Academic journal article Educational Technology & Society

Learning Analytics and Educational Data Mining in Practice: A Systematic Literature Review of Empirical Evidence

Academic journal article Educational Technology & Society

Learning Analytics and Educational Data Mining in Practice: A Systematic Literature Review of Empirical Evidence

Article excerpt

Introduction

The information overload, originating from the growing quantity of "Big Data" during the past decade, requires the introduction and integration of new processing approaches into everyday objects and activities ("ubiquitous and pervasive computing") (Cook & Das, 2012; Kwon & Sim, 2013). Handling large amounts of data manually is prohibitive. Several computational methods have been proposed in the literature to do this analysis.

In commercial fields, business and organizations are deploying sophisticated analytic techniques to evaluate rich data sources, identify patterns within the data and exploit these patterns in decision making (Chaudhuri, Dayal & Narasayya, 2011). These techniques combine strategic planning procedures with informational technology instruments, summarized under the term "Business Intelligence" (Eckerson, 2006; Jourdan, Rainer & Marshall, 2008). They constitute a well-established process that allows for synthesizing "vast amount of data into powerful decision making capabilities" (Baker, 2007, p. 2).

Recently researchers and developers from the educational community started exploring the potential adoption of analogous techniques for gaining insight into online learners' activities. Two areas under development oriented towards the inclusion and exploration of big data capabilities in education are Educational Data Mining (EDM) and Learning Analytics (LA) and their respective communities.

EDM is concerned with "developing, researching, and applying computerized methods to detect patterns in large collections of educational data that would otherwise be hard or impossible to analyze due to the enormous volume of data within which they exist" (Romero & Ventura, 2013, p. 12). Respectively, LA is an area of research related to business intelligence, web analytics, academic analytics, action analytics and predictive analytics. According to the definitions introduced during the 1st International Conference on Learning Analytics and Knowledge (LAK), LA is "the measurement, collection, analysis and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning and environments in which it occurs" (https://tekri.athabascau.ca/analytics/).

Explaining the previous definitions, LA and EDM constitute an ecosystem of methods and techniques (in general procedures) that successively gather, process, report and act on machine-readable data on an ongoing basis in order to advance the educational environment and reflect on learning processes. In general, these procedures initially emphasize on measurement and data collection and preparation for processing during the learning activities. Next, they focus on further analysis, reporting of data and interpretation of results, targeting to inform and empower learners, instructors and organization about performance and goal achievement, and facilitate decision making accordingly.

Both communities share similar goals and focus where learning science and data-driven analytics intersect. However, they differ in their origins, techniques, fields of emphasis and types of discovery (Chatti et al., 2012; Romero & Ventura, 2013; Siemens & Baker, 2012). Romero and Ventura (2013) presented an up-to-date comprehensive overview of the current state in data mining in education. In their overview, the authors do not present research results as empirical evidence. Their focus targets on the objectives, methods, knowledge discovery processes and tools adopted in EDM research. Analogous attempts were presented by Ferguson (2012) and Bienkowski et al. (2012) in the state of LA in 2012 and in an issue brief respectively.

All of these previous studies claim that as far as it concerns the approach to gaining insights into learning processes, LA adopts a holistic framework, seeking to understand systems in their full complexity. On the other hand, EDM adopts a reductionistic viewpoint by analyzing individual components, seeking for new patterns in data and modifying respective algorithms. …

Search by... Author
Show... All Results Primary Sources Peer-reviewed

Oops!

An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.