Detecting anomalies in social network data consumption.

As the popularity and usage of social media exploded over the years, understanding how social network users' interests evolve gained importance in diverse fields, ranging from sociological studies to marketing. In this paper, we use two snapshots from the Twitter network and analyze data interest patterns of users in time to understand individual and collective user behavior on social networks. Building topical profiles of users, we propose novel metrics to identify anomalous friendships, and validate our results with Amazon Mechanical Turk experiments. We show that although more than 80 % of all friendships on Twitter are created due to data interests, 83 % of all users have at least one friendship that can be explained neither by users' past interest nor collective behavior of other similar users. [ABSTRACT FROM AUTHOR]