Abstract | ||
---|---|---|
With the increasing number of TV channels, it is more difficult for viewers to find their preferred TV channel. Thus, the recommender system for TV is needed. However, it has several difficulties. First, the viewer's preferred TV channel is different according to the temporal context. Moreover, the sparseness problem also occurs when we consider temporal context. Temporal context has been recognized as an important factor to consider in personalized recommender systems. A lot of time aware recommendation methods were proposed for these difficulties. In this paper, we survey and compare some techniques for time aware TV channel recommendation such as Singular Value Decomposition (SVD), traditional Matrix Factorization (MF), and Temporal Regularized Matrix Factorization (TRMF). We apply them for real-world data to analyze possible benefits of temporal context information for TV channel recommendation and compare the performance of each of them. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/SCIS-ISIS.2014.7044859 | SCIS&ISIS |
Keywords | Field | DocType |
digital television,recommender systems,singular value decomposition,svd,trmf,personalized recommender system,temporal context information,temporal regularized matrix factorization,time aware tv channel recommendation,time aware recommendation method,tv program recommendation,content-based filtering,matrix factorization,recommender system,temporal context,time aware recommendation | Recommender system,Singular value decomposition,Information retrieval,Computer science,Matrix decomposition,Communication channel,Temporal context | Conference |
ISSN | Citations | PageRank |
2377-6870 | 2 | 0.35 |
References | Authors | |
10 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Sungtak Oh | 1 | 2 | 0.35 |
Noo-ri Kim | 2 | 2 | 0.35 |
Jae-Dong Lee | 3 | 175 | 26.07 |
Jee-Hyong Lee | 4 | 4 | 4.85 |