本文選題：循環(huán)神經(jīng)網(wǎng)絡(luò)　切入點(diǎn)：點(diǎn)隨機(jī)過程　出處：《軟件學(xué)報(bào)》2017年11期

【摘要】：社交網(wǎng)絡(luò)中,消息的爆發(fā)預(yù)測屬于社交網(wǎng)絡(luò)流行動(dòng)態(tài)分析的范疇,是社會(huì)計(jì)算領(lǐng)域的研究熱點(diǎn)之一.通過利用基于深度循環(huán)神經(jīng)網(wǎng)絡(luò)對(duì)社交消息的傳播過程進(jìn)行建模,提出了SMOP(social messages outbreak prediction model based on recurrent neural network)模型.與傳統(tǒng)的基于機(jī)器學(xué)習(xí)的模型相比,SMOP直接對(duì)消息轉(zhuǎn)發(fā)的到達(dá)過程進(jìn)行建模,避免了傳統(tǒng)方法中繁瑣的特征工程;與基于點(diǎn)隨機(jī)過程的模型相比,SMOP可以自動(dòng)學(xué)習(xí)消息傳播過程的速率函數(shù),不需要手動(dòng)定義消息傳播速率的特征函數(shù),具有較強(qiáng)的數(shù)據(jù)場景適應(yīng)性.另外,SMOP采用了時(shí)間向量和用戶向量的輸入表示方法,將時(shí)間的周期性和用戶的興趣偏好建模到傳播過程之中,提升了SMOP的預(yù)測效果.在Twitter和新浪微博數(shù)據(jù)集上的實(shí)驗(yàn)結(jié)果均表明,SMOP具有優(yōu)良的數(shù)據(jù)適應(yīng)能力,可以在消息傳播的早期(0.5h),以較高的F1值預(yù)測某條社交消息是否爆發(fā),驗(yàn)證了模型的有效性.
[Abstract]:In social networks, the burst prediction of messages belongs to the category of social network popular dynamic analysis, and is one of the research hotspots in the field of social computing.The SMOP(social messages outbreak prediction model based on recurrent neural network is proposed by modeling the propagation process of social message based on the deep loop neural network.Compared with the traditional model based on machine learning, SMOP models the arrival process of message forwarding directly and avoids the tedious feature engineering in the traditional method.Compared with the model based on point random process, SMOP can learn the rate function of message propagation process automatically, and does not need to define the characteristic function of message propagation rate manually, so it has strong adaptability to data scene.In addition, SMOP uses the input representation method of time vector and user vector to model the periodicity of time and user's interest preference into the propagation process, which improves the prediction effect of SMOP.The experimental results on the data sets of Twitter and Sina Weibo show that SMOP has good data adaptability and can predict whether a social message erupts with a higher F1 value at the early stage of message transmission, which proves the validity of the model.
【作者單位】： 中國科學(xué)院網(wǎng)絡(luò)數(shù)據(jù)科學(xué)與技術(shù)重點(diǎn)實(shí)驗(yàn)室(中國科學(xué)院計(jì)算技術(shù)研究所);中國科學(xué)院大學(xué);中國人民解放軍61755部隊(duì);
【分類號(hào)】：G206;TP18

【相似文獻(xiàn)】

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)測與關(guān)系強(qiáng)度研究[A];第七屆（2012）中國管理學(xué)年會(huì)商務(wù)智能分會(huì)場論文集（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)：1721965