Previous personalized DTV recommendation systems focus only on viewers' historical viewing records or demographic data. This study proposes a new recommending mechanism from a user oriented perspective. The recommending mechanism is based on user properties such as Activities, Interests, Moods, Experiences, and Demographic information-AIMED. The AIMED data is fed into a neural network model to predict TV viewers' program preferences. Evaluation results indicate that the AIMED model significantly increases recommendation accuracy and decreases prediction errors compared to the conventional model.
|Title of host publication||INTERACTIVE TV: A SHARED EXPERIENCE, PROCEEDING|
|Publisher||Springer-Verlag Berlin Heidelberg|
|State||Published - 24 May 2007|
|Name||Lecture Notes in Computer Science|
- TV program recommendation system
- personal information
Hsu, S-H., Wen, M-H., Lin, H-C., Lee, C-C., & Lee, C-H. (2007). AIMED - A personalized TV recommendation system. In INTERACTIVE TV: A SHARED EXPERIENCE, PROCEEDING (Vol. 4471, pp. 166-+). (Lecture Notes in Computer Science). Springer-Verlag Berlin Heidelberg. https://doi.org/10.1007/978-3-540-72559-6_18