Pendidikan editorial
Open AccessOA2022
Using Chatbots as AI Conversational Partners in Language Learning
This study examines the knowledge, satisfaction, and perceptions of 176 pre-service teachers from Spain and Poland regarding the integration of conversational AI (Replika, Kuki, Wysa) in language learning. Results show positive attitudes and perceived ease of use, but more moderate behavioral intention, with some gender differences.
Jose Belda-Medina; José Ramón Calvo-Ferrer· Applied Sciences· 2022· DOI 10.3390/app12178427
The core problem
Recent advances in Artificial Intelligence (AI) and machine learning have paved the way for the increasing adoption of chatbots in language learning. Research published to date has mostly focused on chatbot accuracy and chatbot–human communication from students’ or in-service teachers’ perspectives. This study aims to examine the knowledge, level of satisfaction and perceptions concerning the integration of conversational AI in language learning among future educators. The research addresses a gap by focusing on pre-service teachers, who are key stakeholders in the future implementation of such technologies. The study is set in two educational settings, Spain and Poland, and involves 176 undergraduates. The authors designed a learning module about AI and language learning, including an ad hoc model called the Chatbot–Human Interaction Satisfaction Model (CHISM), to evaluate linguistic and technological features of three conversational agents: Replika, Kuki, and Wysa.
Innovation
This mixed-method research used convenience sampling to recruit 176 undergraduates from two educational settings: Spain (n = 115) and Poland (n = 61). Participants interacted autonomously with three conversational agents (Replika, Kuki, Wysa) over a four-week period. A learning module about Artificial Intelligence and language learning was specifically designed for this research, including the Chatbot–Human Interaction Satisfaction Model (CHISM), which was used by teacher candidates to evaluate different linguistic and technological features of the three conversational agents. Quantitative and qualitative data were gathered through a pre-post-survey based on the CHISM and the TAM2 (technology acceptance) models and a template analysis (TA). Data were analyzed using IBM SPSS 22 and QDA Miner software. The CHISM model likely includes constructs such as perceived ease of use (PeU), attitudes (AT), and behavioral intention (BI), as these are mentioned in the results. The mixed-methods design allowed for triangulation of quantitative survey data with qualitative insights from template analysis.
Introduction
Recent advances in Artificial Intelligence (AI) and machine learning have paved the way for the increasing adoption of chatbots in language learning. Research published to date has mostly focused on chatbot accuracy and chatbot–human communication from students’ or in-service teachers’ perspectives. This study aims to examine the knowledge, level of satisfaction and perceptions concerning the integration of conversational AI in language learning among future educators. The research addresses a gap by focusing on pre-service teachers, who are key stakeholders in the future implementation of such technologies. The study is set in two educational settings, Spain and Poland, and involves 176 undergraduates. The authors designed a learning module about AI and language learning, including an ad hoc model called the Chatbot–Human Interaction Satisfaction Model (CHISM), to evaluate linguistic and technological features of three conversational agents: Replika, Kuki, and Wysa.
Why it matters
The findings indicate that future educators are generally positive about the use of conversational AI in language learning, especially regarding ease of use and attitudes. This aligns with the growing interest in integrating AI tools in education. However, the moderate behavioral intention scores suggest that while pre-service teachers see the value, they may not yet be fully committed to adopting these tools in their own teaching practices. This could be due to concerns about effectiveness, lack of training, or other barriers. The gender differences in satisfaction with chatbot design and topics of interaction point to the need for more personalized and inclusive chatbot designs. The study contributes to the field by applying the CHISM model and TAM2 to evaluate chatbots from the perspective of future educators. Limitations include the convenience sampling and the short duration of interaction. Future research should explore long-term effects and include more diverse populations. Overall, the study underscores the potential of chatbots as conversational partners in language learning and the importance of preparing teachers for their integration.
Who should read this
Pembaca Research Digest dan praktisi rumpun ini.
Opening member content…