Call for Papers

EDM 2024: the 17th International Conference on Educational Data Mining

Atlanta, Georgia, USA, July 14—17, 2024

New tools, new prospects, new risks – educational data mining in the age of generative AI

Educational Data Mining is a leading international forum for high-quality research that mines datasets to answer educational research questions, including exploring how people learn and how they teach. These data may originate from a variety of learning contexts, including learning and information management systems, interactive learning environments, intelligent tutoring systems, educational games, and data-rich learning activities. Educational data mining considers a wide variety of types of data, including but not limited to log files, student-produced artifacts, discourse, learning content and context, sensor data, and multi-resource and multimodal streams. The overarching goal of the Educational Data Mining research community is to support learners and teachers more effectively, by developing data-driven understandings of the learning and teaching processes in a wide variety of contexts and for diverse learners.

The 17th iteration of the conference, EDM 2024, will take place in a hybrid format, both online and in-person, to facilitate participation and networking for all.

The theme of this year’s conference is “New tools, new prospects, new risks – educational data mining in the age of generative AI”. This year’s theme focuses on the movement from descriptive and predictive models to generative artificial intelligence (AI) and what that means for learning environments and processes. While the new methods unlock exciting new potentials for educational data mining, they also foreground many ethical considerations and risks that are associated with all types of machine learning and artificial intelligence. In addition to the general topics listed below, we welcome research in the following areas: mitigating biases and harms that may result from model use, accounting for the stereotypes that are inherent to the large models that drive generative AI, separating the hype surrounding these new technologies from their potential in educational settings, and finding ways to use these models to better understand learning processes and support learning.

Topics of Interest

Topics of interest to the conference include but are not limited to:

  • Developing new techniques for mining educational data.
  • Closing the loop between EDM research and learning sciences
    • Informing data mining research with educational and/or motivational theories
    • Actionable advice rooted in educational data mining research, experiments, and outcomes
    • Evaluating the efficacy of curriculum and interventions
  • Domain Knowledge Modeling
    • Deriving representations of domain knowledge from data
    • Algorithms for discovering relationships, associations, and prerequisite structures between learning resources with different formats, including programming practices, essays, and videos
    • Algorithms to improve existing domain models
    • Novel methods to collect domain knowledge models, including crowd-sourcing and expert tagging
  • Educational Recommenders, Instructional Sequencing, and Personalized Learning
    • Learning resource recommendation algorithms, remedial recommendations, and learner choice in selecting the next activity
    • Goal-oriented instructional sequencing
    • Personalized course recommendations
    • Peer recommendation for collaborative learning
    • Offline and online evaluation methods for educational recommender systems and sequencing algorithms
  • Equity, Privacy, Transparency, and Fairness
    • Ethical considerations in EDM
    • Legal and social policies to govern EDM
    • Developing privacy-protecting EDM algorithms and detecting learner privacy violations in existing methods
    • Developing and applying fairer learning algorithms, and detecting and correcting instances of algorithmic unfairness in existing methods
    • Developing, improving, and evaluating explainable EDM algorithms
  • Learner Cognitive and Behavior Modeling and its association with performance
    • Modeling and detecting students’ affective and cognitive states (e.g., engagement, confusion) with multimodal data
    • Temporal patterns in student behavior including gaming the system, procrastination, and sequence modeling
    • Data mining to understand how learners interact with various pedagogical environments such as educational games and exploratory learning environments
  • Learner Knowledge and Performance Modeling 
    • Automatically assessing student knowledge
    • Learner knowledge gain and forgetting models in domains with complex concept structures
    • Modeling real-world problem-solving in open-ended domains
    • Causal inference of students’ learning
    • Predicting students’ future performance
  • Learning analytics
    • Institutional analytics
    • Learner profiling 
    • Multimodal analytics
  • Social and Collaborative Learning
    • Modeling student and group verbal and non-verbal interactions for collaborative and/or competitive problem-solving
    • Social network analysis of student and teacher interactions
    • Data mining to understand how learners interact in formal and informal educational contexts
    • Peer-assessment modeling
    • Social learner modeling
  • Reproducibility
    • Replicating previous studies with larger sample sizes, in different domains, and/or in more diverse contexts
    • Facilitating accessible benchmarking systems and publishing educational datasets that are useful for the community

Submission Types

For all tracks, the acknowledgements and references sections at the end of the paper does not count towards the listed page limits.

  • Full Papers — 10 pages. Should describe original, substantive, mature, and unpublished work.
  • Short Papers — 6 pages. Should describe original, unpublished work. This includes early stage, less developed works in progress.
  • JEDM Journal Track Papers — Papers submitted to the Journal of Educational Data Mining track (and accepted before May 30, 2024) will be published in JEDM and presented during the JEDM track of the conference.
  • Industry Papers — 6 pages. Should describe innovative uses of EDM techniques in a commercial setting.
  • Doctoral Consortium — 2-4 pages. Should describe the graduate/postgraduate student’s research topic, proposed contributions, and results so far. See below for details.
  • Posters/Demos — 2-4 pages. Posters should describe original unpublished work in progress or last-minute results. Demos should describe EDM tools and systems, or educational systems that use EDM techniques.
  • Workshop proposals — 2-4 pages. Should describe the organizers’ plan both to conduct the workshop (e.g., format, rough schedule, proposed list of speakers) and to stimulate growth in the workshop’s area of focus. Workshop organizers should indicate whether they would prefer to host their event in a hybrid format (supporting both in-person and remote attendees), or a remote-only format. For more information, please refer to the special instructions at the bottom of this page.
  • Tutorial proposals — 2-4 pages. Should motivate and describe succinctly the field or tool that will be presented, as well as a plan for attendees to learn it in a hands-on way. Tutorial organizers should indicate whether they would prefer to host their event in a hybrid format (supporting both in-person and remote attendees), or a remote-only format. For more information, please refer to the special instructions at the bottom of this page.

