基于SVM的微博轉(zhuǎn)發(fā)規(guī)模預(yù)測方法
發(fā)布時間:2018-10-09 19:50
【摘要】:為了評價微博的傳播效果,在分析影響用戶轉(zhuǎn)發(fā)行為因素的基礎(chǔ)上,提出了采用用戶影響力、用戶活躍度、興趣相似度、微博內(nèi)容重要性和用戶親密程度五項特征進(jìn)行轉(zhuǎn)發(fā)行為預(yù)測的SVM算法,以及基于該算法的轉(zhuǎn)發(fā)規(guī)模預(yù)測算法。最后給出了傳播規(guī)模預(yù)測的評價方法。針對新浪微博用戶數(shù)據(jù)的實驗表明,預(yù)測精度達(dá)到了86.63%。
[Abstract]:In order to evaluate the transmission effect of Weibo, on the basis of analyzing the factors that affect the user's forwarding behavior, the author proposes to adopt user influence, user activity, interest similarity, etc. The SVM algorithm for predicting forwarding behavior based on the five features of Weibo's content importance and user's closeness, as well as the algorithm for predicting forwarding scale based on this algorithm. Finally, the evaluation method of propagation scale prediction is given. For Sina Weibo user data experiments show that the accuracy of the prediction reached 86.63.
【作者單位】: 國家數(shù)字交換系統(tǒng)工程技術(shù)研究中心;
【基金】:國家“863”計劃資助項目(2011AA010603)
【分類號】:TP393.092
[Abstract]:In order to evaluate the transmission effect of Weibo, on the basis of analyzing the factors that affect the user's forwarding behavior, the author proposes to adopt user influence, user activity, interest similarity, etc. The SVM algorithm for predicting forwarding behavior based on the five features of Weibo's content importance and user's closeness, as well as the algorithm for predicting forwarding scale based on this algorithm. Finally, the evaluation method of propagation scale prediction is given. For Sina Weibo user data experiments show that the accuracy of the prediction reached 86.63.
【作者單位】: 國家數(shù)字交換系統(tǒng)工程技術(shù)研究中心;
【基金】:國家“863”計劃資助項目(2011AA010603)
【分類號】:TP393.092
【參考文獻(xiàn)】
相關(guān)期刊論文 前3條
1 林學(xué)民;王煒;;集合和字符串的相似度查詢[J];計算機(jī)學(xué)報;2011年10期
2 施聰鶯;徐朝軍;楊曉江;;TFIDF算法研究綜述[J];計算機(jī)應(yīng)用;2009年S1期
3 張s,
本文編號:2260569
本文鏈接:http://sikaile.net/guanlilunwen/ydhl/2260569.html
最近更新
教材專著