社交网络群中用户活跃度分析与预测

张效尉<sup>1</sup>,余云霞<sup>2</sup>,王伟<sup>1</sup>

doi:10.13718/j.cnki.xsxb.2018.12.019

西南师范大学学报(自然科学版)

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
	姓名不能为空！
邮箱
	邮箱不能为空！非法的邮箱地址。
手机号码
	电话不能为空！请输入有效手机号!
标题
	标题不能为空！
留言内容
	内容不能为空！
验证码
	验证码不能为空！验证码错误！

社交网络群中用户活跃度分析与预测

张效尉1,余云霞2,王伟1. 社交网络群中用户活跃度分析与预测[J]. 西南师范大学学报(自然科学版), 2018, 43(12): 115-121. doi: 10.13718/j.cnki.xsxb.2018.12.019

引用本文:

张效尉¹,余云霞²,王伟¹. 社交网络群中用户活跃度分析与预测[J]. 西南师范大学学报(自然科学版), 2018, 43(12): 115-121. doi: 10.13718/j.cnki.xsxb.2018.12.019

ZHANG Xiao-wei1, YU Yun-xia2, WANG Wei1. On Prediction and Analysis of Social Network Group User Activity[J]. Journal of Southwest China Normal University(Natural Science Edition), 2018, 43(12): 115-121. doi: 10.13718/j.cnki.xsxb.2018.12.019

Citation:

ZHANG Xiao-wei¹, YU Yun-xia², WANG Wei¹. On Prediction and Analysis of Social Network Group User Activity[J]. Journal of Southwest China Normal University(Natural Science Edition), 2018, 43(12): 115-121. doi: 10.13718/j.cnki.xsxb.2018.12.019

社交网络群中用户活跃度分析与预测

张效尉¹,余云霞²,王伟¹

1. 周口师范学院网络工程学院, 河南周口 466001;
2. 荆楚理工学院计算机工程学院, 湖北荆门 448000

On Prediction and Analysis of Social Network Group User Activity

ZHANG Xiao-wei¹, YU Yun-xia², WANG Wei¹

1. School of Network Engineer, Zhoukou Normal University, Zhoukou Henan 466001, China;
2. School of Computer Engineering, Jingchu University of Technology, Jingmen Hubei 448000, China

摘要: 对于社交网络中不同的群组，由于用户属性（性别、年龄等）、群类别、群成员之间关系等因素的影响，其活跃度各不相同.本文首先从社交网络用户数据中提取人口信息、群的类别、社交关系、群用户黏性（分享消息数、图片数）等特征，然后利用logistic回归、支持向量机、BP神经网络等机器学习算法对不同群中用户的活跃度进行预测.结果表明，BP神经网络针对社交网络群中用户活跃度分类判断时具有较高的预测性能，社交关系特征对群用户活跃性具有重要影响.
- 社交网络群 /
- 用户活跃度 /
- 人口信息学 /
- 社交关系
Abstract: For different groups in a social network, their activities are frequently influenced by a variety of factors such as user's attributes (i.e., gender, age), group classes, social relationships between group members and so on. In order to model and analyze the activities of different groups in this paper, several features which may influence the activity of a group have first been extracted from the historical data generated from a social network, such as census information, social relationships, group class, user stickiness (the number of the shared photos and information) and so on. Then, based on the extracted features, the activity of a group is predicted using logistic regression model, support vector machine and BP neural network. The results show that BP neural network has high performance on classifying group users' activity, and social relationships have a major impact on the activity of a group.
- social network group /
- user activity /
- demographic informatics /
- social relationships .

[1]	蒋文丽, 汤庸, 许玉赢, 等. 社交网络中角色活跃度的好友推荐[J]. 小型微型计算机系统, 2016, 37(10):2162-2165.
[2]	HAN Y, TANG J. Who to Invite Next? Predicting Invitees of Social Groups[C]//26th International Joint Conference on Artificial Intelligence. Melbourne:AAAI Press, 2017:3714-3720.
[3]	QIU J Z, LI Y X, TANG J, et al. The Lifecycle and Cascade of WeChat Social Messaging Groups[C]//25th World Wide Web Conference. Montréal:ACM Press, 2016:311-320.
[4]	Butler B S. Membership Size, Communication Activity and Sustainability:A Resource-Based Model of Online Social Structures[J]. Information Systems Research, 2001, 12(4):346-362.
[5]	李献礼. 在线社会网络多维度链式信任计算算法[J]. 西南大学学报(自然科学版), 2016, 38(8):142-147.
[6]	黄炜, 李总苛, 李岳峰. 微信用户活跃度影响因素分析[J]. 湖北工业大学学报, 2015, 30(6):29-32.
[7]	SHI X L, ZHU J, CAI R, et al. User Grouping Behavior in Online Forums[C]//15th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Paris:ACM Press, 2009:777-785.
[8]	YANG J, WEI X, ACKERMAN M S, et al. Activity Lifespan:An Analysis of User Survival Patterns in Online Knowledge Sharing Communities[C]//4th International Conference on Weblogs and Social Media. Washington:the Association for the Advancement of Artificial Intelligence, 2010:186-193.
[9]	ZHU Y, ZHONG E H, PAN S J, et al. Predicting User Activity Level in Social Networks[C]//22nd ACM International Conference on Information & Knowledge Management. California:ACM Press, 2013:159-168.
[10]	周静, 李季. 从人口统计特征和生活方式探讨SNS社交网站用户的使用行为及其活跃度[J]. 科技与管理, 2011, 13(2):72-77.
[11]	MAGNUSON M J, LAUREN L. Gender Differences in "Social Portraits" Reflected in My Space Profiles[J]. Cyber Psychology and Behavior, 2008, 11(2):239-241.
[12]	梁修荣, 杨正益. 基于聚类和SVM的数据分类方法与实验研究[J]. 西南师范大学学报(自然科学版), 2018, 43(3):91-96.

计量

文章访问数: 1427
HTML全文浏览数: 1103
PDF下载数: 113
施引文献: 0

社交网络群中用户活跃度分析与预测

张效尉¹,余云霞²,王伟¹

1. 周口师范学院网络工程学院, 河南周口 466001;
2. 荆楚理工学院计算机工程学院, 湖北荆门 448000

收稿日期: 2017-12-21

关键词:

摘要: 对于社交网络中不同的群组，由于用户属性（性别、年龄等）、群类别、群成员之间关系等因素的影响，其活跃度各不相同.本文首先从社交网络用户数据中提取人口信息、群的类别、社交关系、群用户黏性（分享消息数、图片数）等特征，然后利用logistic回归、支持向量机、BP神经网络等机器学习算法对不同群中用户的活跃度进行预测.结果表明，BP神经网络针对社交网络群中用户活跃度分类判断时具有较高的预测性能，社交关系特征对群用户活跃性具有重要影响.

English Abstract

On Prediction and Analysis of Social Network Group User Activity

1. 周口师范学院网络工程学院, 河南周口 466001;
2. 荆楚理工学院计算机工程学院, 湖北荆门 448000

Received Date: 2017-12-21

Keywords:

Abstract: For different groups in a social network, their activities are frequently influenced by a variety of factors such as user's attributes (i.e., gender, age), group classes, social relationships between group members and so on. In order to model and analyze the activities of different groups in this paper, several features which may influence the activity of a group have first been extracted from the historical data generated from a social network, such as census information, social relationships, group class, user stickiness (the number of the shared photos and information) and so on. Then, based on the extracted features, the activity of a group is predicted using logistic regression model, support vector machine and BP neural network. The results show that BP neural network has high performance on classifying group users' activity, and social relationships have a major impact on the activity of a group.