Analysis of Topic Influence and Post Features of Sina-Weibo

DOI

10.2991/csece-18.2018.105How to use a DOI?

Keywords

Sina-Weibo; social network; features; information tipping points; predictive model

Abstract

Microblog serves as an outlet for expressing ideas of events and plays a significant role in propagating news. This paper focused on the most popular microblog in China - Sina-Weibo and discussed topic influences. Firstly, this paper decomposed topic structure into Average Fundamental Popularity and Information Tipping Points. This paper classified topics into three patterns. Next, we collected 10455 available Information Tipping Points and obtained all the posts on each one by Python. We processed these posts and got 20 features, including features within the social network and features in the whole network, such as Ratio of Original Posts and Forward Hierarchy. Furthermore, K-means and EM algorithm were applied to cluster subtopics. Statistical methods such as Spearman Rank Correlation Coefficient Method, the Levene Homogeneity of Variance Test, and One-way Analysis of Variance were used to analyze the relationship among some features. We find that eight of all the features have strong relationships with the Number of Weibo Posts. Furthermore, the total number of posts on one topic (the Number of Weibo Posts) can represent topic impact. This paper established a predictive model via the regression method to predict the Number of Weibo Posts. We also find that whether a topic can become influential can be predicted by its features in the whole network. Finally, this paper applied SVM algorithm to determine which subtopic can become a trending issue.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Borong Lyu
AU  - Xinhui Shao
AU  - Yinbo Huang
AU  - Yuyang Xie
PY  - 2018/02
DA  - 2018/02
TI  - Analysis of Topic Influence and Post Features of Sina-Weibo
BT  - Proceedings of the 2018 International Conference on Computer Science, Electronics and Communication Engineering (CSECE 2018)
PB  - Atlantis Press
SP  - 479
EP  - 486
SN  - 2352-538X
UR  - https://doi.org/10.2991/csece-18.2018.105
DO  - 10.2991/csece-18.2018.105
ID  - Lyu2018/02
ER  -