The influence of feedback with different opinions on continued user participation in online newsgroups

Abstract

With the popularity of social media in recent years, it has been a critical topic for social network designer to understand the factors that influence continued user participation in online newsgroups. Our study examines how feedback with different opinions is associated with participants' lifetime in online newsgroups. Firstly, we propose a new method of classifying different opinions among user interaction contents. Generally, we leverage user behavior information in online newsgroups to estimate their opinions and evaluate our classification results based on linguistic features. In addition, we also implement this opinion classification method into our SINCERE system as a real-time service. Based on this opinion classification tool, we use survival analysis to examine how others' feedback with different opinions influence continued participation. In our experiment, we analyze more than 88,770 interactions on the official Occupy LA Facebook page. Our final result shows that not only the feedback with the same opinions as the user, but also the feedback with different opinions can motivate continued user participation in online newsgroup. Furthermore, an interaction of feedback with both the same and different opinions can boost user continued participation to the greatest extent. This finding forms the basis of understanding how to improve online service in social media.

Hashtags and followers

“…Looking into users as a group creates a more complete solution when combined with traditional sentiment analysis approaches. (Bifet and Frank 2010;Pak and Paroubek 2010;Wang et al 2011;Thelwall et al 2011;Wang et al 2013;Go et al 2009;Diakopoulos and Shamma 2010).…”

Multi-view Community Detection in Facebook Public Pages

“…Basically, there is no formal definition of community, but it is believed that entities are densely connected inside each community with less links between different communities [1]. This community structure plays a significant role in visualization [2], dynamic community detection [3], opinion mining [4], and behavior prediction [5].…”