Perception of Social Phenomena through the Multidimensional Analysis of Online Social Networks

We propose an analytical framework aimed at investigating from many different views the discussions regarding polarized topics which occur in Online Social Networks (OSNs).

The framework supports the analysis of the opposing views about a controversial topic emerging in an OSN along multiple dimensions, i.e., time, space and sentiment.

To assess its usefulness for mining insights about social phenomena, we apply it to two very different Twitter case studies: the discussions about the refugee crisis and the United Kingdom European Union membership referendum. These complex and con- troversial topics are very important issues for EU citizens and stimulated a multitude of Twitter users to take side and actively participate in the discussions. Our frame- work allows to monitor in a scalable way the raw stream of relevant tweets and to automatically enrich them with space information (user and mentioned locations), and sentiment polarity (positive vs. negative). The analyses we conducted show that the framework allows the differences in positive and negative user sentiment over time and space to be identified, and that the resulting knowledge can support the understanding of complex opinion dynamics by matching variations in the perception with specific events and locations.