Data is critical for educational institutions. Data helps to achieve better results in educational processes. While the concept of educational data has been in existence for some time, the term learning analytics (LA) has gained popularity as a crucial area of focus in recent years. The term LA refers to the systematic process of measuring, collecting, analyzing, and reporting data related to learners and their educational contexts. It can be said that there are four main elements of LA: data, analysis, report, and action. LA offers a range of benefits for education: Prediction of learner outcomes, personalized learning experiences, etc. Despite its benefits, LA raises important ethical concerns. In this chapter, the concept of learning analytics is introduced and its main dimensions are discussed.
TopIntroduction
Data is critical for educational institutions (Elayyan, 2021). Data helps to achieve better results in educational processes. The reasons for analyzing data can be listed as why learners fail exams or why they decide to drop out of the courses or why some subjects are not understood (Reid-Martinez, 2015). Data includes tracking learner tool usage, analyzing learner progress, learner-specific data, etc. (Osmanoglu et al., 2020). While the concept of educational data has been in existence for some time, the term Learning Analytics (LA) has gained popularity as a crucial area of focus in recent years (Macfadyen & Dawson, 2012).
LA has become a growing community of researchers and practitioners that has emerged over the last decade as an important area of technology-enhanced learning (Lang et al., 2022). The term of LA, which has many definitions in the literature, can be defined as follows. The term LA refers to the systematic process of measuring, collecting, analyzing, and reporting data related to learners and their educational contexts. The main purpose of LA is to gain an understanding of the learning process and enhance it, as well as to optimize the learning environments in which it occurs (Long & Siemens, 2011).
From this perspective, the most fundamental thing that LA emphasizes is to determine the efficacy of the learning experience (Guzmán-Valenzuela et al., 2021; Lee et al., 2020). What is meant by effectiveness can be considered as the acquisition of education-oriented knowledge and skills. Considering that the focus of instructional design is how to teach a subject better, LA has a strong relationship with the concept of instructional design (Lockyer & Dawson, 2011).
The field of LA is rapidly evolving and holds great potential for improving education. However, it is a complex and multifaceted discipline with various applications, primarily centered around the processing of large datasets. To harness the power of LA effectively, researchers and educators must possess a diverse skill set, encompassing data analysis, proficiency in web software languages, and methodological expertise (Avella et al., 2016; Baig et al., 2020).
This interdisciplinary nature of LA highlights its close ties to other fields, including Web analytics, academic analytics, educational data mining, action analytics, and business intelligence. These relationships are vital in understanding how data-driven insights can be applied to enhance educational processes and outcomes.
LA serves a diverse audience and has several practical applications (Lee et al., 2020):
Learners: LA provides learners with valuable feedback on their progress in courses. Dashboards offer insights into attendance, participation rates, quiz results, and assignment scores. Recommendations based on individual needs help learners become more effective learners.
Educators: Teachers can use LA to gain insights into factors influencing learner participation and adjust their teaching strategies accordingly. Analytical algorithms help align online behavior with predictive models, allowing educators to adapt their methods to improve learner engagement.
Program Coordinators: Coordinators can assess the performance of learner groups or entire programs using analytical data. They can evaluate the effectiveness of teaching methods and curricula, making data-driven decisions to enhance learning outcomes.
Researchers: LA data is a valuable resource for researchers exploring different teaching methods and course designs. It enables experiments and A/B testing to determine the most effective approaches for various types of learners and contexts.
Data sources for LA include Virtual Learning Environments (VLEs), Student Information Systems (SISs), and additional data from monitoring systems. VLEs offer rich data sources, especially in online learning environments, while SISs provide demographic and academic information. Other sources, such as library usage data, contribute to a comprehensive understanding of learner behavior and performance (Srinivasa & Muralidhar, 2020).
The technical infrastructure for LA is evolving, with competition among various software solutions. Institutions are seeking suitable platforms to consolidate and analyze data from multiple sources, with the goal of making data-driven decisions to enhance education.