Introduction to the Proceedings
Preface
The University of Palermo is proud to host the 18th International Conference on Educational Data Mining (EDM) in Palermo, Italy, from July 20 to July 23, 2025. EDM is the annual flagship conference of the International Educational Data Mining Society. This year’s theme is New Goals, New Measurements, New Incentives to Learn. The theme highlights the shift toward an era dominated by artificial intelligence - where machines can surpass human performance in numerous cognitive tasks - and highlights the imperative for our educational systems to evolve accordingly.
The scientific program for EDM2025 includes:
Two keynote talks by outstanding researchers in the field:
Jill Burstein (Duolingo, USA).
Chris Piech (Stanford University, USA).
A plenary Prof. Ram Kumar Educational Data Mining Test of Time Award talk given by Ryan S. Baker (University of Pennsylvania, USA).
An invited Data Set Award talk by L Burleigh (The Learning Agency, USA).
Five workshops and three tutorials.
Eight presentation sessions with parallel (2 and 3) tracks.
A poster presentation session.
An industry track session.
A doctoral consortium session.
A cross-conference panel moderated by Ken Koedinger (Carnegie Mellon University, USA):
EDM: Ryan Baker (University of Pennsylvania, USA).
Learning@Scale: Mar Perez-Sanagustin (Université Paul Sabatier Tolouse III, France).
AIED: Olga Santos (Universidad Nacional de Educación a Distancia, Spain).
The workshops are:
9th Educational Data Mining in Computer Science Education (CSEDM) Workshop.
2nd Human-Centric eXplainable AI in Education (HEXED) Workshop.
2nd Workshop on Educational Data Mining in Writing and Literacy Instruction.
Interactive Workshop: Multimodal, Multiparty Learning Analytics (MMLA).
CausalEDM: Linking Innovations in Instructional Design and the Complex Behaviors that Underlie Learning Processes and Outcomes.
The tutorials are:
Bringing Generative Artificial Intelligence (GenAI) to Education.
Leveraging KOALA for Programming Data Collection: A Half-Day Tutorial for Research Application.
Applying DebiasEd: A Package for Mitigating Unfairness in Educational Data
This year, EDM received 105 submissions to the Full Papers track (10 pages), 81 to the Short Papers track (6 pages), and 37 to the Posters and Demos track (4 pages). The program committee accepted 29 full papers (27.6% acceptance rate), 24 short papers (29.6% acceptance rate), 19 poster and demo papers, and 3 industry track papers. Furthermore, EDM 2025 also continued its tradition of providing opportunities for young researchers to present their work and receive feedback from peers and senior researchers. The Doctoral Consortium track this year featured 5 participants. We are also proud to offer travel sponsorships to 24 students who will attend thanks to this support.
We thank the sponsors of EDM 2025 for their generous support. We thank all the authors who submitted their work and the program committee members for their expert inputs. We thank the members of the organization committee for their leadership that made this conference possible. And, a big thank you to the local organizing committee who made this event memorable.
