Towards Boosting Video Popularity via Tag Selection

Video content abounds on the Web. Although viewers may reach items via referrals, a large portion of the audience comes from keywordbased search. Consequently, the textual features of multimedia content (e.g., title, description, tags) will directly impact the view count of a particular item, and ultimately the advertisement-generated revenue. This study makes progress on the problem of automating tag selection for online videos with the goal of increasing viewership. It brings two major insights: first, it describes a methodology to construct a ground truth to evaluate methods that aim to improve social content popularity; second, it provides evidence that the tags on existing YouTube videos can be improved by an automated tag recommendation process even for a sample of well curated videos; finally, it suggests a roadmap to explore low-cost techniques either based on crowdsourcing or on tag recommendation algorithms to improve the quality of tags for online video content. Copyright c © by the paper’s authors. Copying permitted only for private and academic purposes. In: S. Papadopoulos, P. Cesar, D. A. Shamma, A. Kelliher, R. Jain (eds.): Proceedings of the SoMuS ICMR 2014 Workshop, Glasgow, Scotland, 01-04-2014, published at http://ceur-ws.org