A study on discontinuity pattern in online social networks data using regression discontinuity design

Abstract

The analysis of Online Social Networks (OSNs) data is an emerging field involving sociology, statistics, and graph theory. Regression Discontinuity Design (RDD) is a quasi-experimental research design widely used in social, behavioral and related sciences. In this paper, we proposed a methodology to analyze the data from the most popular micro-blogging OSN ‘Twitter’. The methodology is implemented using ‘R’ statistical tool. The tweets related to the ‘Mangalayan’ event, India’s Mars Orbiter Mission launched on 5 November 2013 by the Indian Space Research Organization are analyzed. The Twitter users who are expressive/non expressive on this event are examined. In particular the pattern related to the user’s responses to this event is identified, which helps in predicting the Twitter users’ social behavior and their involvement associated to such similar events. The most frequent words reflecting the relevance to this event are visualized. The visual results are helpful to understand the pattern or trend of tweets generated by the Twitter users. The users and their tweets in the study are analyzed as two groups based on the word frequency and their relevance to the event. This helps in analyzing the discontinuity pattern in the tweets and exploits the inherent randomness that exists in the frequency of word occurrence using RDD. It is realized from the experimental study that the RDD estimates and plots are credible to analyze the data from the Twitter OSN. Further, it will help the research community to explore the dynamic behavior of the Twitter users adopting this methodology.