| Caitlin Mills | University of Minnesota, USA | Program Chair |
| Giora Alexandron | Weizmann Institute of Science, Israel | Program Chair |
| Davide Taibi | CNR-ITD, Italy | General Chair |
| Giosuè Lo Bosco | University of Palermo, Italy | General Chair |
| Luc Paquette | University of Illinois Urbana-Champaign, USA | General Chair |
July 10, 2025
Palermo, Italy
Organizing Committee
General Chairs
Davide Taibi, CNR-ITD, Italy
Giosuè Lo Bosco, University of Palermo, Italy
Luc Paquette, University of Illinois Urbana-Champaign, USA
Program Chairs
Caitlin Mills, University of Minnesota, USA
Giora Alexandron, Weizmann Institute of Science, Israel
Awards Chairs
Arnon Hershkovitz, Tel Aviv University, Israel
Tanja Käser, EPFL, Switzerland
Doctoral Consortium Chairs
Angela Stewart, University of Pittsburgh, USA
Min Chi, North Carolina State University, USA
Neil Heffernan, Worcester Polytechnic Institute, USA
Equity, Diversity, Inclusion, and Accessibility Chairs
Anna Rafferty, Carleton College, USA
Laura Allen, University of Minnesota, USA
Nigel Bosch, University of Illinois Urbana-Champaign, USA
Industry Track Chairs
Avi Segal, Ben-Gurion University of the Negev, Israel
Davide Zucchetti, Randstad, Italy
Yang Jiang, ETS Research Institute, USA
JEDM Track Chairs
Agathe Merceron, Berlin University of Applied Sciences, Germany
Roberto Martinez-Maldonado, Monash University, Australia
Poster & Demo Track Chairs
Heeryung Choi, University of Minnesota, USA
Mingyu Feng, WestEd, USA
Tanya Nazaretsky, EPFL, Switzerland
Proceedings Chairs
Miguel Portaz, UNED, Spain
Mirko Marras, University of Cagliari, Italy
Scholarship Chairs
Ryan Baker, University of Pennsylvania, USA
Antonija Mitrovic, University of Canterbury, New Zealand
Social Media & Publicity Chairs
Gabriella Casalino, University of Bari Aldo Moro, Italy
Jill-Jênn Vie, Inria, France
Sponsorship Chairs
Pier Paolo Corso, University of Palermo, Italy
Simon Woodhead, Eedi, UK
Student Volunteer Chair
Salvatore Calderaro, University of Palermo, Italy
Web Chairs
Daniele Schicchi, CNR-ITD, Italy
Paul Salvador Inventado, California State University Fullerton, USA
Workshop & Tutorial Chairs
Stephen Hutt, University of Denver, USA
Ramkumar Rajendran, IIT Bombay, India
Yang Shi, Utah State University, USA
IEDMS Officers
| Luc Paquette | University of Illinois Urbana-Champaign, USA | President |
| Anna Rafferty | Carleton College, USA | Treasurer |
IEDMS Board of Directors
| Rakesh Agrawal | Data Insights Laboratories, USA |
| Tiffany Barnes | North Carolina State University, USA |
| Nigel Bosch | University of Illinois Urbana-Champaign, USA |
| Neil Heffernan | Worcester Polytechnic Institute, USA |
| Sharon Hsiao | Santa Clara University, USA |
| Tanja Käser | EPFL, Switzerland |
| Kenneth Koedinger | Carnegie Mellon University, USA |
| Ramkumar Rajendran | Indian Institute of Technology Bombay, India |
Program Committee
Senior Program Committee Members
| Bita Akram | North Carolina State University, USA |
| Vincent Aleven | Carnegie Mellon University, USA |
| Roger Azevedo | University of Central Florida, USA |
| Ryan Baker | University of Pennsylvania, USA |
| Tiffany Barnes | North Carolina State University, USA |
| Nigel Bosch | University of Illinois Urbana-Champaign, USA |
| Anthony F. Botelho | University of Florida, USA |
| Jesus G. Boticario | UNED, Spain |
| François Bouchet | Sorbonne Université – LIP6, France |
| Alex Bowers | Columbia University, USA |
| Christopher Brooks | University of Michigan, USA |
| Alexandra Cristea | Durham University, UK |
| Michel Desmarais | École Polytechnique de Montréal, Canada |
| Fabiano Dorça | Universidade Federal de Uberlândia, Brazil |
| Michael Eagle | George Mason University, USA |
| Vanessa Echeverria | Monash University, Australia |
