The use of learning analytics and educational data mining to analyze teachers' teaching in online environments: a systematic literature review

• Published in: Interactive learning environments Vol. 33; no. 5; pp. 3317 - 3332
• Main Authors: Chen, Mu-Sheng, Hsu, Ting-Chia, Tu, Yun-Fang
• Format: Journal Article
• Language: English
• Published: Routledge 28.05.2025
• Subjects: Bibliometric analysis; educational data mining; machine learning; online learning platforms
• ISSN: 1049-4820; 1744-5191
• DOI: 10.1080/10494820.2024.2443070

Learning analytics and educational data mining aim to enhance teaching and learning outcomes by utilizing data and analytical methods. Online learning systems provide a wealth of data that enable educators to understand students' needs and offer appropriate support. This study used bibliometric analysis to examine the distribution of research subjects, educational stages, pedagogical approaches, machine learning algorithms, algorithm evaluation, and keywords in online learning from 2013 to 2022, encompassing the pre-pandemic, mid-pandemic, and post-pandemic periods. The findings indicated that the analyzed studies primarily focused on analyzing students' experiences in online learning systems, while paying limited attention to teachers' perspectives. Additionally, the majority of research concentrated on higher education, with insufficient attention given to pre-college education. Regarding pedagogical approaches in online learning environments, there was a notable absence of detailed descriptions of teaching processes, with greater emphasis placed on the interaction between students and online learning platforms. The study also examined the evolution of keywords across three periods: the pre-pandemic (2013-2018), the mid-pandemic (2019-2020), and the post-pandemic (2021-2022) periods. Finally, several recommendations for future research are provided.