Robot Interaction Styles for Conversation Practice in Second Language Learning

Olov Engwall,Anna Åhlund,José Lopes

doi:10.1007/s12369-020-00635-y

Abstract

Four different interaction styles for the social robot Furhat acting as a host in spoken conversation practice with two simultaneous language learners have been developed, based on interaction styles of human moderators of language cafés. We first investigated, through a survey and recorded sessions of three-party language café style conversations, how the interaction styles of human moderators are influenced by different factors (e.g., the participants language level and familiarity). Using this knowledge, four distinct interaction styles were developed for the robot: sequentially asking one participant questions at the time (Interviewer); the robot speaking about itself, robots and Sweden or asking quiz questions about Sweden (Narrator); attempting to make the participants talk with each other (Facilitator); and trying to establish a three-party robot–learner–learner interaction with equal participation (Interlocutor). A user study with 32 participants, conversing in pairs with the robot, was carried out to investigate how the post-session ratings of the robot’s behavior along different dimensions (e.g., the robot’s conversational skills and friendliness, the value of practice) are influenced by the robot’s interaction style and participant variables (e.g., level in the target language, gender, origin). The general findings were that Interviewer received the highest mean rating, but that different factors influenced the ratings substantially, indicating that the preference of individual participants needs to be anticipated in order to improve learner satisfaction with the practice. We conclude with a list of recommendations for robot-hosted conversation practice in a second language.

Highlights

Conversation practice is fundamental when learning to speak a second language (L2)
Mastery of Swedish is still important for integration in society in general and on the job market in particular. To respond to this need for Technology-enhanced learning (TEL) in second language learning of Swedish, we are currently engaged in a research project on collaborative robot-assisted language learning (RALL), in which we investigate how a social anthropomorphic robot can be used in spoken conversation practice with pairs of L2 learners of Swedish
The ANOVA showed no significant differences, but the trend is that learners at levels 1 and 2 rated Learning higher (μ1 = 3.7, μ2 = 3.5, σ = 1.0; 1.0, n = 14; 26) than those at lower and higher levels (μ0 = 3.3, μ3 = 3.1, σ = 1.6; 1.0, n = 10; 53). This is in line with the findings in [29], where we found that participants need to have a basic level in order to benefit from the conversation practice, but that more proficient learners require a more advanced conversation than is currently provided by the robot moderator

Summary

Introduction

Language cafés provide an important complement by practicing real-life oral skills in a semi-structured and allowing setting. Key concepts are that all interaction should be in the L2 language, that the topics should be universal enough to promote confidence and inclusion of all participants, and that all participants have a high acceptance for others’ language errors, hesitations and slow interaction. Using this implicit contract, language cafés follow the concepts of communicative language teaching [1] and collaborative language learning [2] and employ a constructivistic view of learning

Objectives

Methods

Results

Discussion

Conclusion