• Nov 25, 2021 News!Vol.7, No.2 has been published with online version.   [Click]
  • Jun 11, 2020 News!Vol.6, No.1 has been published with online version.   [Click]
  • Dec 18, 2019 News!Vol.5, No.2 has been published with online version.   [Click]
General Information
    • ISSN: 2382-6185
    • Abbreviated Title: Int. J. Knowl. Eng.
    • Frequency: Semiyearly
    • DOI: 10.18178/IJKE
    • Editor-in-Chief: Prof. Chen-Huei Chou
    • Executive Editor: Ms. Nina Lee
    • Indexed by: Google Scholar, Crossref, ProQuest
    • E-mail: ijke@ejournal.net
Prof. Chen-Huei Chou
College of Charleston, SC, USA
It is my honor to be the editor-in-chief of IJKE. I will do my best to help develop this journal better.
IJKE 2015 Vol.1(2): 100-106 ISSN: 2382-6185
DOI: 10.7763/IJKE.2015.V1.17

Predict Quit Rate of Group from User Behavioral and Social Information

Chang Tu, Peng Cui, and Shiqiang Yang
Abstract—There is a common intuition that the user behavioral pattern and social information of a group may influence its attraction to users. In this paper, we employ user behavioral and social information to predict the user quit rate of social groups and validate the link between social behavioral pattern and group quit rate on a large scale real dataset — Tencent QQ groups. We routinely model this task as a regression problem, and generate 97 features from user behavioral and social information. Then we use an improved Scalable Orthogonal Regression (iSOR) method to predict the quit rate of QQ group. Our study shows that the quit rate of a group can be predicted with high accuracy, furthermore, the iSOR method selected several import features from the total 97 social behavioral features.

Index Terms—Quit rate, social group, social information, user behavior.

The authors are with the Department of Computer Science and Technology, Tsinghua University, Beijing 10084, China (e-mail: tuc12@mails.tsinghua.edu.cn, cuip@tsinghua.edu.cn, yangshq@tsinghua.edu.cn).


Cite: Chang Tu, Peng Cui, and Shiqiang Yang, "Predict Quit Rate of Group from User Behavioral and Social Information," International Journal of Knowledge Engineering vol. 1, no. 2, pp. 100-106, 2015.

Copyright © 2008-2021   International Journal of Knowledge Engineering. All rights reserved.
E-mail: ijke@ejournal.net