Audience Behavior Mining: Integrating TV Ratings with Multimedia Content

Abstract

To discover relationships between TV ratings and multimedia content, we focus on the change points—that
is, the points in time when people first tune in to a particular TV program. Because these points reflect the
active intention of TV viewers, they contain valuable information about viewers‘ interests. We describe
these points using visual features extracted from video and using keywords extracted from transcripts.
Because the number of such points is huge, we apply various filters. Here, in this extended version of our
earlier work, we propose two applications using our framework, demonstrating how the framework can
extract valuable knowledge from TVratings data. A general framework for audience behavior mining
integrates the analysis of TV ratings and multimedia content. Focusing on change points in TV ratings
data, the authors propose applications for interactive mining of audience behavior and for detecting popular
news topics.