Scholarlink

<p>The swift rise of technology-driven educational environments mandates the use of advanced analytics so as to enhance learning outcomes. An emerging technique, multi-modal learning analytics (MMLA) uses a variety of data sources, including behavioural, cognitive, and interactional measures, to offer thorough insights on learner engagement and achievement. By mapping research trends, notable contributors, and thematic advances in the field, this study offers a bibliometric analysis of MMLA in technologically enabled educational settings. To attempt to identify publication distribution trends, prominent authors, institutional affiliations, and collaboration networks, 77 peer-reviewed manuscripts&#xa0;published between 2010 and 2024 were analysed using Scopus as the main database. Results show that research on&#xa0;MMLA has grown significantly since 2016, with noteworthy contributions from&#xa0;Germany and United Kingdom. Personalised learning, predictive analytics, and artificial intelligence are increasingly intersecting, according to co-authorship and keyword analysis. It also&#xa0;introduces the Data–Pedagogy Alignment Framework, a theoretical structure that links instructional design and adaptive learning in technologically driven contexts with bibliometric insights. The study also points out areas that require further study, including the areas of ethical issues, MMLA’s scalability in various educational contexts, and the use of real-time analytics. This work advances the knowledge of how MMLA might improve adaptive learning and guide data-driven educational decisions by synthesising the body of existing literature and outlining potential research directions.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Mapping multi-modal learning analytics in techno-driven learning environments: a bibliometric analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年11月3日

查看全文
  • Vaibhav Verma,
  • Jijo Varghese

摘要

The swift rise of technology-driven educational environments mandates the use of advanced analytics so as to enhance learning outcomes. An emerging technique, multi-modal learning analytics (MMLA) uses a variety of data sources, including behavioural, cognitive, and interactional measures, to offer thorough insights on learner engagement and achievement. By mapping research trends, notable contributors, and thematic advances in the field, this study offers a bibliometric analysis of MMLA in technologically enabled educational settings. To attempt to identify publication distribution trends, prominent authors, institutional affiliations, and collaboration networks, 77 peer-reviewed manuscripts published between 2010 and 2024 were analysed using Scopus as the main database. Results show that research on MMLA has grown significantly since 2016, with noteworthy contributions from Germany and United Kingdom. Personalised learning, predictive analytics, and artificial intelligence are increasingly intersecting, according to co-authorship and keyword analysis. It also introduces the Data–Pedagogy Alignment Framework, a theoretical structure that links instructional design and adaptive learning in technologically driven contexts with bibliometric insights. The study also points out areas that require further study, including the areas of ethical issues, MMLA’s scalability in various educational contexts, and the use of real-time analytics. This work advances the knowledge of how MMLA might improve adaptive learning and guide data-driven educational decisions by synthesising the body of existing literature and outlining potential research directions.