First International Workshop on
Enabling Data-Driven Decisions from Learning on the Web
(L2D 2021)

to be held as part of the 14th ACM International Conference on Web Search and Data Mining (WSDM 2021)

March 12, 2021 - Morning UTC +02:00 - ONLINE EVENT

Workshop Aims and Scope

By offering courses and resources, learning platforms on the Web have been attracting lots of participants, and the interactions with these systems have generated a vast amount of learning-related data. Their collection, processing and analysis have promoted a significant growth of learning analytics and have opened up new opportunities for supporting and assessing educational experiences. To provide all the stakeholders involved in the educational process with a timely support, being able to understand learner's behavior and create models that provide data-driven decisions pertaining to the learning domain is a primary feature of modern online platforms. This workshop aims to present novel, high-quality, high-impact, original research results reporting the current state of the art of online education systems empowered with data mining (DM) and machine learning (ML). Specifically, this workshop will pursue the following objectives:

  • Raise attention on education in the DM and ML community.
  • Identify human aspects affected by DM and ML in education.
  • Solicit contributions targeting DM and ML in education.
  • Get insights on recent open issues and methods in this area.
  • Expose gaps between research and actual needs in this area.

Given the growing importance of these topics, the DM and ML community is more and more eager to delve into this applicative domain and, as a consequence, can strongly benefit from a dedicated event. For this reason, this workshop would provide the WSDM community with rich, yet clear, focused, and well-structured insights on this domain. L2D 2021 will be the WSDM's workshop aimed at collecting new contributions in education-related DM and ML, and at providing a common ground for interested researchers and practitioners. Given also the current situation faced by education worldwide due to the pandemic, we expect that this workshop will foster a strong outcome and a wide community dialog.

Workshop Topics

We are interested in novel contributions targeting DM and ML in education on the Web, focused but not limited to the following areas. We seek to receive papers that clearly state and contextualize how the proposed contribution is integrated in the real-world scenario and supports educational stakeholders during decision-making.

  • Data Set Collection and Preparation:
    • New tools and systems for capturing educational data (e.g., eye-tracking, motion, physiological, etc.).
    • Proposals of procedures and tools to store, share and preserve learning and teaching traces.
    • Knowledge graphs and annotation schemas for data that can be leveraged for DM and ML in education.
    • Collecting and sharing data sets useful for applying DM and ML in online education contexts.
  • Model, Tool, and System Design and Implementation:
    • Semantic content-based retrieval of educational materials to identify appropriate contents.
    • Tools for adaptive question-answering and dialogue or automatically generating test questions.
    • Personalized support tools and systems for communities of learners (e.g., recommendation).
    • Natural language processing applied on exam data in order to assign a grade to them.
    • Behavioral and physiological analysis of learners while interacting in online education platforms.
    • Student engagement assessment via machine-learning techniques (e.g., sentiment analysis).
    • Systems that detect and/or adapt the platform to sentiment or emotional states of learners.
    • Techniques to provide automated proctoring support during online examinations, e.g., via biometric recognition.
    • Tools able to predict the learner's success or failure along the educational path.
  • Evaluation Protocol Design and Implementation:
    • Evaluation techniques, metrics, and protocols relying on computational analyses in online education contexts.
    • Interpretability and/or fairness of the models and the resulting impact on real-world adoption.
    • Error analysis aiming at understanding, measuring, and managing uncertainty in model design.
    • Strategies to evaluate effectiveness and impact of DM and ML systems on educational environments.
    • Exploration of cognition, affect, motivation, and attitudes of stakeholders, while deploying systems.
    • Learning-while-searching investigations conducted in the current educational contexts.
  • Ethics and Privacy Investigation:
    • Analysis of issues and approaches to the lawful and ethical use of intelligent DM and ML systems.
    • Tackling unintended bias and value judgements in DM and ML intelligent systems.
    • Regulations and policies in data management ensuring privacy while designing intelligent DM and ML systems.
    • Broad discussion on potential and pitfalls of intelligent systems for educational contexts.
    • Studies on how teachers can be made part of the loop as moderators instead of being replaced.

Important Dates

  • Submissions: January 25, 2021
  • Notifications: February 22, 2021
  • Camera-Ready: March 1, 2021
  • Workshop: March 12, 2021 - ONLINE EVENT

All deadlines are 11:59pm, AoE time (Anywhere on Earth).

Submission Details

The submissions must be in English and adhere to the CEUR-WS one-column template. The papers should be submitted as PDF files to Easychair at https://easychair.org/conferences/?conf=l2d2021. The review process will be single-blind. Please be aware that at least one author per paper must be registered and attend the workshop to present the work.

We will consider four different submission types:

  • Full Papers (10-12 pages) should be clearly placed with respect to the state of the art and state the contribution of the proposal in the domain of application, even if presenting preliminary results. In particular, research papers should describe the methodology in detail, experiments should be repeatable, and a comparison with the existing approaches in the literature is encouraged.
  • Reproducibility Papers (10-12 pages) should repeat prior experiments using the original source code and datasets to show (i) how, why, and when the methods work or not, (ii) or should repeat prior experiments, preferably using the original source code, in new contexts (e.g., different domains and datasets, different evaluation and metrics) to further generalize and validate or not previous work.
  • Short Papers (5-9 pages) should describe significant novel work in progress. Compared to full papers, their contribution may be narrower in scope, be applied to a narrower set of application domains, or have weaker empirical support than that expected for a full paper. Submissions likely to generate discussions in new and emerging areas of data mining and machine learning in education are encouraged.
  • Position Papers (4-5 pages) should introduce new point of views in the workshop topics or summarize the experience of a group in the field. Practice and experience reports should present in detail real-world scenarios in which data mining and/or machine learning are exploited in the educational context.

