Search

Artificial intelligence (AI) chatbots are gaining increasing popularity in education. Due to their increasing popularity, many empirical studies have been devoted to exploring the effects of AI chatbots on students' learning outcomes. The proliferation of experimental studies has highlighted the need to summarize and synthesize the inconsistent findings about the effects of AI chatbots on students' learning outcomes. However, few reviews focused on the meta‐analysis of the effects of AI chatbots on students' learning outcomes. The present study performed a meta‐analysis of 24 randomized studies utilizing Stata software (version 14). The main goal of the current study was to meta‐analytically examine the effects of AI chatbots on students' learning outcomes and the moderating effects of educational levels and intervention duration. The results indicated that AI chatbots had a large effect on students' learning outcomes. Moreover, AI chatbots had a greater effect on students in higher education, compared to those in primary education and secondary education. In addition, short interventions were found to have a stronger effect on students' learning outcomes than long interventions. It could be explained by the argument that the novelty effects of AI chatbots could improve learning outcomes in short interventions, but it has worn off in the long interventions. Future designers and educators should make attempt to increase students' learning outcomes by equipping AI chatbots with human‐like avatars, gamification elements and emotional intelligence. Practitioner notesWhat is already known about this topicIn recent years, artificial intelligence (AI) chatbots have been gaining increasing popularity in education.Studies undertaken so far have provided conflicting evidence concerning the effects of AI chatbots on students' learning outcomes.There has remained a paucity of meta‐analyses synthesizing the contradictory findings about the effects of AI chatbots on students' learning outcomes.What this paper addsThis study, through meta‐analysis, synthesized these recent findings about the effects of AI chatbots on students' learning outcomes.This study found that AI chatbots could have a large effect on students' learning outcomes.This study found that the effects of AI chatbots were moderated by educational levels and intervention duration.Implications for practice and/or policyAI chatbot designers could make AI chatbots better by equipping AI chatbots with human‐like avatars, gamification elements and emotional intelligencePractitioners and/or teachers should draw attention to the positive and negative effects of AI chatbots on students.Considering the importance of ChatGPT, more research is required to develop a better understanding of the effects of ChatGPT in education.More research is needed to examine the mechanisms underlying the effects of AI chatbots on students' learning outcomes. [ABSTRACT FROM AUTHOR]

Abstract Concerns regarding the potential risks associated with learners’ misusing ChatGPT necessitate an extensive investigation into learner attitudes towards ChatGPT-assisted language learning. This study adopts a mixed-method approach, combining structural equation modeling techniques and interviews. It aims to examine the influencing factors of learner attitudes regarding ChatGPT-assisted language learning under the extended three-tier technology use model from an interdisciplinary perspective, including the technology acceptance model, etc. The study finds that information system quality and hedonic motivation are more significant in contributing to performance expectancy and perceived satisfaction compared to self-regulation in ChatGPT-assisted language learning. Behavioral intention is a better predictor of learning effectiveness in ChatGPT-assisted language learning than perceived satisfaction and performance expectancy. This research also examines the partial or full mediating effects of behavioral intention and performance expectancy between other variables. Although this study is limited by some aspects (e.g., the outdated version of ChatGPT-3 or ChatGPT-3.5), it holds substantial implications for future practice and research. It appeals to more attention from future developers on hedonic motivation and information services of ChatGPT and from future researchers on a more comprehensive insight into influencing factors of learner attitudes towards ChatGPT-assisted language learning. [ABSTRACT FROM AUTHOR]