Akademik Veri Yönetim Sistemi
Frontiers in Education, cilt.10, 2025 (ESCI)
Introduction: Artificial intelligence (AI)-powered chatbots are increasingly integrated into early childhood education; however, their contribution to children's social-emotional learning (SEL) has not been systematically synthesized. While evidence suggests that such technologies can support self-awareness, emotional regulation, and social interaction, research remains fragmented in terms of developmental appropriateness, ethical safeguards, and pedagogical alignment. This review addresses this gap by mapping the current state of knowledge on chatbot-supported SEL in early learning contexts. Methods: Following the PRISMA-ScR protocol, a comprehensive search was conducted across Scopus, Web of Science, ERIC, ScienceDirect, and SpringerLink for peer-reviewed studies published between January 2019 and March 2025. Inclusion criteria required studies to involve children aged 0–8, investigate chatbot-based interaction in educational settings, and examine at least one SEL domain. Data were charted and thematically synthesized according to research design, participant profile, technological features, and SEL competencies. Results: Of 205 records initially identified, 13 studies met the eligibility criteria. Most were published in 2023–2024 (76.9%). Nearly half employed experimental or intervention designs (46.2%), with smaller proportions focusing on design-based studies (30.8%), theoretical or ethical analyses (15.4%), and qualitative investigations (7.7%). Mapping against SEL domains indicated stronger emphasis on self-awareness and self-management (each 30.8%), with relatively limited coverage of social awareness (15.4%), relationship skills (15.4%), and responsible decision-making (23.1%). Frequently adopted technological affordances included natural language processing, emotion recognition, and multimodal interfaces, though adult mediation and long-term developmental effects were rarely addressed. Ethical considerations were also insufficiently examined. Discussion: The findings underscore the promise of AI-powered chatbots in advancing SEL during early childhood while highlighting significant gaps in empirical validation, theoretical grounding, and ethical responsibility. This review contributes a consolidated knowledge base to guide future research, pedagogical practice, and technology design, ensuring that chatbot applications in early learning environments are developmentally appropriate, ethically sound, and contextually meaningful.