Jindong Chen
ABSTRACT
In Bulletin Board System, when an author submits a post to start a thread, what kinds of elements affect the popularity of this thread? To address this issue, Tianya Zatan board of Tianya Club is selected as data source for this study. Through database and online data, the daily new threads with high degree of online interactions in 2012 are collected for analysis. To explore the key elements relating to the popularity of thread, several elements are analyzed using different methods: the topics of original posts are based on Latent Dirichlet Allocation, the high frequency words of titles, the basic features (the length of titles, the titles with/without picture information, and the length of the content of original posts) and reply modes are based on statistics. Finally, several practical tips for an author to promote the popularity of the thread are given.
Index Terms
- How to Become a More Popular Thread on Tianya Club
Recommendations
Prevailing Trends Detection of Public Opinions Based on Tianya Forum
IDEAL 2013: Proceedings of the 14th International Conference on Intelligent Data Engineering and Automated Learning --- IDEAL 2013 - Volume 8206How to catch both the central topics and the trend of topics over the on-line discussions are not only of theoretical importance for scientific research, but also of practical importance for social management in current China. In social management ...
How to Become a More Popular Thread on Tianya Club
SocialCom '14: Proceedings of the 2014 International Conference on Social ComputingIn Bulletin Board System, when an author submits a post to start a thread, what kinds of elements affect the popularity of this thread? To address this issue, Tianya Zatan board of Tianya Club is selected as data source for this study. Through database ...
Exploring Societal Risk Classification of the Posts of Tianya Club
To identify the societal risk category of the posts of Tianya Club, several studies are carried out toward the posts of Tianya Club. With 2-month manually risk labeled new posts published during December of 2011 to January of 2012, statistical analysis ...
Comments