The theme of the workshop is “Multimodal Interactions Across Physical and Digital Spaces in Real World Learning Contexts”. The workshop highlights the need for devising learning analytics innovations that can provide timely feedback and support to learners and teachers in real-world contexts. The above theme aims to encourage workshop participants to think about this educational need in our increasingly complex everyday world and to consider both the growing interest in real-world learning analytics. The workshop will focus on the following four sub-themes:
- Learning analytics across digital and physical spaces
- Integration of multiple data sources
- Engaging and communicating meaning to learners and teachers from learning analytics
- Challenges for multimodal learning analytics across diverse spaces
Short papers – 4-6 pages (5 pages minimum for inclusion in CEUR Proceedings). Short papers consist of authors describing their research in the area of learning analytics across physical and digital spaces. Authors of successful submissions will give a brief firehose presentation and present a poster at the poster session during the workshop.
Position papers – 2-5 pages (5 pages minimum for inclusion in CEUR Proceedings). Position papers explain a unique perspective on the field that the author would like to contribute. Authors of successful submissions will participate in one panel to be held during the workshop.
All workshop participants are encouraged to submit at least one paper under any of these two categories. There is no restriction on the number of papers submitted by the same author. The submission of a paper is not compulsory. After the conference, full-length submissions resulting from the discussions will be published on CEUR (http://ceur-ws.org/), and we are exploring the joint edition of future journal special issues on the topic. In addition, LAK will also publish the proceedings of the workshop in a Companion Proceedings series.
List of accepted workshop papers:
- Learning false friends across contexts
Victoria Abou-Khalil, Brendan Flanagan, Hiroaki Ogata
- Combining Multimodal Learning Analytics with Backward Design to Assess Learning
Melanie E. Peffer
- On the Prediction of Students’ Quiz Score by Recurrent Neural Network
Fumiya Okubo, Takayoshi Yamashita, Atsushi Shimada, Yuta Taniguchi, Shin’ichi Konomi
- Multimodal Transcript of Face-to-Face Group-Work Activity Around Interactive Tabletops
Xavier Ochoa, Katherine Chiluiza, Roger Granda, Gabriel Falcones, James Castells, Bruno Guamán
- Multimodal Learning Analytics’ Past, Present, and, Potential Futures
- The Big Five: Addressing Recurrent Multimodal Learning Data Challenges
Daniele Di Mitri, Jan Schneider, Marcus Specht, Hendrik Drachsler