| Yo Ehara | Tokyo Gakugei University, Japan |
| Stephen Fancsali | Carnegie Learning, Inc., USA |
| Mingyu Feng | WestEd, USA |
| Carol Forsyth | Educational Testing Service, USA |
| Dragan Gasevic | Monash University, Australia |
| Neil Heffernan | Worcester Polytechnic Institute, USA |
| Sharon Hsiao | Santa Clara University, USA |
| Paul Inventado | California State University Fullerton, USA |
| Johan Jeuring | Utrecht University, Netherlands |
| Srecko Joksimovic | Education Future, University of South Australia, Australia |
| Jelena Jovanovic | University of Belgrade, Serbia |
| Kirsty Kitto | University of Technology Sydney, Australia |
| Rene Kizilcec | Cornell University, USA |
| Simon Knight | University of Technology Sydney, Australia |
| Irena Koprinska | The University of Sydney, Australia |
| Tanja Käser | EPFL, Switzerland |
| Sébastien Lallé | Sorbonne Université, France |
| Andrew Lan | University of Massachusetts Amherst, USA |
| Jeonghyun Lee | Georgia Institute of Technology, USA |
| James Lester | North Carolina State University, USA |
| Collin Lynch | North Carolina State University, USA |
| Mirko Marras | University of Cagliari, Italy |
| Roberto Angel Melendez | Instituto Tecnológico Superior de Misantla, Mexico |
| Agathe Merceron | Berlin University of Applied Sciences, Germany |
| Roger Nkambou | Université du Québec à Montréal, Canada |
| Jaclyn Ocumpaugh | University of Pennsylvania, USA |
| Andrew Olney | University of Memphis, USA |
| Benjamin Paaßen | Bielefeld University, Germany |
| Ranilson Paiva | Universidade Federal de Alagoas, Brazil |
| Luc Paquette | University of Illinois Urbana-Champaign, USA |
| Zach Pardos | University of California, Berkeley, USA |
| Radek Pelánek | Masaryk University Brno, Czechia |
| Niels Pinkwart | Humboldt-Universität zu Berlin, Germany |
| Agoritsa Polyzou | Florida International University, USA |
| Thomas Price | North Carolina State University, USA |
| Mar Pérez-Sanagustín | Université Paul Sabatier Toulouse III, France |
| Anna Rafferty | Carleton College, USA |
| R Rajalakshmi | VIT University, Chennai Campus, India |
| Ramkumar Rajendran | IIT Bombay, India |
| Maria Mercedes T. Rodrigo | Ateneo de Manila University, Philippines |
| Cristobal Romero | University of Cordoba, Spain |
| Shazia Sadiq | The University of Queensland, Australia |
| Sherry Sahebi | University at Albany – SUNY, USA |
| Niels Seidel | FernUniversität in Hagen, Germany |
| Atsushi Shimada | Kyushu University, Japan |
| Sergey Sosnovsky | Utrecht University, Netherlands |
| Tiffany Tang | Wenzhou-Kean University, China |
| Stefan Trausan-Matu | University Politehnica of Bucharest, Romania |
| Maomi Ueno | The University of Electro-Communications, Japan |
| Sebastián Ventura | University of Córdoba, Spain |
| Jill-Jênn Vie | Inria Lille, France |
| Stephan Weibelzahl | Private University of Applied Sciences, Germany |
Regular Program Committee Members
| Faruk Ahmed | The University of Memphis, USA |
| Ali Al-Zawqari | Vrije Universitiet Brussel, Belgium |
| Nazia Alam | North Carolina State University, USA |
| Laia Albó | Universitat de Vic, Spain |
| Laura Allen | University of Minnesota, USA |
| Claudia Antunes | Universidade de Lisboa, Portugal |
| Simón Pedro Arguijo | Tecnológico Nacional de México, Mexico |
| Jose Manuel Azevedo | ISCAP, Portugal |
| Aicha Bakki | LERIA – Angers University, France |
| Ayan Banerjee | Arizona State University, USA |
| Denilson Barbosa | University of Alberta, Canada |
| Abhinava Barthakur | University of South Australia, Australia |
| Marie Bexte | FernUniversität in Hagen, Germany |
| Anis Bey | La Rochelle University, France |
| Plaban Kumar Bhowmick | Indian Institute of Technology Kharagpur, India |
