Bibliometrics Analysis on Using Machine Learning Algorithms in Teacher Education Researches

Abstract

Machine learning (ML) techniques hold promise for innovating teacher preparation and development programs. However, the current state of research leveraging artificial intelligence in teacher-focused contexts remains unclear. This study undertook a systematic bibliometric analysis to characterize the emerging domain investigating ML applications for enhancing teacher effectiveness. Using the bibliographic R tool Bibliometrix, metadata of 740 English-language articles published during 2019-2023 extracted from Web of Science educational databases were examined to determine performance metrics, science mapping, citation networks, and research trends situating at the intersection of ML and teacher education. Document growth averaged 39.57% annually, with collaborations involving 87% of publications and 21.62% engaging international co-authorships. The USA led productivity metrics, though opportunities exist to expand geographical diversity. Analyses revealed research activity presently concentrates around employing ML for student analytics, assessment frameworks, and online learning environments. Highly cited works dealt with ML systems for evaluation and competency modeling of teachers rather than directly supporting pedagogical practice. Significant gaps persist exploring intelligent recommendation engines and affective computing chatbots tailored to teachers’ dynamic training needs and emotional responses. This bibliometric review synthesizes the contours and trends in investigating ML applications for augmenting teachers’ capabilities. Findings inform stakeholders to mobilize efforts strategically advancing this domain for enriching classrooms.