Uncovering Response Biases in Recommendation

Kyung-Wha Park, Byoung-Hee Kim, Tae-Suh Park, Byoung-Tak Zhang

Abstract: An user-specific tendency of biased movie rating is investigated, leading six identified types of rating pattern in a massive movie rating dataset. Based on the observed bias assumption, we propose a rescaling method of preferential scores by considering the rating types.  Experimental results show significant enhancement for movie recommendation systems.