This chapter provides a brief introduction to learning analytics (LA) to support teaching and learning. In doing so, it attempts to enhance the perspectives to organize educational communities to showcase emergent practices specifically for K-12 education for a better learning design for both learners and teachers. Thus, how data can transform learning environments to enhance learner engagement and performance together with the utilization of LA for educational purposes are scrutinized by means of evidence-based research in related literature to provide pedagogical applications of LA as a promising area of research.
TopLearning Analytics (La): Above And Beyond
“Data analytics and adaptive learning are two critical innovations gaining a foothold in higher education that we must continue to support, interrogate, and understand if we are to bend higher education’s iron triangle and realize the sector’s longstanding promise of catalyzing equitable success. The oppor- tunity and peril of these pioneering 21st century technologies (made availa- ble by recent advances in the learning sciences, high performance computing, cloud data storage and analytics, AI, and machine learning) requires our full engagement and study. Without the foundational and advanced insights compiled in this volume and continued careful measurement, transparency around assumptions and hypotheses testing, and open debate, we will fail to devise and implement both ethical and more equitable enhancements to the student experience – improvements that are both urgent and vital for real- izing higher education’s promise on delivering greater opportunity and value to current and future generations of students.”
(Rahim S. Rajan, Deputy Director, Bill & Melinda Gates Foundation)
In today’s time, it has increasingly become a commonplace chalk to support learning and teaching environment with technology. Yet, it does not only mean to utilize a specific type or form of technology to guarantee learner performance development, and/or success. Then, which types are more compatible to put forward success? How are we going to analyze the results? What is the best method for analysis? Does that information have something to tell teachers to positively impact their pedagogical practice(s)? Which type of technologies are more data rich?
At this point, learning analytics (LA) has emerged as a novel approach to provide responses to such questions by means of data collection, analysis, and application of the results to promote better learning by means of statistical techniques, interactive visuals, frameworks, and computer-aided modeling. Herein, the goal is to optimize learning for both learners and teachers to redefine better pedagogical strategies and speculate on potential pedagogies to provoke learner engagement in a fine-tuned alternate. As the data speculate on real-time analysis, learners can see their strengths and weaknesses on a subject-matter whereas teachers can observe their own educational efficacy. In each case, LA caters insights to all stakeholders irrespective of material being exploited, topic being covered, and activity leveraging in the classroom environment, even outside the classroom environment, just to improve learning and teaching (Elias, 2011).
Encompassing a myriad of models, algorithms, methods, and technologies to provide performance-based data, LA opens a window into the trajectories of learning and teaching to prioritize quality education. In doing so, the footprints of the learners can be extracted from the digital data to form educational databases to identify the achievement gap and provide remedial solutions to increase the level of achievement (Hwang et al., 2017). Herein, teachers do not only get a comprehensive view of learner progress but also monitor how learners are interacting with the course materials together with others (e.g., peers and teachers) in that clarification of the concepts through observation, questions, advice, and alternative views are of critical importance to maximize learning. LA can also be tool to support decision-making processes for course design and development. The results of the data analysis may require the improvement of course content and instructional resources on a regular basis. Besides, learners’ interactions can be dissolved through timely feedback which is one of the key features of the learning process that is of utmost importance for both learners and teachers (Brookhart, 2017), which can improve the learning outcomes in turn (Merceron et al., 2015) apart from the six aspects that LA can support to enhance the learning and teaching process (Wong, 2017).
These aspects can be noted as (1) enhancing learner retention; (2) backing up informed decision-making; (3) pinpointing cost-effectiveness; (4) comprehending learners’ behaviors; (5) establishing assistance to learners for self-paced learning; (6) giving feedback on a timely manner and providing intervention if needed. To note, these aspects are interactant to each other, albeit not segregated as entities.