Submissions should not exceed the indicated number of pages, including any diagrams and references.

Each submission will be reviewed by three independent reviewers on the basis of relevance for the workshop, novelty/originality, significance, technical quality and correctness, quality and clarity of presentation, quality of references and reproducibility.

The accepted papers and the material generated during the meeting will be available on the workshop website. The workshop proceedings will be sent for inclusion in a CEUR-WS volume and consequently indexed on Google Scholar, DBLP, and Scopus. Authors of selected papers may be invited to submit an extended version in a journal special issue.

We expect authors, the programm committee, and the organizing committee to adhere to the ACM’s Conflict of Interest Policy and the ACM’s Code of Ethics and Professional Conduct.

Program (currently being updated)

Due to the ongoing worldwide COVID-19 situation, the L2D@WSDM2021 workshop will take place online on March 12, 2021, morning (UTC +02:00).

Timing Content
5 mins Opening Remarks
40 mins Keynote on Learning about Learners, Learner Computer Interaction: Finding about Relevant Data in Learning Processes

Speaker: Marcus Specht, Technical University of Delft (TU Delft), The Netherlands

Short Bio: Prof. Dr. Marcus Specht is Professor for Digital Education at the Technical University of Delft and Director of the Leiden-Delft-Erasmus Center for Education and Learning. He received his Diploma in Psychology in 1995 and a Dissertation from the University of Trier in 1998 on adaptive information technology. From 2001 he headed the department "Mobile Knowledge" at the Fraunhofer Institute for Applied Information Technology (FIT). From 2005 to 2018 he was Professor for Learning Technologies at the Open Universiteit Nederland and head of the Learning Innovation Lab. His research focus is on Computational Thinking, Learning Analytics, AI in Education, and Virtual and Augmented Reality for Education. Prof. Specht is an Apple Distinguished Educator and was President (2013-2015) of the International Association of Mobile Learning.

Short Abstract: TBD

40 mins Paper Session 1
15 mins Coffee Break
40 mins Paper Session 2
40 mins Paper Session 3
15 mins Coffee Break
40 mins Panel and Discussion on Leveraging Intelligent Systems for Online Education at Scale

Panelists:

Short Abstract: What does it mean to build, deploy, and do research on top of large-scale online educational platforms in our era? How can data mining and machine learning support in understanding learners' behavior at large scale? How can intelligent models provide data-driven decisions tailored to the stakeholders' needs in modern online platforms? Which challenges are being faced and how can academia and industry collaborate to address them? Finding answers to these questions is crucial to ensure the systems we develop improve the online education ecosystem. It encompasses many topics, including technology, pedagogy, learning, fairness, transparency, privacy, and social impact. With this panel, we bring a variety of perspectives from industry to discuss these questions and foster the discussion in this vibrant area.

5 mins Concluding Remarks

Committees

Workshop Chairs

Program Committee

  • Mehwish Alam, FIZ Karlsruhe & Karlsruhe Institute of Technology, Germany
  • Fahriye Altınay Aksal, Near East University, Cyprus
  • Geoffray Bonnin, LORIA, France
  • Ludovico Boratto, Eurecat - Centre Tecnòlogic de Catalunya, Spain
  • Javier Bravo-Agapito, Madrid Open University (UDIMA), Spain
  • Gong Cheng, Nanjing University, China
  • Irene-Angelica Chounta, University of Tartu, Estonia
  • Mathieu D'Aquin, National University of Ireland Galway, Ireland
  • Daniele Di Mitri, DIPF | Leibniz Institute for Research and Information in Education, Germany
  • Ralph Ewerth, L3S Research Center, Leibniz Universität Hannover, Germany
  • Davide Fossati, Emory University, USA
  • Erik Hemberg, Massachusetts Institute of Technology, USA
  • Eelco Herder, Radboud University, The Netherlands
  • Martin Hlosta, The Open University
  • Fabian Hoppe, FIZ Karlsruhe & Karlsruhe Institute of Technology, UK
  • Ioana Jivet, TU Delft, The Netherlands
  • Zuzana Kubincová, Comenius University, Slovakia
  • Pasquale Lisena, EURECOM, France
  • Matteo Lombardi, Griffith University, Australia
  • Francesca Maridina Malloci, University of Cagliari, Italy
  • Martino Mensio, The Open University, UK
  • Donatella Merlini, University of Florence, Italy
  • Angelo Antonio Salatino, The Open University, UK
  • Nadine Steinmetz, TU Ilmenau, Germany
  • Tabea Tietz, FIZ Karlsruhe & Karlsruhe Institute of Technology, Germany

Contacts

For general enquiries on the workshop, please send an email to danilo.dessi@kit.edu and mirko.marras@epfl.ch.