Abstract
Context-awareness has become a critical factor to improve the prediction of user interest in modern online TV recommendation systems. In addition to individual user preferences, existing context-aware approaches like tensor factorization incorporate system-level contextual bias to increase predicting accuracy. We analyzed a user interaction dataset from a WebTV platform and found that such contextual bias creates a skewed selection of recommended programs which ultimately limits users in a filter bubble. To address this issue, we introduce the Twitter social stream as an external contextual factor to extend the choice with items related to social media events. We apply two trend indicators, Trend Momentum and SigniScore, to the Twitter histories of relevant programs. The evaluation reveals that Trend Momentum outperforms SigniScore and signalizes 96% of all peaks ahead of time regarding the selected candidate program titles.
| Original language | English |
|---|---|
| Title of host publication | ACM International Conference on Interactive Experiences for Television and Online Video (ACM TVX) |
| Place of Publication | The Netherlands |
| Publisher | Association for Computing Machinery (ACM) |
| Pages | 21-30 |
| Number of pages | 10 |
| ISBN (Print) | 978-1-4503-4529-3 |
| DOIs | |
| Publication status | Published - 16 Jun 2017 |
Keywords
- Privacy reserving recommender
- context-aware applications
- event detection
- userexperience
- video on demand