Chatbots Language Design: The Influence of Language Variation on User Experience with Tourist Assistant Chatbots

Abstract

Chatbots are often designed to mimic social roles attributed to humans. However, little is known about the impact of using language that fails to conform to the associated social role. Our research draws on sociolinguistic to investigate how a chatbot’s language choices can adhere to the expected social role the agent performs within a context. We seek to understand whether chatbots design should account for linguistic register. This research analyzes how register differences play a role in shaping the user’s perception of the human-chatbot interaction. We produced parallel corpora of conversations in the tourism domain with similar content and varying register characteristics and evaluated users’ preferences of chatbot’s linguistic choices in terms of appropriateness, credibility, and user experience. Our results show that register characteristics are strong predictors of user’s preferences, which points to the needs of designing chatbots with register-appropriate language to improve acceptance and users’ perceptions of chatbot interactions.

Artificial Intelligence-Enabled Chatbots in Mental Health: A Systematic Review

“…Latent Semantic Analysis (LSA) and AIML are widely used to create chatbots. In the form of a vector representation, the technology is used to find correlations among words [17]. LSA is able to react to unanswered questions, while AIML may be used to address template-based questions like welcomes and general inquiry [18].…”

Chatbot Recommender Systems in Tourism: A Systematic Review and a Benefit-Cost Analysis

“…Very often, online users are communicating with AI technologies without even knowing. Recent research indicated that more chatbots (as opposed to human customer services representatives) are on the other end of the line, replying to the consumers' questions [28][29][30].…”

Desenho de Linguagem de Chatbots: influência da variação da linguagem na experiência do usuário com chatbot assistente de turismo

“…Do ponto de vista técnico, os chatbots precisam responder adequadamente às perguntas do usuário [Brandtzaeg and Følstad 2018], o que tem sido amplamente explorado na literatura. Do ponto de vista social, os chatbots precisam retratar habilidades sociais que se adequem ao modelo mental do usuário de uma conversa [Feine et al 2019, Chaves et al 2022.…”

“…O estudo apresentado em [Chaves et al 2022] avalia se o registro poderia encapsular a possível variac ¸ão de estilo que um chatbot pode usar, o que pode possivelmente melhorar as percepc ¸ões de adequac ¸ão da linguagem pelo usuário. Este estudo é fundamental para a colaborac ¸ão entre humanos e agentes conversacionais por afetar, de acordo com os resultados do estudo, a credibilidade e presenc ¸a social do agente durante a interac ¸ão.…”