Friday, April 8, 2022 - 11:00 to 12:00
SCHOOL OF COMPUTER SCIENCE – Colloquium Series
The School of Computer Science at the University of Windsor is pleased to present…
PhD Seminar / Colloquium Presentation by Soroush Ziaeinejad

Date: Friday April 8, 2022
Time: 11:00am-12:00pm
Meeting URL: https://us06web.zoom.us/j/85977146778?from=addon
Passcode: If interested in attending this event, contact the Graduate Secretary at csgradinfo@uwindsor.ca with sufficient notice before the event to obtain the passcode.
Abstract
Online user communities exhibit distinct temporal dynamics in response to popular topics or breaking events. I want to introduce SEERA, an open-source end-to-end framework, to identify future user communities in a text streaming social network. SEERA models inter-user topical affinities at each time interval via streams of temporal graphs and learns temporal vector representations for users. This all takes place while users’ topics of interest and hence their inter-user topical affinities are changing over time. SEERA predicts yet-to-be-seen user communities based on the final positions of users’ vectors in the latent space. Notably, our framework serves as a one-stop-shop to future user communities for Social Information Retrieval and Social Recommendation systems. Empirical results on a Twitter dataset show the convenience of SEERA in building an effective news article recommender system.
Keywords: Community Prediction, Social Information Retrieval, Temporal Graph Embedding, News Article Recommendation
Biography
My name is Soroush Ziaeinejad, and I am a Ph.D. Student in Computer Science at University of Windsor and a graduated student with a master’s degree from Amirkabir University of Technology (AUT) – Tehran Polytechnic in AI. My main area of interest includes social information retrieval and natural language processing.
PhD Seminar / Colloquium Presentation 
5113 Lambton Tower 401 Sunset Ave. Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 csgradinfo@uwindsor.ca