社區(qū)熱點(diǎn)微博推薦研究
發(fā)布時(shí)間：2018-11-21 14:54
【摘要】：分析并總結(jié)了影響用戶對(duì)特定微博興趣的若干因素,在此基礎(chǔ)上基于潛在因素模型提出了1個(gè)融合顯式特征和潛在特征的社區(qū)熱點(diǎn)微博推薦算法(community micro-blog recommendation,CMR),并將其用于發(fā)現(xiàn)微博興趣社區(qū)熱點(diǎn)信息.算法在3個(gè)興趣社區(qū)上進(jìn)行了實(shí)驗(yàn),結(jié)果表明:1)融合2種特征信息的微博推薦效果好于使用單一特征信息的推薦;2)CMR的推薦效果好于基于轉(zhuǎn)發(fā)次數(shù)的對(duì)照實(shí)驗(yàn)(micro-blog repost rank based recommendation,MRR);3)通過(guò)分析各個(gè)算法所推薦的微博內(nèi)容,發(fā)現(xiàn)CMR傾向于為用戶推薦興趣社區(qū)相關(guān)微博,而MRR傾向于為用戶推薦公共熱點(diǎn)微博.
[Abstract]:This paper analyzes and summarizes some factors that affect users' interest in specific Weibo. Based on the model of potential factors, a community hot spot Weibo recommendation algorithm (community micro-blog recommendation,CMR) is proposed, which combines explicit and potential features. And use it to discover Weibo interest community hot spot information. The algorithm is tested in three communities of interest. The results show that: 1) the recommended effect of Weibo with two kinds of feature information is better than that with single feature information; 2) the recommendation effect of CMR is better than that of micro-blog repost rank based recommendation,MRR; 3) by analyzing Weibo content recommended by various algorithms, it is found that CMR tends to recommend community of interest to users, while MRR tends to recommend common hot spot Weibo for users.
【作者單位】： 中國(guó)科學(xué)院軟件研究所基礎(chǔ)軟件國(guó)家工程研究中心;計(jì)算機(jī)科學(xué)國(guó)家重點(diǎn)實(shí)驗(yàn)室(中國(guó)科學(xué)院軟件研究所);
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(61433015,61272324) 國(guó)家“八六三”高技術(shù)研究發(fā)展計(jì)劃基金項(xiàng)目(2015AA015405) 網(wǎng)絡(luò)文化與數(shù)字傳播北京市重點(diǎn)實(shí)驗(yàn)室開放課題(ICDD201204)
【分類號(hào)】：TP391.3;TP393.092
本文編號(hào)：2347305
[Abstract]:This paper analyzes and summarizes some factors that affect users' interest in specific Weibo. Based on the model of potential factors, a community hot spot Weibo recommendation algorithm (community micro-blog recommendation,CMR) is proposed, which combines explicit and potential features. And use it to discover Weibo interest community hot spot information. The algorithm is tested in three communities of interest. The results show that: 1) the recommended effect of Weibo with two kinds of feature information is better than that with single feature information; 2) the recommendation effect of CMR is better than that of micro-blog repost rank based recommendation,MRR; 3) by analyzing Weibo content recommended by various algorithms, it is found that CMR tends to recommend community of interest to users, while MRR tends to recommend common hot spot Weibo for users.
【作者單位】： 中國(guó)科學(xué)院軟件研究所基礎(chǔ)軟件國(guó)家工程研究中心;計(jì)算機(jī)科學(xué)國(guó)家重點(diǎn)實(shí)驗(yàn)室(中國(guó)科學(xué)院軟件研究所);
【基金】：國(guó)家自然科學(xué)基金項(xiàng)目(61433015,61272324) 國(guó)家“八六三”高技術(shù)研究發(fā)展計(jì)劃基金項(xiàng)目(2015AA015405) 網(wǎng)絡(luò)文化與數(shù)字傳播北京市重點(diǎn)實(shí)驗(yàn)室開放課題(ICDD201204)
【分類號(hào)】：TP391.3;TP393.092
【參考文獻(xiàn)】
相關(guān)期刊論文 前1條
1 彭澤環(huán);孫樂(lè);韓先培;石貝;;基于排序?qū)W習(xí)的微博用戶推薦[J];中文信息學(xué)報(bào);2013年04期
【共引文獻(xiàn)】
相關(guān)博士學(xué)位論文 前1條
1 段亞娟;微博搜索的關(guān)鍵技術(shù)研究[D];中國(guó)科學(xué)技術(shù)大學(xué);2014年
相關(guān)碩士學(xué)位論文 前2條
1 吳磊;基于社會(huì)網(wǎng)絡(luò)分析的微博用戶研究[D];安徽大學(xué);2014年
2 余紫丹;基于信任關(guān)系與主題分析的微博用戶推薦技術(shù)[D];華東理工大學(xué);2015年
，本文編號(hào)：2347305
本文鏈接：http://sikaile.net/guanlilunwen/ydhl/2347305.html
最近更新
教材專著
