Socially aware tv program recommender for multiple viewers

Authors:
Choonsung Shin;Woontack Woo
Affiliations:
Dept. of Inf. & Commun., GIST, South Korea;-
Venue:
IEEE Transactions on Consumer Electronics
Year:
2009

Citing 0
Cited 8

Group recommendation using feature space representing behavioral tendency and power balance among members

Proceedings of the fifth ACM conference on Recommender systems
Widget-Based simulator for testing smart space

Transactions on Edutainment III
Document recommendations based on knowledge flows: A hybrid of personalized and group-based approaches

Journal of the American Society for Information Science and Technology
Rough Set Theory Based User Aware TV Program and Settings Recommender

International Journal of Advanced Pervasive and Ubiquitous Computing
MUSST: workshop on multi-user services for social TV

Proceedings of the 11th european conference on Interactive TV and video
TV predictor: personalized program recommendations to be displayed on SmartTVs

Proceedings of the 2nd International Workshop on Big Data, Streams and Heterogeneous Source Mining: Algorithms, Systems, Programming Models and Applications
Design of Context Aware Recommendation Engine for Cell Phone using Bayesian Network, Fuzzy Logic, and Rough Set Theory

International Journal of Advanced Pervasive and Ubiquitous Computing
QA document recommendations for communities of question-answering websites

Knowledge-Based Systems

Quantified Score

Hi-index	0.43

Visualization

Abstract

With the increasing amount of research on smart TVs, users are interacting with them in an evermore convenient way. However, current program recommendations mainly focus on using individual profiles and require users' active participation when multiple viewers coexist. In this paper, we propose a socially aware program recommender for multiple viewers of a digital TV that rates and selects TV programs based on individual and group preferences. For this task, the proposed recommender generates recommendations for users by merging user profiles and combining their common interests. In this way, programs that all users prefer are automatically selected and ambiguous or conflicting programs are mediated based on user feedback. Through subsequent experiments with a smart TV equipped with the program recommender, we found that the performance of group recommendations improved when individual profiles and the group's common interests were used, and that users preferred different strategies when they were with other people.