Abstract
This article aims at offering an overview of educational data mining and learning analytics and highlighting their essential role in improving 21st century education. Hence, it analyzes their concepts, goes over the recent literature, and extracts invaluable information according to the results and outcomes of related studies. Furthermore, it discusses their use in educational settings, examines their benefits, and suggests ways to address some of the current open challenges, issues, and limitations. In addition, it presents the summary of the main findings, draws conclusions, and provides directions for future research. Based on the results, educational data mining and learning analytics fields can significantly influence the current educational system and provide opportunities for new learner-centered tools and smart learning environments that provide customized experiences and meet students' specific needs to be developed. Finally, it was evident that for the complete adoption of these fields, a data-driven culture should be followed by the educational institutions.
TopBackground
A lot of emphasis is put on the collection, processing and analysis of data so as to better comprehend and optimize the learning and teaching process and outcomes. Educational data mining and learning analytics are two fields which are becoming more popular due to this fact.
Educational data mining is a specialized form of data mining which focuses on educational environments. It aims at addressing educational issues by analyzing data and developing models that enhance the overall learning experience and outcomes and increase the institutional effectiveness (Baker and Yacef, 2009; Dutt et al., 2017). It is worth noting that due to its nature, it can be applied at all educational levels (Saa, 2016). According to the Educational Data Mining community, educational data mining can be defined as “an emerging discipline, concerned with developing methods for exploring the unique and increasingly large-scale data that come from educational settings and using those methods to better understand students, and the settings which they learn in” (Educational Data Mining Community, 2021). Based on this particular definition, it is apparent that educational data mining constitutes an interdisciplinary field. Therefore, it exploits machine learning, statistics, information retrieval, recommender systems and other innovative technologies and techniques (Romero & Ventura, 2010).
Key Terms in this Chapter
Learning Analytics: It is an interdisciplinary scientific field which examines the way in which data can be used to improve the overall learning quality and to address a variety of educational challenges and issues.
Data Mining: It is also known as Knowledge Discovery in Databases (KDD) and refers to the use of algorithms, techniques, and methods in order to generate knowledge by discovering novel and useful information, patterns, relationships or structures from large data collections.
Educational Data Mining: It is a specialized form of data mining which focuses on utilizing data that derives from educational environments and aims at addressing educational issues and enhancing the overall learning experience, performance, and outcomes.
Big Data: An exponentially increasing volume of heterogeneous data which is differentiated from traditional data based on its volume, variety, veracity, velocity, and value.