發(fā)布時(shí)間：2019-06-17 12:34

【摘要】：隨著互聯(lián)網(wǎng)技術(shù)以及信息傳播技術(shù)的飛速發(fā)展,基于web2.0平臺(tái)的微博等開放互聯(lián)網(wǎng)社交服務(wù)模式越來(lái)越流行。在微博平臺(tái)中,人人都像媒體一樣可以自由發(fā)表感受和見解。近年來(lái),基于微博的數(shù)據(jù)挖掘相關(guān)研究越來(lái)越多,本文通過(guò)構(gòu)建微博用戶興趣模型,針對(duì)用戶在微博平臺(tái)發(fā)布的海量數(shù)據(jù),挖掘能揭示用戶興趣點(diǎn)的關(guān)鍵主題詞,并根據(jù)挖掘結(jié)果進(jìn)一步深入探討了如何實(shí)現(xiàn)個(gè)性化的廣告推薦,從而幫助廣告主們降低廣告成本,提升廣告的投放效果。 本文對(duì)如何利用微博數(shù)據(jù)對(duì)用戶興趣進(jìn)行分析,以及實(shí)現(xiàn)個(gè)性化廣告推薦的方法和形式進(jìn)行了研究和探索。與該領(lǐng)域已有的研究工作相比,本文主要有以下幾點(diǎn)不同： 首先,對(duì)不同的主題模型進(jìn)行分析,比較了TwitterRank、Author-Topic和TwitterLDA三種主題模型在構(gòu)建微博用戶興趣模型方面的性能,結(jié)合本文的研究?jī)?nèi)容,選擇采用TwitterLDA模型進(jìn)行新浪微博用戶的興趣識(shí)別。 其次,將目前已有的改進(jìn)后的LDA算法應(yīng)用于微博用戶主題詞的挖掘,通過(guò)分析主題結(jié)構(gòu)(topic structure)里的后驗(yàn)概率,來(lái)找出了能夠表達(dá)主題含義的短語(yǔ)。改進(jìn)后的算法既能保留傳統(tǒng)LDA模型調(diào)換詞序?qū)χ黝}挖掘結(jié)果沒有影響的特點(diǎn),同時(shí)還能使算法變得更高效,并獲得了能表示主題含義的n-gram短語(yǔ)。 最后,提出在微博個(gè)性化廣告推薦的各種廣告形式中融合故事型廣告的創(chuàng)新模式并設(shè)計(jì)了以新浪微博普通用戶為例的實(shí)證調(diào)研。最終通過(guò)對(duì)調(diào)研結(jié)果進(jìn)行分析,驗(yàn)證了論文中使用的主題模型在普通微博用戶中進(jìn)行興趣挖掘的可行性及有效性,并簡(jiǎn)單地就故事型廣告的創(chuàng)新形式接納度和興趣模型的有效性進(jìn)行了調(diào)研評(píng)估。 通過(guò)本文的研究,可以發(fā)現(xiàn),微博用戶的行為和興趣之間有很強(qiáng)的關(guān)聯(lián)性,尤其是發(fā)布行為、轉(zhuǎn)發(fā)行為和評(píng)論行為這三種主要行為�；谖⒉┯脩襞d趣模型的個(gè)性化廣告推薦研究能夠分析微博用戶的興趣并進(jìn)行精準(zhǔn)的廣告投放,降低廣告成本,提高廣告收益,帶來(lái)更好的經(jīng)濟(jì)及社會(huì)效益。
[Abstract]:With the rapid development of Internet technology and information communication technology, open Internet social service models such as Weibo based on web2.0 platform are becoming more and more popular. In the Weibo platform, everyone is as free to express their feelings and opinions as the media. In recent years, there are more and more research on data mining based on Weibo. This paper constructs Weibo user interest model, mining the key subject words that can reveal the points of interest of users, and further discusses how to realize personalized advertising recommendation according to the mining results, so as to help advertisers reduce the cost of advertising and improve the effect of advertising. This paper studies and explores how to use Weibo data to analyze user interest and how to realize personalized advertising recommendation. Compared with the existing research work in this field, this paper mainly has the following differences: firstly, the different topic models are analyzed, and the performance of TwitterRank,Author-Topic and TwitterLDA in building Weibo user interest model is compared. combined with the research content of this paper, the TwitterLDA model is selected to identify the interest of Sina Weibo users. Secondly, the improved LDA algorithm is applied to the mining of topic words of Weibo users. By analyzing the posterior probability in the topic structure (topic structure), the phrases that can express the meaning of the topic are found out. The improved algorithm can not only preserve the characteristic that the traditional LDA model changing word order has no effect on the topic mining results, but also make the algorithm more efficient, and obtain the n-gram phrase which can express the meaning of the topic. Finally, this paper puts forward the innovative mode of integrating story-based advertising into various advertising forms recommended by Weibo personalized advertising, and designs an empirical investigation with Sina Weibo ordinary users as an example. Finally, through the analysis of the research results, the feasibility and effectiveness of the topic model used in this paper in interest mining among ordinary Weibo users are verified, and the innovative form acceptance of story advertising and the effectiveness of interest model are simply investigated and evaluated. Through the study of this paper, we can find that there is a strong correlation between the behavior and interest of Weibo users, especially the three main behaviors: publishing behavior, forwarding behavior and comment behavior. The personalized advertising recommendation research based on Weibo user interest model can analyze the interests of Weibo users and carry out accurate advertising, reduce advertising costs, improve advertising revenue, and bring better economic and social benefits.
【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】：2014
【分類號(hào)】：G358;F713.8

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 陳倩;;微博廣告發(fā)展現(xiàn)狀與傳播效果分析[J];產(chǎn)業(yè)與科技論壇;2012年02期

2 于洪波;;中文分詞技術(shù)研究[J];東莞理工學(xué)院學(xué)報(bào);2010年05期

3 陳淵;林磊;孫承杰;劉秉權(quán);;一種面向微博用戶的標(biāo)簽推薦方法[J];智能計(jì)算機(jī)與應(yīng)用;2011年05期

4 葉欣;王文軒;;植入式廣告運(yùn)作策略的思考[J];大市場(chǎng).廣告導(dǎo)報(bào);2006年08期

5 孫鐵利;劉延吉;;中文分詞技術(shù)的研究現(xiàn)狀與困難[J];信息技術(shù);2009年07期

6 賈西平;彭宏;鄭啟倫;石時(shí)需;江焯林;;基于主題的文檔檢索模型[J];華南理工大學(xué)學(xué)報(bào)(自然科學(xué)版);2008年09期

7 林鴻飛,楊元生;用戶興趣模型的表示和更新機(jī)制[J];計(jì)算機(jī)研究與發(fā)展;2002年07期

8 宋麗哲;牛振東;余正濤;宋瀚濤;董祥軍;;一種基于混合模型的用戶興趣漂移方法[J];計(jì)算機(jī)工程;2006年01期

9 陳一峰;趙恒凱;余小清;萬(wàn)旺根;;基于本體的用戶興趣模型構(gòu)建研究[J];計(jì)算機(jī)工程;2010年21期

10 黃小亮;郁抒思;關(guān)佶紅;;基于LDA主題模型的軟件缺陷分派方法[J];計(jì)算機(jī)工程;2011年21期

，

本文編號(hào)：2500992