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 inconsistencies in these ratings cause noise, reduce the quality of recommendations and decrease the users’ trust in the system. Detecting and addressing these instabilities in ratings is therefore very important. In this work, we investigate the influence of interaction methods on the users’ rating behavior 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 interaction methods while either sitting or walking. Results show that the interaction method influences the users’ ratings. Thus, these effects contribute to rating noise and ultimately affect recommendation results.