Footnote:
Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
Description:
In this paper, a novel framework is developed to support personalized news video recommendation. First, multi-modal information sources for news videos are seamlessly integrated and synchronized to achieve more reliable news topic detection, and the contexts between different news topics are extracted automatically. Second, topic network and hyperbolic visualization are seamlessly integrated to support interactive navigation and exploration of large-scale collections of news videos at the topic level, so that users can gain deep insights of large-scale collections of news videos at the first glance. In such interactive topic network navigation and exploration process, users personal background knowledge can be exploited for selecting news topics of interest interactively, building up their mental models of news needs precisely and formulating their queries easily by selecting the visible news topics on the topic network directly. Our system can further recommend the relevant web news, the new search directions, and the most relevant news videos according to their importance and representativeness scores. Our experiments on large-scale collections of news videos have provided very positive results. ; published