| Nathaniel Blanchard | Colorado State University, USA |
| Maria Bolsinova | Tilburg University, Netherlands |
| Geoffray Bonnin | Université de Lorraine – LORIA, France |
| Conrad Borchers | Carnegie Mellon University, USA |
| Mamadou Bousso | Thies University, Senegal |
| Keith Brawner | United States Army Research Laboratory, USA |
| Julien Broisin | IRIT, Université Toulouse III – Paul Sabatier, France |
| Armelle Brun | Université de Lorraine – LORIA, France |
| Minghao Cai | University of Alberta, Canada |
| Renza Campagni | Università degli Studi di Firenze, Italy |
| Meng Cao | Carnegie Mellon University, USA |
| Paulo Carvalho | Carnegie Mellon University, USA |
| Mehmet Celepkolu | University of Florida, USA |
| Guanliang Chen | Monash University, Australia |
| Heeryung Choi | University of Minnesota, USA |
| Irene-Angelica Chounta | University of Duisburg-Essen, Germany |
| Wei Chu | The University of Memphis, USA |
| Cheng-Yu Chung | Chunghwa Telecom Laboratories (CHTTL), Taiwan |
| Ruth Cobos | Universidad Autónoma de Madrid, Spain |
| Maria Constantino González | Tecnológico de Monterrey Campus Laguna, Mexico |
| Maria Cutumisu | McGill University, Canada |
| Cynthia D’Angelo | University of Illinois at Urbana-Champaign, USA |
| Jesper Dannath | Universität Bielefeld, Germany |
| Syaamantak Das | Indian Institute of Technology Bombay, India |
| M Ali Akber Dewan | Athabasca University, Canada |
| Nicholas Diana | Colgate University, USA |
| Fahima Djelil | IMT Atlantique, France |
| Cristina Dumdumaya | University of Southeastern Philippines, Philippines |
| Nghia Duong-Trung | German Research Centre for AI, Germany |
| Luke Eglington | Amplify Education Inc., USA |
| Effat Farhana | Vanderbilt University, USA |
| Márcia Fernandes | Federal University of Uberlândia, Brazil |
| Nigel Fernandez | University of Massachusetts Amherst, USA |
| Jeremiah Folsom-Kovarik | Soar Technology, Inc., USA |
| Davide Fossati | Emory University, USA |
| Kazuma Fuchimoto | The University of Electro-Communications, Japan |
| Hagit Gabbay | School of Education, Tel Aviv University, Israel |
| Wenbin Gan | NIICT, Japan |
| Adam Gaweda | North Carolina State University, USA |
| Aldo Gordillo | Universidad Politécnica de Madrid (UPM), Spain |
| Guher Gorgun | University of Alberta, Canada |
| Sabine Graf | Athabasca University, Canada |
| Julio Guerra | Universidad Austral de Chile, Chile |
| Ella Haig | University of Portsmouth, UK |
| Feifei Han | Australian Catholic University, Australia |
| Ching Nam Hang | Saint Francis University, Hong Kong |
| Jiangang Hao | Educational Testing Service, USA |
| Jason Harley | McGill University, Canada |
| Carl Haynes-Magyar | Carnegie Mellon University, USA |
| Surina He | University of Alberta, Canada |
| Sami Heikkinen | LAB University of Applied Sciences, Finland |
| Nicolas Hernandez | Nantes Université, France |
| Martin Hlosta | Swiss Distance University of Applied Sciences, Switzerland |
| Brahim Hmedna | Ibn Zohr University Science Agadir, Morocco |
| Anett Hoppe | Leibniz Universität Hannover, Germany |
| Paul Hur | Free University of Berlin, Germany |
| Stephen Hutt | University of Denver, USA |
| Sébastien Iksal | LIUM – Le Mans Université, France |
| Vladimir Ivančević | University of Novi Sad, Serbia |
| Hyeji Jang | Ewha Womans University, South Korea |
| Lan Jiang | University of Illinois Urbana-Champaign, USA |
| Yang Jiang | Columbia University, USA |
| Jina Kang | University of Illinois Urbana-Champaign, USA |
| Mohammad Khalil | University of Bergen, Norway |
| Ean Teng Khor | Nanyang Technological University, Singapore |
| Ekaterina Kochmar | MBZUAI, United Arab Emirates |
| Sotiris Kotsiantis | University of Patras, Greece |
