Echo-chambers in recommender systems

TALK ABSTRACT: Social media has been effective in showing us what we want to see but has also helped create echo-chambers at a large scale. Recent events have sparked research on de-siloing these information bubbles from different perspectives. At Flipboard, a tech company in the journalism space, we have done a few experiments where we map news articles into latent spaces using variants of topic modelling that help our algorithms pick out articles that appeal to different distinct sets of user groups. Through this talk, I aim to illustrate what we have tried to do from a data-science perspective and share our learnings, and most importantly, start a discussion on this vital problem.

EVENT TIME:

• Doors open at 5:30pm
• Networking from 5:30pm to 6pm
• Talk starts at 6pm
• Head to Rogue at Waterfront for more networking

EVENT VENUE: UrbanLogiq Software - 700 W Pender St Suite 1505

BIO: Arnab Bhadury is a machine learning engineer and data scientist on the data products team at Flipboard, Vancouver. He is the main author of the current multilingual topic extraction pipeline at Flipboard and is currently working closely with the recommendations team to improve news recommendation in multiple languages and locales. Mr. Bhadury holds an MSc from Tsinghua University where he worked on Bayesian Topic Modeling and Large Scale Bayesian Inference. His current research interests include recommender systems, natural language processing and Bayesian machine learning.