Analyzing the Role of Users' Interactions in Information Spread

The emergence of social platforms has provided us with a vast amount of raw data on people's daily activities, their social connections, interactions, interests, influence, etc. This creates an opportunity to extract valuable insights, helpful in various applications including but not limited to the identification of the trending topics, community detection, health purposes, and marketing. This thesis designs a platform that analyzes users' interactions (e.g., posts, likes, and shares) and connections (e.g., friendship and followership), and maximizes information spread in the network accordingly. There are numerous applications to this such as advertising, knowledge dissemination, encouraging the adoption of productive behavior in a society, etc. I present a 3-part platform that utilizes users' activities to maximize information spread. It starts by analyzing users' posts (Step 1), and proceeds with users' interactions (Step 2), and connections (Step 3). This information is utilized to locate user communities formed based on topical cascades. Targeting these communities helps to increase the spread of information. In the first step, posts (e.g., tweets) are categorized into partitions representing topics of discussion. Part 2 identifies bursty user groups for each topic of interest. A bursty user group includes a collection of socially connected users who are active and influential with regard to a specific topic. Bursty user groups for a topic are the sources of previous activities on that topic and are of high importance in marketing campaigns. Finally having a limited budget for advertising (i.e., a fixed seed set size), Part 3 determines the best groups among all to target to maximize the spread of information in the network. The analysis is based on the state-of-the-art viral marketing models. All of the proposed algorithms have been extensively evaluated on real-world datasets including Twitter fire-hose, co-authorship, and telecommunication datasets. We present quantitative and qualitative experimental results in each chapter attesting to the practicality of our algorithms.Ph.D