| Vitomir Kovanovic | The University of South Australia, Australia |
| Milos Kravcik | DFKI GmbH, Germany |
| Swathi Krishnaraja | University of Potsdam, Germany |
| Amruth Kumar | Ramapo College of New Jersey, USA |
| Hatim Lahza | The University of Queensland, Australia |
| Hollis Lai | University of Alberta, Canada |
| Juan Alfonso Lara Torralbo | Universidad de Córdoba, Spain |
| Mikel Larrañaga | University of the Basque Country, Spain |
| Tai Le Quy | University of Koblenz, Germany |
| Alwyn Vwen Yen Lee | Nanyang Technological University, Singapore |
| Marie Lefevre | LIRIS – Université Lyon 1, France |
| Arun Balajiee Lekshmi Narayanan | University of Pittsburgh, USA |
| Jiawei Li | Nanyang Technological University, China |
| Jionghao Lin | Carnegie Mellon University, USA |
| Zhexiong Liu | University of Pittsburgh, USA |
| Yu Lu | Beijing Normal University, China |
| Ivan Luković | University of Belgrade, Serbia |
| Nick Lytle | Georgia Institute of Technology, USA |
| Sonsoles López-Pernas | University of Eastern Finland, Finland |
| Boxuan Ma | Kyushu University, Japan |
| Qiang Ma | Kyoto Institute of Technology, Japan |
| Qianou Ma | Carnegie Mellon University, USA |
| Yael Feldman Maggor | KTH Royal Institute of Technology, Sweden |
| Aditi Mallavarapu | University of Illinois at Chicago, USA |
| Jeffrey Matayoshi | McGraw Hill ALEKS, USA |
| Ahmad Mel | IDLab, Ghent University, Belgium |
| Victor Menendez-Dominguez | Universidad Autónoma de Yucatán, Mexico |
| Donatella Merlini | Università di Firenze, Italy |
| Tsunenori Mine | Kyushu University, Japan |
| Tsubasa Minematsu | Kyushu University, Japan |
| Sein Minn | INRIA, France |
| Phaedra Mohammed | The University of the West Indies, Trinidad and Tobago |
| Luis Alberto Morales Rosales | U. Michoacana de San Nicolás de Hidalgo, Mexico |
| Pedro Manuel Moreno-Marcos | Universidad Carlos III de Madrid, Spain |
| Kousuke Mouri | Tokyo University of Agriculture and Technology, Japan |
| Pedro J. Muñoz-Merino | Universidad Carlos III de Madrid, Spain |
| Tanya Nazaretsky | EPFL, Israel |
| Huy Nguyen | University of Pittsburgh, USA |
| Ange Adrienne Nyamen Tato | Université Laval, Canada |
| Teresa Ober | Educational Testing Service, USA |
| Püren Öncel | University of Minnesota Twin Cities, USA |
| Korinn Ostrow | Edmentum, USA |
| Tounwendyam F. Ouedraogo | Université Norbert ZONGO, Burkina Faso |
| Maciej Pankiewicz | University of Pennsylvania, Poland |
| Yancy Vance Paredes | Arizona State University, USA |
| Philip I. Pavlik Jr. | University of Memphis, USA |
| Jorge Poco | Fundação Getulio Vargas, Brazil |
| Paul Stefan Popescu | University of Craiova, Romania |
| Oleksandra Poquet | Technical University of Munich, Germany |
| David Pritchard | Massachusetts Institute of Technology, USA |
| Napol Rachatasumrit | Carnegie Mellon University, USA |
| Narjes Rohani | University of Edinburgh, UK |
| José Raúl Romero | University of Cordoba, Spain |
| Joshua Rosenberg | University of Tennessee, Knoxville, USA |
| Daniela Rotelli | University of Pisa, Italy |
| Vasile Rus | The University of Memphis, USA |
| Mirka Saarela | University of Jyväskylä, Finland |
| Asaf Salman | Weizmann Institute of Science, Israel |
| Sreecharan Sankaranarayanan | Carnegie Mellon University, USA |
| Petra Sauer | Beuth University of Applied Sciences, Germany |
| Eliana Scheihing | Universidad Austral de Chile, Chile |
| Robin Matthias Schmucker | Carnegie Mellon University, Germany |
| Filippo Sciarrone | Universitas Mercatorum, Italy |
| Lele Sha | Monash University, Australia |
| Lei Shi | Newcastle University, UK |
| Aditi Singh | Cleveland State University, USA |
| Daevesh Singh | Indian Institute of Technology, India |
| Maxim Skryabin | Skryabin.PRO, Russia |
