IAI MovieBot: A Conversational Movie Recommender System

TL;DR

This paper introduces IAI MovieBot, an open-source conversational movie recommender system that supports multi-turn dialogues, multi-modal interactions, and adapts to changing user preferences, implemented as a Telegram channel.

Contribution

It presents a novel framework combining dialogue flow, multi-modal chat, and preference adaptation for conversational movie recommendations.

Findings

Open source implementation available

Supports multi-turn, multi-modal conversations

Effectively handles dynamic user preferences

Abstract

Conversational recommender systems support users in accomplishing recommendation-related goals via multi-turn conversations. To better model dynamically changing user preferences and provide the community with a reusable development framework, we introduce IAI MovieBot, a conversational recommender system for movies. It features a task-specific dialogue flow, a multi-modal chat interface, and an effective way to deal with dynamically changing user preferences. The system is made available open source and is operated as a channel on Telegram.