An investigation on the user interaction modes of conversational recommender systems for the music domain

Abstract

Conversational Recommender Systems (CoRSs) implement a paradigm that allows users to interact in natural language with the system for defining their preferences and discovering items that best fit their needs. CoRSs can be straightforwardly implemented as chatbots that, nowadays, are becoming more and more popular for several applications, such as customer care, health care, and medical diagnoses. Chatbots implement an interaction based on natural language, buttons, or both. The implementation of a chatbot is a challenging task since it requires knowledge about natural language processing and human-computer interaction. A CoRS might be particularly useful in the music domain since music is generally enjoyed in contexts when a standard interface cannot be exploited (driving, doing homeworks, running). However, there is no work in the literature that analytically compares different interaction modes for a conversational music recommender system. In this paper, we focus on the design and implementation of a CoRS for the music domain. Our CoRS consists of different components. The system implements content-based recommendation, critiquing and adaptive strategies, as well as explanation facilities. The main innovative contribution is that the user can interact through different interaction modes: natural language, buttons, and mixed. Due to the lack of available datasets for testing CoRSs, we carried out an in vivo experimental evaluation with the goal of investigating the impact of the different interaction modes on the recommendation accuracy and on the cost of interaction for the final user. The experiment involved 110 people, and 54 completed the whole process. The analysis of the results shows that the best interaction mode is based on a mixed strategy that combines buttons and natural language. In addition, the results allow to clearly understand which are the steps in the dialog that are particularly strenuous for the user.

Preface to the Special Issue on user modeling for personalized interaction with music

“…Both the papers Narducci et al (2019) and Kamehkhosh et al (2019) show the importance of the user intent, which has been neglected in the past for the more Preface to the Special Issue on user modeling for personalized… accessible variables of context. Other user-centric variables, such as affect and personality, have also been identified in related work as important and will likely be up-and-coming topics in future research.…”

“…This special issue contains articles that contribute to the state of the art on (a) personalized user interfaces for music (Jin et al 2019;Narducci et al 2019) and (b) playlist creation (Kamehkhosh et al 2019).…”

“…The paper An investigation on the user interaction modes of conversational recommender systems for the music domain (Narducci et al 2019) addresses the issue of how to design conversational recommender systems for music. The authors evaluated several approaches to the design of a conversational user interface and concluded, based on a user study, that the highest user acceptance of such an interface is when a mixed approach is used, i.e., allowing the user to interact both with natural language and buttons.…”

Implementation of Online E –Auction to Overcome the Problem of Corruption with Effective and Efficient Procurement with Transparency

“…They don't have to go to any other place, they can get that feedback and suggestions column like when they are registered users during auctioning process meanwhile at the same platform they can also have that suggestion option without the wastage of time. [20]…”

A Socially-Aware Conversational Recommender System for Personalized Recipe Recommendations

“…Rather than focusing on system's dialogue policy or strategies, some other works try to find the best way for users to interact with a recommender system. The authors in [19] investigate different interaction modes by objectively comparing three versions of a same music recommender systems. The first one used buttons to interact with users, the second one used free text, and the last one was a hybrid version that used buttons whenever there was a need to disambiguate.…”