals with the text processing and sub-event detection of Weibo without tags, and the acquisition of network catchwords and the determination of emotional polarity in the affective analysis of Weibo.On this basis, this paper puts forward the TH-LDA model to solve the hot spot event detection of Weibo. Based on the emotional polarity characteristics of dictionaries and network catchwords, the research work mainly includes the following contents: 1) put forward the TH-LDA model.This paper combines Weibo's topic tag, which can be used to detect and analyze the theme of Weibo's text, with the theme model LDA to detect hot events.By using this model, the text of Weibo, which belongs to the same hot event, is retrieved without label, and then a more comprehensive set of Weibo texts of the same hot event is obtained, and the neutron event detection of the hot event is realized at the same time.Furthermore, it can better track the evolution and development of events. (2) this paper puts forward the network Catchwords Filter rule (NCF rule) to construct the network catchword dictionary and the network catchword emotion dictionary.According to the network catchword dictionary to obtain the network catchwords in Weibo's text, the emotion dictionary of network pop language is used to judge the emotional polarity of network buzzwords.Combined with the basic emotion dictionary, emoji dictionary and network pop language dictionary, and combined with the emotional polarity characteristics of the network catchword, Weibo's emotional polarity was judged.The experimental results show that the TH-LDA model can more accurately obtain the text information of Weibo with no label in the same event, and realize the detection of neutron events of hot events.It can also better track the evolution of hot events. NCF rules can build a more perfect dictionary of popular words on the Internet. The emotional polarity characteristics of network catchwords play a good role in correcting Weibo's judgment of emotional polarity.The effectiveness of the method is verified by experiments.
【學(xué)位授予單位】：西南大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：TP391.1;TP393.092

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 賀敏;杜攀;張瑾;劉悅;程學(xué)旗;;基于動量模型的微博突發(fā)話題檢測方法[J];計(jì)算機(jī)研究與發(fā)展;2015年05期

2 黃挺;姬東鴻;;基于圖模型和多分類器的微博情感傾向性分析[J];計(jì)算機(jī)工程;2015年04期

3 申國偉;楊武;王巍;于淼;;面向大規(guī)模微博消息流的突發(fā)話題檢測[J];計(jì)算機(jī)研究與發(fā)展;2015年02期

4 李婷婷;姬東鴻;;基于SVM和CRF多特征組合的微博情感分析[J];計(jì)算機(jī)應(yīng)用研究;2015年04期

5 曹玖新;吳江林;石偉;劉波;鄭嘯;羅軍舟;;新浪微博網(wǎng)信息傳播分析與預(yù)測[J];計(jì)算機(jī)學(xué)報;2014年04期

6 王志濤;於志文;郭斌;路新江;;基于詞典和規(guī)則集的中文微博情感分析[J];計(jì)算機(jī)工程與應(yīng)用;2015年08期

7 張珊;于留寶;胡長軍;;基于表情圖片與情感詞的中文微博情感分析[J];計(jì)算機(jī)科學(xué);2012年S3期

8 張晨逸;孫建伶;丁軼群;;基于MB-LDA模型的微博主題挖掘[J];計(jì)算機(jī)研究與發(fā)展;2011年10期

9 閆幸;常亞平;;微博研究綜述[J];情報雜志;2011年09期

10 龍樹全;趙正文;唐華;;中文分詞算法概述[J];電腦知識與技術(shù);2009年10期

相關(guān)博士學(xué)位論文 前3條

1 劉楠;面向微博短文本的情感分析研究[D];武漢大學(xué);2013年

2 崔安頎;微博熱點(diǎn)事件的公眾情感分析研究[D];清華大學(xué);2013年

3 田野;基于微博平臺的事件趨勢分析及預(yù)測研究[D];武漢大學(xué);2012年

相關(guān)碩士學(xué)位論文 前3條

1 高巖;微博情感分析的相關(guān)技術(shù)研究[D];華北電力大學(xué);2014年

2 樊小超;基于機(jī)器學(xué)習(xí)的中文文本主題分類及情感分類研究[D];南京理工大學(xué);2014年

3 蔣斌;基于停用詞處理的漢語語音檢索方法[D];哈爾濱工業(yè)大學(xué);2008年

，

本文編號：1700528