All accepted papers will be published in the open-access proceedings of the conference, except for the Journal track as stated above. Papers submitted to workshops will be published separately in the workshop proceedings. All paper submissions must be submitted for double-masked reviewing.

Submission

For all information on how to submit and format your paper, please refer to the Instructions for Authors page.

Special Instructions

Workshop and Tutorial proposals

Workshop and Tutorial proposals should use the EDM proceedings template (LaTeX or Word) and include at least the following elements: 

  • Title.
  • Length of workshop/tutorial: full or half-day.
  • Proposed format of the workshop/tutorial, approximate timeline and the type(s) of planned activities (e.g., paper presentations, discussions, demos, panels, invited speakers, tutorial, etc.).
  • Description of the workshop/tutorial content and themes, including their relevance and importance to the EDM community.
  • Expected target audience and expected maximum number of participants.
  • Previous editions of the workshop/tutorial series, if applicable.
  • Plans for supporting remote attendees (either as a hybrid or fully-remote event).
  • Names, short biographies, and contact information of workshop/tutorial chair(s). For tutorials, this biography needs to include detailed information about the qualifications of the proposer to conduct the tutorial on the proposed topic. For workshops, also add a list of tentative program committee members, who should be from multiple universities.

JEDM Track Papers

JEDM track papers should be formatted according to the JEDM guidelines and should be submitted to the journal directly at:

https://jedm.educationaldatamining.org/index.php/JEDM/about/submissions

by selecting the option “EDM 2024 Journal Track” in the corresponding Section box.

Doctoral Consortium

The EDM Doctoral Consortium is an interactive event to support doctoral students working in domains relevant to the interdisciplinary research areas of educational data mining. In the Doctoral Consortium, the students will share and discuss their research ideas and plans with more experienced colleagues, i.e., mentors, who will provide feedback on various aspects of the student’s work including the theoretical framing and the methodological approaches. Doctoral Consortium participants will also have the opportunity to informally introduce themselves to the larger EDM community.

We invite all doctoral students for submissions. However, the candidates selected will be those who are at a stage in their research for which feedback from the EDM community will be of most value. That is, the students who have a clear topic and research approach, and have made some progress, but who are not so far along in their work that they can no longer benefit from feedback received during the conference. It is possible to participate in the Doctoral Consortium if the candidate is in a doctoral program, and also if the individual has graduated within the year. Paper submissions must be primarily authored by the students with advisors and collaborators listed as co-authors. The topics of interest are related to the main conference topics.

Though the main objective of the Doctoral Consortium is to provide an opportunity for feedback on students’ current research, we also seek to continue to build interdisciplinary research ideas, theoretical frameworks, and methodological approaches because these intersections are critical to EDM as an area of scholarship. We recognize that a supportive and trans-disciplinary research community can only be possible with opportunities for healthy dialogic exchange between members of the EDM community. Therefore, it is of utmost importance that the Doctoral Consortium fosters such collaborative interactions among the participants of the conference in order to enhance the experience of all participants and build capacity in the field.

Format and Content

Accepted candidates will participate in 1-on-1 talks with senior researchers and other students (virtual or hybrid) during the conference in which they will present their work and receive feedback on their research. 

In addition, prior to the conference, each student with an accepted paper will be assigned a mentor with specialized background on the student’s research topic or methodological approach so that more detailed and specific feedback can be provided to each student. As part of the application, students will list names of potential mentors in the EDM community they want to meet, and we will do our best to connect each student with those individuals.  

The submission has two equally important parts: 

  1. A 4-page paper to be published in the conference proceedings. Important: If you wish to also submit your paper, or a close version, to the main conference (full or short paper track) and it is accepted under one of those tracks, then you will instead be invited to provide a one page abstract for the camera ready copy of the Doctoral Consortium proceedings. That way your paper will not be published twice yet your participation in the DC will be recorded in the proceedings.
  2. A presentation letter with additional information about the student and the research carried out to date.

The paper should follow the format template linked below and describe, in a logical and coherent manner, the aims and objectives of the proposed research by clearly illustrating the following:

  1. The problem(s) addressed and the fit with the state of the art, including any previous work the student has done.
  2. The theoretical framing and proposed solution(s), as well as the methodology adopted to achieve it. Include the progress made to date on the work.
  3. The expected contribution(s) and impact of the research to the EDM community being mindful of both the Learning Sciences and Computer Science.

The presentation letter should include all of the following information:

  1. Paper Title
  2. Name of the student and supervisor(s)
  3. Student’s title and university affiliation
  4. Short description of the study where the research is carried out.
  5. A paragraph describing the student’s contribution to the work, the stage of the studies, with a brief description of the student’s background.
  6. The type of feedback sought by the student from the Doctoral Consortium.
  7. List of other contributions submitted to the EDM 2024 conference, including the list order of authors, and status of the submission.
  8. Three names of EDM researcher-mentors the student would like to meet and why.
  9. U.S. Citizenship and/or Green Card Status for funding consideration by the NSF. 
  10. Link to your research webpage and/or CV. 

Submission Instructions

  • The papers can be co-authored by the student and supervisor(s), but the student should be the first author.
  • Papers should be 2-4 pages long, including references using the format used for the conference. Presentation letters are limited to 2 pages and can follow any format. 
  • Both files should be combined as a single PDF and uploaded to EasyChair. 

Important Dates

Doctoral Consortium papers are due one week after the main paper deadline. If the main paper deadline is pushed back a week, then this deadline will be pushed back by the same amount of time. For more information, please check the conference’s dates page.

Looking forward to seeing you at EDM 2024 in Atlanta!