Real-time Social Media Content Recommendation for Live Sports Events
Name
Liu-rbliu-meng-eecs-2022-thesis.pdf
Description
Thesis PDF
Size
9.03 MB
Format
Adobe PDF
Checksum (MD5)
81fc318a31312572fb162247d0ff6743
Author(s)
Liu, Renbin
Advisor(s)
Palacios, Tomás
Peng, Feifei
Date Issued
May 2022
Publisher
Massachusetts Institute of Technology
Abstract
The presence of social media is getting greater in the sports arena. Many people who watch live sports games also follow social media platforms for live coverage and commentaries. Although these additional content can enrich the watching experiences of the audience, they may become distractions to the audience from some key events in a live sports game. In this thesis, we propose a system that will automatically present relevant and engaging social media content for a live game. We will employ techniques in Natural Language Processing to filter social media posts to select the best ones for users to follow while watching the game. With an engagement prediction model augmented with other metadata of the post and of its author, the audience can enjoy the game without missing out on important game coverage and reactions on social media.
MIT Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
In Copyright - Educational Use Permitted
Copyright MIT
Persistent DSpace Link
