Race, religion or sex: what makes a superbowl ad controversial?

Advertisements that generate undue controversies can destroy an advertising campaign. However it is difficult to estimate the potential of controversies in advertisements through traditional methods such as customer surveys and market research. In this paper, we develop a controversy detection system based on initial comments on online advertisements posted on YouTube. We extract early YouTube comments on a collection of Superbowl advertisements and generate a comprehensive set of over 2500 semantic and linguistic features for automatically detecting controversies. Our results show good accuracy in early detection of controversies. The proposed data-driven approach can complement and greatly aid traditional approaches of market research.