Abstract
Online video recommender systems help users find the suitable videos for their preferences. However, they have difficulty in recommending videos to new users and identifying dynamic user preferences. In this research, we propose a new procedure using the changes of facial expressions every moment to solve these problems. Facial expressions portray the user's actual emotion felt about a video. We can utilize them to discover dynamic user preferences and recommend videos to new users. Experiment results show that the proposed procedure outperform the benchmark system such as random recommendation and a typical CF for recommendation both to new users and existing users. From the results, we conclude that facial expression is an important element in recommendation and the proposed system is very efficient in recommending videos with a simple Web cam device only.
| Original language | English |
|---|---|
| Publication status | Published - 2014 |
| Event | 24th Annual Workshop on Information Technologies and Systems: Value Creation from Innovative Technologies, WITS 2014 - Auckland, New Zealand Duration: 17 Dec 2014 → 19 Dec 2014 |
Conference
| Conference | 24th Annual Workshop on Information Technologies and Systems: Value Creation from Innovative Technologies, WITS 2014 |
|---|---|
| Country/Territory | New Zealand |
| City | Auckland |
| Period | 17/12/14 → 19/12/14 |