Modularized User Modeling in Conversational Recommender Systems [chapter]

Pontus Wärnestål
2005 Lecture Notes in Computer Science  
This thesis examines recommendation dialogue, in the context of dialogue strategy design for conversational recommender systems. The purpose of a recommender system is to produce personalized recommendations of potentially useful items from a large space of possible options. In a conversational recommender system, this task is approached by utilizing natural language recommendation dialogue for detecting user preferences, as well as for providing recommendations. The fundamental idea of a
more » ... sational recommender system is that it relies on dialogue sessions to detect, continuously update, and utilize the user's preferences in order to predict potential interest in domain items modeled in a system. Designing the dialogue strategy management is thus one of the most important tasks for such systems. Based on empirical studies as well as design and implementation of conversational recommender systems, a behavior-based dialogue model called bcorn is presented. bcorn is based on three constructs, which are presented in the thesis. It utilizes a user preference modeling framework (preflets) that supports and utilizes natural language dialogue, and allows for descriptive, comparative, and superlative preference statements, in various situations. Another component of bcorn is its message-passing formalism, pcql, which is a notation used when describing preferential and factual statements and requests. bcorn is designed to be a generic recommendation dialogue strategy with conventional, information-providing, and recommendation capabilities, that each describes a natural chunk of a recommender agent's dialogue strategy, modeled in dialogue behavior diagrams that are run in parallel to give rise to coherent, flexible, and effective dialogue in conversational recommender systems. Three empirical studies have been carried out in order to explore the problem space of recommendation dialogue, and to verify the solutions put forward in this i ii Abstract work. Study I is a corpus study in the domain of movie recommendations. The result of the study is a characterization of recommendation dialogue, and forms a base for a first prototype implementation of a human-computer recommendation dialogue control strategy. Study II is an end-user evaluation of the acorn system that implements the dialogue control strategy and results in a verification of the effectiveness and usability of the dialogue strategy. There are also implications that influence the refinement of the model that are used in the bcorn dialogue strategy model. Study III is an overhearer evaluation of a functional conversational recommender system called CoreSong, which implements the bcorn model. The result of the study is indicative of the soundness of the behavior-based approach to conversational recommender system design, as well as the informativeness, naturalness, and coherence of the individual bcorn dialogue behaviors. Preface Over the years that this research has been carried out, I have tried to keep in mind that research on conversational interaction with machines in the end must support real people when carrying out their tasks. Just like dialogue, this turns out to be a two-way street: The task of writing this thesis would not have been completed without the support of, and conversations with, real people. First of all, I am indebted to Arne Jönsson, my main supervisor. He has guided and supported me over the years, and enthusiastically engaged in critical discussions about a great many topics. My secondary supervisor, Lars Degerstedt, has been a great influence and patiently discussed, and opened up my eyes for, many issues of engineering and technological aspects of software design and development. Apart from being great supervisors, you have been great collaborators and co-workers.
doi:10.1007/11527886_78 fatcat:c6lfkkv35vhppjqkuhialz5fla