Mimi Adjei & Ana-Paula Correia
Over the years, educators have used various instructional methods and tracking strategies to address the educational needs of students. This process helps create personalized learning, a tailored approach to learning experiences focused on students’ strengths, skills, interests, and how the brain functions. (Personalizing Learning, n.d.). Learning analytics (LA) can explain unexpected learning behaviors, identify successful learning patterns, detect misconceptions and misplaced effort, introduce appropriate interventions, and increase users’ awareness of their own actions and progress (Society for Learning Analytics Research, 2019; Mangaroska & Giannakos, 2018).
In this review, students’ experience takes a constructivist and learner-centered approach. With multiple attempts to utilize LA in learning experience design, what is often overlooked is the need to properly frame interpretations within a socio-technical system. The intent is for students and instructors to use the data as a check on their intuition to stay data-informed as opposed to data-driven (Jimerson, 2015). This study aims to highlight the synergy of learning analytics with learning experiences.
The design and methods used in this study follow the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines. This approach includes a set of procedures widely used in systematic literature reviews: (1) developing the review criteria, (2) identifying the relevant literature from the databases, (3) screening and reviewing the literature, and (4) analyzing the selected literature. Twenty-seven studies meeting the inclusion criteria were analyzed for this study.
Multiple studies reveal that LA provides insights to assess learning behavior and how students interact with course content through the analysis of students’ log and academic performance data (Nunn et al., 2016; Yağcı, 2022). With LA, students can receive meaningful and timely feedback as they interact with course materials in the classroom. Complex data collected can produce real-time visualizations that encourage students’ reflections and growth. This paves the way for learner autonomy. Data collected is also a way to predict student performance and draw attention to the need for instructor intervention. From a critical perspective, there are also challenges with data tracking and collection, ethical and privacy issues (Pardo & Siemens, 2014). These are discussed in this review.
The findings of this systematic literature review identified the extent to which learning analytics can support data-informed learning in K-12 classrooms. How to bridge the existing theories of education research, learning sciences, and human-computer interaction with the application of learning analytics (Reimann, 2016) is another expected implication.
Mimi Adjei presenting at the 2023 Ohio State’s College of Education and Human Ecology Research Forum [February 2023].
References:
Jimerson, J. B. (2015). How are we approaching data-informed practice? Development of the Survey of Data Use and Professional Learning. Educational Assessment, Evaluation and Accountability, 28(1), 61–87.
Mangaroska, K., & Giannakos, M. N. (2018). Learning analytics for learning design: A systematic literature review of analytics-driven design to enhance learning. IEEE Transactions on Learning Technologies, 1(–1).
Nunn, S., Avella, J. T., Kanai, T., & Kebritchi, M. (2016). Learning analytics methods, benefits, and challenges in higher education: A systematic literature review. Online Learning, 20(2).
Pardo, A., & Siemens, G. (2014). Ethical and privacy principles for learning analytics. British Journal of Educational Technology, 45(3), 438–450.
Reimann, P. (2016). Connecting learning analytics with learning research: the role of design-based research. Learning: Research and Practice, 2(2), 130–142.
Siemens, G., & Gasevic, D. (2012). Guest editorial: Learning and knowledge analytics. Educational Technology and Society, 15(3), 1–2.
Society for Learning Analytics Research, (2019). What is Learning Analytics? Society for Learning Analytics Research (SoLAR).
Personalizing Learning, (n.d.). What is Personalized Learning? KnowledgeWorks.
Yağcı, M. (2022). Educational data mining: prediction of students’ academic performance using machine learning algorithms. Smart Learning Environments, 9(1).