BayLAN 2020: The Bay Area Learning Analytics Network Conference 2020 UC Berkeley Berkeley, CA, United States, May 2, 2020 |
Conference website | https://www.baylan.org/ |
Submission link | https://easychair.org/conferences/?conf=baylan2020 |
Submission deadline | March 15, 2020 |
About BayLAN: Our mission is to build bridges between Bay Area folks from different backgrounds working on analytics for education and educational technology. We target a broad audience of researchers and developers from academia and industry, education and computer science, as well as practitioners bringing everyday experience developing and using educational technology.
Learning analytics concerns the measurement, collection, analysis, and reporting of data about learners and their contexts, for purposes of understanding and optimizing learning and the learning environments. Broadly defined, the learning environments may include offline classrooms, online platforms (e.g., learning and assessment systems, intelligent tutoring systems, chatbots, and recommender systems), and the integration of the two.
This year, we are coordinating five sessions that approach learning analytics from different angles: 1) Equity in Learning Analytics, 2) Application of Learning Theory in Learning Analytics 3) Models for Online Learning 4) Machine Learning in Education and 5) Efficacy of Educational Products. A large poster session will ensure that everyone (including students) can share their work on one of these five themes as well.
Session 1: Equity in Learning Analytics
This session will aim to discuss equity issues in learning analytics. In the hope of improving education for all, we invite presentations on research and practices that take into account all learners and aim to promote equitable learning across diverse groups. Since we seek to reduce inequity in measurable ways, in addition, we welcome contributions that explore the operational definitions and metrics of “equity in education,” and what they mean to educationally underserved groups, educators, researchers, and policymakers in all aspects (e.g. representativeness, practices, and outcomes).
Session chair: Ranjeet Tate
Co-organizers: Sanghamitra Deb and Diego Sierra
Session 2: Application of Learning Theory in Learning Analytics
This session will focus on the integration of learning theories in learning analytics. In 2016, Professor Paul A. Kirschner at LAK16 posed the question “What do the learning sciences have to do with learning analytics (LA)?” His utopian vision was accompanied by a dystopian future where learning science and learning analytics had not yet come together. Since then, how have researchers and practitioners across the fields of learning science and learning analytics worked together to advance learning outcomes for students using big data? We invite submissions that answer this question and showcase learning analytics and educational data mining research that is rooted in learning science principles. We invite papers that examine learning processes in real-life learning and ed-tech products to influence learning outcomes.
Session chair: Ruchi Bhanot
Session 3: Models for Online Learning
This session will target statistical and computational approaches to studying online learning, with emphasis on interpretable models, ideally, those grounded in psychometrics and cognitive theory. This includes modeling dynamic aspects of the learning process such as knowledge acquisition, reinforcement, interference, and forgetting, as well as student-dependant factors such as attentional or motivational state, and item-level attributes including difficulty or salience.
Session chairs: Shane Mooney and Anna Khazenzon
Session 4: Machine Learning in Education
This session will mainly focus on the application of artificial intelligence, machine learning, and data mining to understanding or optimizing learning and its environment. Recent advances in computer and data sciences have expanded the type and scale of measurements we take, as well as the interventions we exert, in various learning environments. In this session, we foster multidisciplinary communication and collaboration in educational innovation by presenting state-of-the-art research and applications that highlight:
- Novel use of machine learning in various learning environments;
- Affective computing; and
- Automated generation of educational content.
Session chair: TBD
Session 5: Efficacy of Educational Products
This session will explore the barriers and benefits of conducting efficacy research on educational technology products. We will discuss major obstacles to efficacy research, practical strategies for overcoming these obstacles, and the benefits of conducting this type of research for different stakeholders involved. We invite submissions from all methodological, empirical, and ethical aspects of efficacy research as well as contributors from industry and philanthropy who can offer practical insights, guidelines, and examples that are highly relevant to the evaluation of educational technology products.
Session chair: Molly Zielezinski
Process
We solicit abstract submissions reporting on research on one of the above-mentioned session themes. Abstracts will be assessed by the program committee on the relevance to the session theme as well as quality. Accepted work will be invited for presentation as one of:
- Research talk. 15-20 minutes (including Q&A)
- Poster
- Demo of your application.
Due to time constraints, we can only invite a limited number of talks. The majority of submissions will be invited for a poster presentation.
While submissions from for-profit companies are welcomed, reviewers will not accept sales pitches.