| Stefan Slater | Teachers College, USA |
| Álvaro Sobrinho | Federal University of the Agreste of Pernambuco, Brazil |
| Frank Stinar | University of Illinois Urbana-Champaign, USA |
| Jun-Ming Su | National University of Tainan, Taiwan |
| Ashwin T S | Vanderbilt University, USA |
| Anaïs Tack | KU Leuven, Belgium |
| Ling Tan | Australian Council for Educational Research, Australia |
| Michelle Taub | University of Central Florida, USA |
| Khushboo Thaker | University of Pittsburgh, USA |
| Craig Thompson | The University of British Columbia, Canada |
| Emiko Tsutsumi | The University of Electro-Communications, Japan |
| Maya Usher | Technion, Israel |
| Masaki Uto | The University of Electro-Communications, Japan |
| Oswaldo Velez-Langs | Universidad de Cordoba, Colombia |
| Rémi Venant | LIUM - Le Mans Université, France |
| Markel Vigo | The University of Manchester, UK |
| Alessandro Vivas | UFVJM, Brazil |
| Tuyet-Trinh Vu | SOICT-HUST, Viet Nam |
| Deliang Wang | The University of Hong Kong, Hong Kong |
| Daniel Weitekamp | Carnegie Mellon University, USA |
| Jacob Whitehill | Worcester Polytechnic Institute, USA |
| Alistair Willis | The Open University, UK |
| Aaron Wong | University of Minnesota, USA |
| Beverly Park Woolf | University of Massachusetts, USA |
| Peter Wulff | Heidelberg University of Education, Germany |
| Elad Yacobson | Weizmann Institute of Science, Israel |
| Amelia Zafra Gómez | University of Cordoba, Spain |
| Andrew Zamecnik | University of South Australia, Australia |
| Alfredo Zapata González | Universidad Autónoma de Yucatán, Mexico |
| Diego Zapata-Rivera | Educational Testing Service, USA |
| Jiayi Zhang | University of Pennsylvania, USA |
| Yingbin Zhang | South China Normal University, China |
| Jia Zhu | The Ohio State University, USA |
| Craig Zilles | University of Illinois at Urbana-Champaign, USA |
Sponsors
Platinum
Gold
Silver
Bronze
Scholarship and Award Support
Keynote Talks
Growing with AI: A Dynamic Ecosystem for Digital Learning and Assessment
Jill Burstein & Duolingo, USA
The broader “why” in educational data mining is to enhance education with an eye toward improving learner and test-taker experiences and success. To do this, our communities use generative AI, classical AI/machine learning, and statistical and psychometric methods to model learner and test-taker data (such as, data from student-tutor dialogs, writing responses, and clickstream data). Patterns that emerge from the data enable us, for example, to better understand learning behaviors, predict academic performance, and create adaptive learning and assessment experiences that foster student and test-taker success. Thinking about our research, it is important to ask: What is my “why”? And, how does my work create impact within a dynamic learning and assessment ecosystem that includes task design, measurement, security, learner and test-taker experience, and human-centered, responsible AI? Drawing from my assessment background, I will present a theoretical assessment ecosystem, highlighting key components, leverage points, and a human-centered AI approach for accurate and responsible data-driven outcomes. Using concrete examples drawn from language assessment, the talk will examine the intersection of assessment theory and practice. Expanding on this, I will discuss how to adapt the ecosystem for learning, and the importance of the ecosystem as a growth mechanism that supports continuous AI growth and use in digital learning and assessment research and systems development. The talk will offer a perspective about how the ecosystem can help us effectively implement our “Why?”, producing theoretically sound, ethical, and impactful learning and assessment research and systems.
