Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
}
TY - GEN
T1 - Countering contextual bias in TV watching behavior
T2 - introducing social trend as external contextual factor in TV recommenders
AU - Lorenz, Felix
AU - Yuan, Jing
AU - Lommatzsch, Andreas
AU - Mu, Mu
AU - Race, Nicholas
AU - Hopfgartner, Frank
AU - Albayrak, Sahin
PY - 2017/6/14
Y1 - 2017/6/14
N2 - Context-awareness has become a critical factor in improving the predictions of user interest in modern online TV recommendation systems. In addition to individual user preferences, existing context-aware approaches such as tensor factorization incorporate system-level contextual bias to increase predicting accuracy. We analyzed a user interaction dataset from a WebTV platform, and identified that such contextual bias creates a skewed selection of recommended programs which ultimately locks users in a filter bubble. To address this issue, we introduce the Twitter social stream as a source of external context 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.
AB - Context-awareness has become a critical factor in improving the predictions of user interest in modern online TV recommendation systems. In addition to individual user preferences, existing context-aware approaches such as tensor factorization incorporate system-level contextual bias to increase predicting accuracy. We analyzed a user interaction dataset from a WebTV platform, and identified that such contextual bias creates a skewed selection of recommended programs which ultimately locks users in a filter bubble. To address this issue, we introduce the Twitter social stream as a source of external context 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.
KW - context-aware applications, privacy reserving recommender, trend detection, user experience, video on demand
U2 - 10.1145/3077548.3077552
DO - 10.1145/3077548.3077552
M3 - Conference contribution/Paper
SN - 9781450345293
T3 - TVX '17
SP - 21
EP - 30
BT - Proceedings of the 2017 ACM International Conference on Interactive Experiences for TV and Online Video
PB - ACM
CY - New York, NY, USA
ER -