發(fā)布時間：2018-03-29 20:33

  本文選題：在線社交網(wǎng)絡　切入點：觀點傳播　出處：《計算機學報》2017年04期

【摘要】：在不同情感極性上建模用戶間的影響力是觀點形成和病毒式營銷的一個關鍵問題.已有工作將用戶間影響力直接定義在用戶對上,無法刻畫未觀測到用戶對之間的關聯(lián)關系,造成用戶影響力學習的過擬合問題.此外,目前尚無針對不同情感極性的用戶間影響力建模的有效方法.因此,該文提出一種融合情感因素的用戶分布式表達模型.該模型首先構(gòu)建兩個低維參數(shù)矩陣度量在不同情感極性上傳播者的影響力和接受者的易感性,然后通過生存分析模型刻畫級聯(lián)的傳播行為,最后利用負采樣方法解決模型中存在正負例嚴重不平衡的問題.基于帶有情感觀點的微博轉(zhuǎn)發(fā)所形成級聯(lián)數(shù)據(jù)集的實驗結(jié)果表明,與基準方法對比,該文方法在"預測動態(tài)級聯(lián)"和"誰將會被轉(zhuǎn)發(fā)"任務上MRR指標分別提高了273%和32.4%,在"級聯(lián)大小預測"任務上MAPE指標下降了10.46%,很好地驗證了該文模型的有效性.此外,該文分析用戶的情感影響力和易感性分布并發(fā)現(xiàn)了一些重要的現(xiàn)象.
[Abstract]:Modeling the influence between users on different emotional polarities is a key issue in view formation and viral marketing. In addition, there is no effective method for modeling the influence between users with different affective polarities. In this paper, a user distributed representation model combining emotional factors is proposed. Firstly, two low-dimensional parameter matrices are constructed to measure the influence of the communicator and the susceptibility of the receiver in different affective polarities. Then the propagation behavior of cascades is described by survival analysis model. Finally, negative sampling method is used to solve the problem of serious imbalance of positive and negative cases in the model. Compared with the baseline method, In this paper, the MRR index of "predicting dynamic cascade" and "who will be forwarded" is increased by 27.3% and 32.4% respectively, and the MAPE index of "cascaded size prediction" task is decreased by 10.46%, which verifies the validity of the model. This paper analyzes the affective influence and susceptibility distribution of users and finds some important phenomena.
【作者單位】： 福州大學數(shù)學與計算機科學學院;福建省網(wǎng)絡計算與智能信息處理重點實驗室(福州大學);中國科學院網(wǎng)絡數(shù)據(jù)科學與技術(shù)重點實驗室;
【基金】：國家“九七三”重點基礎研究發(fā)展規(guī)劃項目基金(2013CB329606,2013CB329602) 國家自然科學基金項目(61572467,61300105) 中國科學院網(wǎng)絡數(shù)據(jù)科學與技術(shù)重點實驗室開放基金課題(CASNDST20140X)資助~~
【分類號】：TP391.1
，

本文編號：1682737