The XLA'20 workshop will be in conjunction with the 10th International Learning Analytics and Knowledge (LAK) Conference, Frankfurt, Germany 23-27 March 2020.

Currently, the Learning Analytics (LA) domain is maturing and often provides insights in and decisions/actions (e.g. interventions, feedback, recommendations) regarding learning and teaching behaviors. Before the insights, decisions, and actions can actually impact learning, the process and outcomes of the data analysis and/or visualizations have to be transparent to the end-users. While advanced machine learning and visualization techniques might create accurate insights, decisions, and actions, they will not be per se trusted by the user. Opening the black-box of LA to the user, in a user-tailored fashion is the first step towards providing transparent insights, decisions, and actions. Approaches for obtaining transparency are key to improve the trustworthiness, impact and adoption of LA systems at scale.

The evolution towards transparent LA is urgent, as recent data protection and privacy regulations (EU GDPR and CCPA (California Consumer Privacy Act)) stipulate that transparency is a fundamental right. Even more, they state that each user has the right to withdraw him/herself from automatic decision making and profiling. So, it is now time to act and to jointly work towards transparent insights, decisions, and actions in the domain of LA.

The aim of the workshop is to advance the research and practices around transparent LA. To this end, the workshop will bring together researchers, practitioners, educational developers and policymakers in an interactive workshop format. We welcome contributions of both long and short papers, and including both research and practitioner papers, around the general theme of explainable insights, decisions, and actions in LA.

• Theories and methods for transparent insights, interventions, feedback, and recommendations in LA
• Explanations for transparency in LA
• Visualizations for transparency in LA
• User involvement/control for transparency in LA
• Explainable user/learner modeling
• Methods to assess transparency and explainability in LA
• Impact of explainable LA on the stakeholders (e.g. motivation, engagement and adoption)
• Case studies demonstrating the need for explainable LA

Contributions can be in the following forms:

• Full papers (10 or more pages)
• Short papers (5-9 pages)

All contributions to the workshop must follow the format of the Companion Proceedings Template and they should be submitted through Easychair using this link. All contributions will be peer-reviewed by at least two members of the Program Committee. The accepted papers will be published in the Companion Proceedings of the LAK 2020 conference.

Submission opens: 1 Nov 2019
Submission deadline: 15 Dec 2019
Notification of acceptance: 5 Jan 2020

During the full-day workshop, we aim to facilitate a very interactive and engaging event where we want to avoid death by powerpoint at all causes and promote discussion activities over presentational ones. We will therefore ask participants to shortly present the work of another submission and to relate it back to their own work. The facilitators will allocate challengers per presentation to move the discussion around common themes and differences in approaches.

Tom Broos, KU Leuven, Belgium
Mohamed Amine Chatti, University of Duisburg-Essen, Germany
Robin De Croon, KU Leuven, Belgium
Tinne De Laet, KU Leuven, Belgium
Martijn Millecamp, KU Leuven, Belgium
Arham Muslim, University of Duisburg-Essen, Germany
Katrien Verbert, KU Leuven, Belgium

Tom Broos, KU Leuven, Belgium
Mohamed Amine Chatti, University of Duisburg-Essen, Germany
Irene-Angelica Chounta, University of Tartu, Estonia
Robin De Croon, KU Leuven, Belgium
Tinne De Laet, KU Leuven, Belgium
H. Ulrich Hoppe, University of Duisburg-Essen, Germany
Martijn Millecamp, KU Leuven, Belgium
Arham Muslim, University of Duisburg-Essen, Germany
María Jesús Rodríguez-Triana, Tallinn University, Estonia
Katrien Verbert, KU Leuven, Belgium