1. MOTIVATION With the arrival of 'big data' in education, the potential was recognised for learning analytics to track students' learning, to reveal patterns in their learning, or to identify at-risk students, in addition to guiding reform and supporting educators in improving teaching and learning processes [1]. Learning Analytics dashboards have been used at all levels, including institutional, regional and national level [2]. In classroom use, while learning visualisations are often based on counts of activity data or interaction patterns, there is increasing recognition that learning analytics relate to learning, and should therefore provide pedagogically useful information [3]. While increasing numbers of technology-enhanced learning applications are embracing the potential of learning analytics at the classroom level, often these are aimed at teachers. However, learners can also benefit from learning analytics data (e.g. [4][5]).
Learner models hold data about an individual’s understanding or
skills, inferred during an interaction, and are at the core of
educational systems that personalise the learning interaction to suit
the needs of the learner [
We thank the members of the Learning Analytics for Learners Program Committee for their substantial efforts in making the workshop a success. Program Committee members were:
Matthew D. JOHNSON
University of Birmingham, UK The workshop sold out quickly at full capacity (40 participants), highlighting the timeliness of this topic in Learning Analytics. 3. WORKSHOP PAPERS The main themes that were addressed in the workshop papers were visualisation/dashboards, metacognition/awareness, and social learning. Several papers considered more than one of these themes. Hatala et al.’s paper compares students’ approaches to learning to learning analytics visualisations, and the quality of messages posted. Al-Shanfari et al.’s paper proposes ways to visualise uncertainty in data in an open learner model context. Marzouk et al.’s paper investigates facilitating self-monitoring and the type of analytics that may meaningfully prompt changes to learning, including social learning. Venant et al.’s paper also considers metacognition, awareness and deep learning, and social awareness; and Davis et al.’s demonstration paper explores self-regulation, and comparison to previous successful learners. Knight and Anderson take a theoretical perspective, arguing for participatory design for learning analytics for learners. Wasson et al.’s position paper argues for the need to address data literacy, and training learners in the new approaches and learning analytics and/or open learner model tools available to them. Finally, Martinez-Maldonado et al.’s paper also explores both learning analytics and open learner models, in their case to support behavioural change in a health context.
We thank all the authors for their contributions, as well as the other workshop participants who contributed substantially to the discussions throughout the day.