PhD Dissertation Defense of Bonaventure Chidube Molokwu:"Social Network Analysis: A Machine Learning Approach "

 

Date: Thursday, July 22, 2021 

Time:  1:00pm – 4:00pm 

Meeting URL:  https://zoom.us/j/97688601388?from=addon 

Passcode: If interested in attending the event, contact the Graduate Secretary at csgradinfo@uwindsor.ca

 

 

Social Network Analysis (SNA) is an appealing research topic, within the domain of Artificial Intelligence (AI), owing to its widespread application in the real world. In this dissertation, we have proposed effective Machine Learning (ML) and Deep Learning (DL) approaches toward resolving these open problems in SNA, viz: Breakup Prediction, Link Prediction, Node Classification, Event-based Analysis, and Trend/Pattern Analysis. Existing literature have focused on studying the apparent and latent interactions within social graphs as an n-ary operation, which yields binary outputs comprising positives (friends, likes, etc.) and negatives (foes, dislikes, etc.). Thus, as part of the research contributions in this dissertation, we have proposed an automatic technique toward flagging ties for breakups (negative-tie state) based on an n-ary operation which renders ternary outputs composed of positives, negatives, and intersections. Furthermore, SNA can be employed toward resolving several real-world problems; and ML as well as DL have proven to be very effective methodologies for accomplishing AI-related goals. 

 

Keywords: Social Network analysis (SNA), Artificial Intelligence (AI), Machine Learning (ML), Deep Learning (DL), breakup prediction, link prediction, node classification, event-based analysis, trend/pattern analysis

 

Internal Reader: Dr. Saeed Samet 

Internal Reader: Dr. Jianguo Lu 

External Reader: Dr. Dragana Martinovic, Faculty of Education   

External Examiner: Dr. Ebrahim Bagheri, Ryerson University           

Advisor:  Dr. Ziad Kobti                       

Chair:  Dr. Kristen Lwin, School of Social Work