It might not surprise you to know that people love to watch animal videos. But did you know that people are more likely to watch if the animal is splashing around in water?
This is the kind of information you can mine and analyze from audience behavior data gathered from TV ratings and multimedia content.
Researchers are keenly interested in what captures and loses a viewer’s attention because this information can be used to create better television programming, produce higher ratings, and attract more sponsors, say authors Ryota Hinami of University of Tokyo and Shin’ichi Satoh of National Institute of Informatics.
“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,” they write.
Read more about how researchers are fine-tuning the algorithms that reveal what we choose to watch in the April–June 2017 issue of IEEE MultiMedia.
Read article (login may be required for full text)
About Lori Cameron
Lori Cameron is a Senior Writer for the IEEE Computer Society and currently writes regular features for Computer magazine, Computing Edge, and the Computing Now and Magazine Roundup websites. Contact her at l.cameron@computer.org. Follow her on LinkedIn.
