Personalized Conversational Recommendation Systems

Our research goals are two-fold. First, we want to improve both interaction quality in recommendation systems and the utility of results returned by making them user adaptive and conversational. Second, we want to improve dialogue system performance by means of personalization. As such, our goals for user modeling differ from those commonly assumed in recommendation systems, such as improving accuracy or related measures like precision and recall. Our goals also differ from that of previous work in user modeling in dialogue systems [38,46,18,44], which emphasizes the ability to track the user's goals as a dialogue progresses, but which does not typically maintain models across multiple conversations. Our hypothesis is that improvements in efficiency and effectiveness can be achieved by using an unobtrusively obtained user model to help direct the system's conversational search for items to recommend. Our approach assumes that there is a large database of items from which to choose, and that a reasonably large number of attributes is needed to describe these items. Simpler techniques might suffice for situations where the database is small or items are easy to describe.