ThumbReels: query sensitive web video previews based on temporal, crowdsourced, semantic tagging

During online search, the user's expectations often differ from those of the author. This is known as the "intention gap" and is particularly problematic when searching for and discriminating between online video content. An author uses description and meta-data tags to label their content, but often cannot predict alternate interpretations or appropriations of their work. To address this intention gap, we present ThumbReels, a concept for query-sensitive video previews generated from crowdsourced, temporally defined semantic tagging. Further, we supply an open-source tool that supports on-the-fly temporal tagging of videos, whose output can be used for later search queries. A first user study validates the tool and concept. We then present a second study that shows participants found ThumbReels to better represent search terms than contemporary preview techniques.