Linking visual concept detection with viewer demographics

The estimation of demographic target groups for web videos -- with applications in ad targeting -- poses a challenging problem, as the textual description and view statistics available for many clips is extremely sparse. Therefore, the goal of this paper is to link a clip's popularity across different viewer ages and genders on the one hand with the video content on the other: Employing user comments and user profiles on YouTube, we show that there is a strong correlation between demographic target groups and semantic concepts appearing in the video (like "teenage male" and "skateboarding"). Based on this observation, we suggest two approaches: First, the demographic target group of a clip is predicted automatically via a content-based concept detection. Second, should sufficient view statistics already give a good impression of a video's audience, we show that this information can serve as a valuable additional signal to disambiguate concept detection. Our experimental results on a dataset of 14,000 YouTube clips commented by 1 mio. users show that -- though content-based viewership estimation is a challenging problem -- suitable demographic groups can be suggested by concept detection. Also, a combination with demographic information as an additional signal leads to relative improvements of concept detection accuracy by 47%.