Online social media allows consumers to engage with each other and to create, share, discuss and modify user-generated content in a highly interactive way. Social media platforms have therefore become critical for companies trying to gauge the pulse of consumers, help identify issues faster, receive immediate feedback on products and offering etc. An effective social media strategy therefore requires companies to mine large volumes of structured unstructured and semi-structured online textual data in order to gain insights into the underlying traits of the consumers and prevailing public opinion. These insights can provide opportunities for market research, protection of brand reputation and a mechanism to gauge user preferences in an attempt to maximize customer satisfaction and consumer-brand engagement. In this paper, we propose and evaluate a classification based framework to predict thread lengths in online discussion forums in order to identify potential topics that may of interest to a particular online community. We identify and evaluate several key features of viral social media conversations through extensive experiments conducted on health 2.0 datasets. We also present a pharmaceutical industry based case study to illustrate how well the viral thread topics relate to real world events.
Sharif, Hashim; Ismail, Saad; Farooqi, Shehroze; Taha Khan, Mohammad; Ali Gulzar, Muhammad; Lakhani, Hasnain; Zaffar, Fareed; and Abbasi, Ahmed, "A Classification Based Framework to Predict Viral Threads" (2015). PACIS 2015 Proceedings. 134.