IRF: Interactive Recommendation through Dialogue

TL;DR

This paper introduces IRF, a framework that enhances recommender systems with dialogue-based interactions to improve user trust, satisfaction, and transparency by providing explanations and refining recommendations through user dialogue.

Contribution

The paper presents a generic middleware layer that adds interactive dialogue functionalities to existing non-interactive recommender systems, enabling better user engagement.

Findings

Framework effectively integrates dialogue interactions into recommender systems.

Improves user trust and satisfaction through explanations and preference refinement.

Enhances recommendation relevance via dialogue-based preference elicitation.

Abstract

Recent research focuses beyond recommendation accuracy, towards human factors that influence the acceptance of recommendations, such as user satisfaction, trust, transparency and sense of control.We present a generic interactive recommender framework that can add interaction functionalities to non-interactive recommender systems.We take advantage of dialogue systems to interact with the user and we design a middleware layer to provide the interaction functions, such as providing explanations for the recommendations, managing users preferences learnt from dialogue, preference elicitation and refining recommendations based on learnt preferences.