Learning Analytics: Trends and Challenges

Learning analytics is used in Technology Enhanced Learning (TEL) to track the learning progress and empower educators and learners to make well-informed data-driven decisions. It is a multi-disciplinary field involving machine learning, artificial intelligence, information retrieval, educational data mining, recommender systems, statistics, visualization, and personalized adaptive learning. Many researchers have highlighted the need for further effort not only to automatically collect a vast number of learners' data but also to provide useful insights and sense-making as well as to use them for further improvements in the learning process. By leveraging learning analytics students, faculty, and administrators can improve learning and course outcomes, and develop more engaged and effective teaching and learning techniques. Learning analytics can also surface trends across schools or other scopes of interest as for example within specific programs, subject disciplines, class sizes, or other contexts. Analytics' questions, insights, and perspectives from each audience can inform and guide the adjustment of integrated analytics to each of these analytics' audiences.

This Research Topic is dedicated to the challenges of collecting, analyzing, reporting, and utilizing data with the specific intent to improve learning. Its focus is on examples that are newly available for research, novel in the application, or significantly expanded in scale. Submissions can describe applications of learning analytics tools to new areas, measurements of their impact on learners, challenges faced in design and implementation, and use of learning analytics to support learners and educators in optimizing the learning process. The main research question is: What is the current scientific knowledge about the application of learning analytics in education? This can be examined in relation to earlier validated propositions: how learning analytics can be used to support learning and teaching and more efficiently reach learning goals and outcomes. Of interest are also papers that describe unique datasets, the technical, ethical, and logistical barriers to their use, and the impact that they have had on learning analytics.

We cordially invite authors to submit high-quality manuscripts related to learning analytics including original research, review articles, and case studies. Topics of interests include, but are not limited to, the following:

• Theories and models in learning analytics;
• Identifying students’ behavioral patterns and learning strategies from educational data;
• Deriving representations of domain knowledge from data;
• Detecting and addressing students’ affective and emotional states;
• Frameworks, techniques, research methods, and approaches for learning analytics;
• Developing learning models or assessment models based on learning analytics results;
• Multi-modal learning environments and sensor analysis;
• Practices for the adaptation of learning analytics results to enhance teaching/learning environments;
• Socio-cultural practices of learning data and learning analytics use;
• Personalization and adaptation in the learning process;
• Development of learner or instructor-facing feedback systems;
• Changes to educational practices when analytics are introduced;
• Use of learning analytics for learning design;
• Development or application of data mining and machine learning techniques to address questions of learning;
• Educational data mining in social and collaborative learning;
• Data mining with pedagogical environments such as educational games MOOCs;
• Information visualization and representation for various stakeholder groups (learners, instructors, de-signers’ administrators).

Keywords: learning analytics, educational data mining, artificial intelligence, recommender systems, personalized adaptive learning

Important note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.