The Next Educational Revolution: Grand Challenges for Learning @ Scale in the Generative AI Era
Chris Piech & Stanford University, USA
The community working on learning at scale has made tremendous progress over the last decade, successfully achieving many of our previously stated grand challenges. As we enter the Generative AI era, what new ambitious milestones should we shoot for to make progress towards the joyful, high-quality education at scale for all learners? How can we get ahead of the curve of the disruption that could come to assessment and jobs? This talk will explore several potential objectives, including scaling human teaching, developing effective generative AI tools, reaching new heights in student understanding, and addressing a major persistent constraint: student motivation.
Prof. Ram Kumar EDM Test of Time Award Talk
Affect Detectors Have Scaled in Research but not in Practice
Ryan S. Baker & University of Pennsylvania, USA
In 2012, we presented one of the first papers demonstrating sensor-free affect detection. This paper established that affect detection was possible using just the interaction logs from a digital learning platform; and it validated the detectors using unseen data from humans conducting classroom observations, establishing a paradigm for the development and validation of these types of EDM models. Since then, dozens of affect detectors have been developed by scholars around the world, providing increasingly high-quality measurements of students’ boredom, frustration, confusion, and engaged concentration/flow, as well as occasionally other affective states such as anxiety and delight. The resultant detectors have been used in a large range of studies investigating affect, from fine-grained studies on affect dynamics, to research on the interaction between affect and behavior or other processes such as self-regulated learning, to research on the longitudinal implications of negative affect. And yet, unlike other EDM algorithms and models — unlike, say, knowledge tracing or dropout prediction — affect detectors are generally not in scaled deployment in real-life learning technologies. Individual papers have demonstrated the potential of affect detection for benefiting learners, but the adaptivity or reporting demonstrated in these papers has not made it into the ongoing functionality of learning systems used at scale.
EDM Data Set Award Talk
PERSUADE (Persuasive Essays for Rating, Selecting, and Understanding Argumentative and Discourse Elements)
L. Burleigh & The Learning Agency, USA
The PERSUADE dataset provides access to comprehensive data such as labels for more than 14,000 essays, including the various argumentative and rhetorical elements contained within each essay response. It also includes the effectiveness rating of these discourse elements, holistic quality scores for the essay responses, and student demographic information that includes grade level, race/ethnicity, economic background, and more. The dataset was developed as a part of the Feedback Prize project, an initiative by Georgia State University and The Learning Agency Lab. The goal of the prize is to spur the development of open-source algorithms in assisted writing feedback tools and help struggling students dramatically improve in writing. The dataset was used in a series of Kaggle challenges, which collectively drew over 10,000 participants. Because the data was publicly shared for research and other uses after the data science competition series, researchers have been able to develop more algorithms for writing feedback outside of competition. Additionally, since the PERSUADE dataset included strong diversity and fairness measures, it has also been sought out by the Gemini AI team at Google to help provide better help to students when students submit essays through their chatbot.
