Automated Story-Based Commentary for Sports


Jodrey School of Computer Science

SEMINAR PRESENTATION

 

Wednesday, February 14, 2018

10:30 - 11:30 PM

Carnegie Hall 207


Automated Story-Based Commentary for Sports

Dr. Greg Lee

Tenure Track Applicant

 

Abstract

Automated sports commentary is a form of automated narrative. Sports commentary exists to keep the viewer informed and entertained. One way to entertain the viewer is by telling brief stories relevant to the game in progress. The Sports Commentary Recommendation System (SCoReS) can automatically suggest stories for commentators to tell during games. Across several user studies commentary using SCoReS was compared to three other types of commentary and it was shown that SCoReS adds significantly to the broadcast across several enjoyment metrics. Interviews with professional sports commentators showed they positively evaluated a demonstration of the system. It has been shown that SCoReS can be a useful broadcast tool, effective at selecting stories that add to the enjoyment and watchability of sports. SCoReS automates storytelling in sports commentary and, thus, automates narrative. Automating narrative is a complex problem that is a step towards artificial intelligence.

About the Presenter

Greg Lee is the Lead Data Scientist at Fundmetric and a Laboratory Instructor at Acadia University. Greg completed his Ph.D. in Computer Science at the University of Alberta. His research focus is on automated storytelling. This research includes work in human computer interaction and mobile computing. During his graduate studies, he collaborated with Minor League Baseball and CBC’s Hockey Night in Canada. He has published papers in numerous academic journals and conferences, and has seen his work recognized by New Scientist magazine, CBC Radio’s Spark and NPR. At Fundmetric, Greg has researched methods to machine learn a donor’s charitable leanings, leading to orders of magnitude improvement in donations for various hospitals, universities and charities. His current research focus is on effectively communicating AI-selected stories to an audience, using modern software engineering methods and ensuring that all storytelling software is mobile friendly.

 

Everyone is welcome to attend


Go back