Investigation of user rating behavior depending on interaction methods on smartphones

Recommender systems are commonly based on user ratings to generate tailored suggestions to users. Instabilities and in- consistencies in these ratings cause noise, reduce the quality of recommendations and decrease the users' trust in the sys- tem. Detecting and addressing these instabilities in ratings is therefore very important. In this work, we investigate the inuence of interaction methods on the users' rating behav- ior as one possible source of noise in ratings. The scenario is a movie recommender for smartphones. We considered three different input methods and also took possible distractions in the mobile scenario into account. In a conducted user study, participants rated movies using these different inter- action methods while either sitting or walking. Results show that the interaction method inuences the users' ratings. Thus, these effects contribute to rating noise and ultimately affect recommendation results.