Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
102 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Educational data mining and learning analytics: An updated survey (2402.07956v1)

Published 10 Feb 2024 in cs.HC and cs.AI

Abstract: This survey is an updated and improved version of the previous one published in 2013 in this journal with the title data mining in education. It reviews in a comprehensible and very general way how Educational Data Mining and Learning Analytics have been applied over educational data. In the last decade, this research area has evolved enormously and a wide range of related terms are now used in the bibliography such as Academic Analytics, Institutional Analytics, Teaching Analytics, Data-Driven Education, Data-Driven Decision-Making in Education, Big Data in Education, and Educational Data Science. This paper provides the current state of the art by reviewing the main publications, the key milestones, the knowledge discovery cycle, the main educational environments, the specific tools, the free available datasets, the most used methods, the main objectives, and the future trends in this research area.

An Updated Survey on Educational Data Mining and Learning Analytics

The paper "Educational Data Mining and Learning Analytics: An Updated Survey" by Cristobal Romero and Sebastian Ventura offers a thorough examination of the developments in educational data mining (EDM) and learning analytics (LA) since their previous survey in 2013. As the field has advanced, this updated survey seeks to provide a current state of the art, covering key developments, tools, methods, and future directions.

Overview of the Field

The evolving landscape of educational data has necessitated robust techniques to analyze the vast repositories generated by e-learning platforms, institutional databases, and emerging educational environments like MOOCs and virtual learning. EDM and LA have emerged as pivotal methodologies in transforming raw educational data into actionable insights, aiding educators, administrators, and stakeholders in enhancing learning outcomes.

Educational Data Mining (EDM) focuses on developing and applying data mining techniques to discover patterns and build models from educational data. In contrast, Learning Analytics (LA) emphasizes measuring and analyzing learner data for optimizing learning experiences and environments. Both fields, despite some methodological overlaps, differ primarily in their research focus—EDM on technological challenges and LA on educational challenges.

Key Developments and Tools

The survey outlines significant growth in publications, with an increase in both books and peer-reviewed papers. The inclusion of various related concepts such as Academic Analytics, Big Data in Education, and Teaching Analytics reflects a broadening scope and acknowledgment of data-driven approaches in education.

The paper highlights diverse educational environments and the distinct data they produce. This necessitates tailored preprocessing and interpretation strategies to, for instance, anonymize sensitive data and ensure ethical use in accordance with privacy guidelines.

A variety of tools are available for conducting EDM and LA research, ranging from general-purpose frameworks like RapidMiner and Weka, to more specialized tools such as DataShop and Moodle Analytics API. These tools provide educators and researchers with capabilities to process large datasets and glean insights relevant to educational contexts.

Methods and Applications

A comprehensive taxonomy of methods and applications is provided, reflecting the complexity and versatility of EDM and LA. Key methods include:

  • Predictive Modeling: Applied to forecast student performance.
  • Clustering and Pattern Mining: Used to identify commonalities and differences in student behavior and learning pathways.
  • Process Mining: Employed to derive insights from event logs in e-learning systems.

Applications are varied, addressing multiple stakeholders from students to educational policymakers, with objectives ranging from enhancing personalized learning to curriculum optimization and institutional decision-making.

Implications and Future Directions

The implications of EDM and LA are both practical and theoretical. Practically, these methodologies aid in creating adaptive learning environments, inform policy decisions, and enhance instructional strategies. Theoretically, they contribute to a deeper understanding of learning processes and behavioral analytics.

The authors stress ongoing challenges and future opportunities, highlighting the need for more general-purpose EDM/LA tools and fostering a data-driven culture in educational institutions. Furthermore, emerging technological trends such as IoT and pervasive neurotechnology could revolutionize the depth and breadth of data available, promising more personalized and context-aware learning experiences.

Conclusion

This updated survey meticulously details the strides made in educational data mining and learning analytics, positioning these disciplines at the forefront of educational innovation. For researchers and practitioners, it provides a foundation to understand recent developments, equips them with the knowledge to leverage current tools, and proposes future directions that promise to further transform the educational landscape.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. C. Romero (130 papers)
  2. S. Ventura (137 papers)
Citations (543)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets

Youtube Logo Streamline Icon: https://streamlinehq.com