Corpus Design for Studying Linguistic Nudges in Human-Computer Spoken Interactions

Proceedings of the 13th Conference on Language Resources and Evaluation (LREC 2022), pages 4079–4087 Marseille, 20-25 June 2022 © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0 4079 Corpus Design for Studying Linguistic Nudges in Human-Computer Spoken Interactions Natalia Kalashnikova∗†, Serge Pajak¶†, Fabrice Le Guel¶†, Ioana Vasilescu∗ Gemma Serrano‡, Laurence Devillers∗§ ∗LISN-CNRS, †Universit´e Paris-Saclay, ¶RITM, ‡Coll`ege des Bernardins, §Sorbonne-University natalia.kalashnikova@limsi.fr, serge.pajak@universite-paris-saclay.fr, fabrice.le-guel@universite-paris-saclay.fr, ioana@limsi.fr, gemma.serrano@collegedesbernardins.fr, devil@limsi.fr Abstract In this paper, we present the methodology of corpus design that will be used to study the comparison of influence between linguistic nudges with positive or negative influences and three conversational agents: robot, smart speaker, and human. We recruited forty-nine participants to form six groups. The conversational agents first asked the participants about their willingness to adopt five ecological habits and invest time and money in ecological problems. The participants were then asked the same questions but preceded by one linguistic nudge, with positive or negative influence. The comparison of standard deviation and mean metrics of differences between these two notes (before the nudge and after) showed that participants were mainly affected by nudges with positive influence, even though several nudges with negative influence decreased the average note. In addition, participants from all groups were willing to spend more money than time on ecological problems. In general, our experiment’s early results suggest that a machine agent can influence participants to the same degree as a human agent. A better understanding of the power of influence of different conversational machines and the potential of influence of nudges of different polarities will lead to the development of ethical norms of human-computer interactions. Keywords: linguistic nudges, corpus design, human-computer spoken interactions 1. Introduction The concept of nudges was highlighted in Economics by Thaler and Sunstein (2008). They defined nudges as techniques of indirect suggestion and positive rein- forcement that can influence people’s choices while not being a direct restriction of their choices. Importantly, a nudge should improve social welfare but it can also work against your interests (Thaler, 2018). In this study, a ”nudge with positive influence” steers a participant to adopt a habit by presenting positive side of the consequences of this habit. The ”nudge with negative influence” focuses on the negative side of a habit’s outcomes, pushing a participant in the op- posite direction (not adopting this habit). The terms ”positive” and ”negative” indicate whether information presents advantages (positive) or disadvantages (nega- tive) of a habit. The explicit topic of the conversation between con- versational agents and participants is their attitude to- wards the climate issues and their ecological practices. People today constantly receive messages about envi- ronmental issues that motivate them to help the envi- ronment. When people receive information that goes against mainstream, it may require more cognitive ef- fort for them to process it. In the domain of spoken interactions, linguistic nudges can be used by conversational agents and connected ob- jects to simplify people’s lives. However, there are a few limits of ethical norms for a conversational agent to enter a …

Content truncated to 500 words