JEDM Talks
Using a Randomized Experiment to Compare Mastery Learning Thresholds
| Jeffrey Matayoshi | McGraw Hill ALEKS, USA |
| Eric Cosyn | McGraw Hill ALEKS, USA |
| Hasan Uzun | McGraw Hill ALEKS, USA |
| Eyad Kurd-Misto | McGraw Hill ALEKS, USA |
Many modern adaptive learning and intelligent tutoring systems implement the principles of mastery learning, where a student must demonstrate mastery of core prerequisite material before working on subsequent content within the system. Typically in such cases, a set of rules or algorithms is used to determine if a student has sufficiently mastered the concepts in a topic. In a previous work, we used a quasi-experimental design to investigate the relationship between two different mastery learning thresholds and the forgetting of the learned material. As a follow-up to this initial study, in the present work we analyze the results from a randomized experiment—or, A/B test—directly comparing these two mastery learning thresholds. These latest results seemingly agree with those from our initial study, giving evidence for the validity of the conclusions from our original quasi-experiment. In particular, we find that although students who learn with the higher mastery threshold are less likely to forget the learned knowledge, over time this difference decreases. Additionally, we build on these analyses by looking at how the relationships between the mastery thresholds change based on other factors, such as the amount of struggle students experience while learning or the subject matter being covered.
Evaluating the Effects of Assignment Report Usage on Student Outcomes in an Intelligent Tutoring System: A Randomized-Encouragement Design
| Wen Chiang Lim | Worcester Polytechnic Institute, USA |
| Neil T. Heffernan | Worcester Polytechnic Institute, USA |
| Adam Sales | Worcester Polytechnic Institute, USA |
As online learning platforms become more popular and deeply integrated into education, understanding their effectiveness and what drives that effectiveness becomes increasingly important. While there is extensive prior research illustrating the benefits of intelligent tutoring systems (ITS) for student learning, there is comparatively less focus on how teachers’ use of ITS impacts student outcomes. Much existing research on teachers’ ITS usage relies on qualitative studies, small-scale experiments, or survey data, making it difficult to identify the causal effects of their engagement with these systems. To bridge this gap, we conducted a study using a randomized encouragement design on an online mathematics platform, where teachers were randomly assigned to one of two groups: an encouragement group or a control group. Teachers in the encouragement group received a popup prompt urging them to explore the assignment report after they created an assignment, while those in the control group did not receive any additional prompts. The study focused exclusively on teachers new to the platform, as this group was expected to be most influenced by the encouragement prompt. The findings show that viewing the assignment report did not significantly impact the percentage of students who started the next assignment or their value-added scores. However, it did lead to a notable increase in the percentage of students completing the next assignment. This effect, confirmed using the Anderson-Rubin test (which is robust against weak instruments), demonstrates a measurable causal relationship between teachers’ use of assignment reports and student outcomes. Based on data from 330 teachers, this large-scale study sheds light on the causal effects of teachers engaging with ITS data on student learning and adds to the growing evidence base for effective teaching strategies in online learning environments.
Predicting Perceived Text Complexity: The Role of Person-Related Features in Profile-Based Models
| Boris Thome | Heinrich Heine University Düsseldorf, Germany |
| Friederike Hertweck | RWI - Leibniz Institute for Economic Research, Germany |
| Stefan Conrad | Heinrich Heine University Düsseldorf, Germany |
Text complexity is inherently subjective, as it is not solely determined by linguistic properties but also shaped by the reader’s perception. Factors such as prior knowledge, language proficiency and cognitive abilities influence how individuals assess the difficulty of a text. Existing methods for measuring text complexity commonly rely on quantitative linguistic features and ignore differences in the readers’ backgrounds. In this paper, we evaluate several machine learning models that determine the complexity of texts as perceived by teenagers in high school prior to deciding on their post-secondary pathways. Wecollected and publicly released a dataset from German schools, where 193 students with diverse demographic backgrounds, school grades and language abilities annotated a total of 3,954 German sentences. The text corpus is based on official study guides authored by German governmental authorities. In contrast to existing methods of determining text complexity, we build a model that is specialized to behave like the target audience, thereby accounting for the diverse backgrounds of the readers. The annotations indicate that students generally perceived the texts as significantly simpler than suggested by the Flesch-Reading-Ease score. We show that K-Nearest-Neighbors, Multilayer Perceptron and ensemble models perform well in predicting the subjectively perceived text complexity. Furthermore, SHapley Additive exPlanation (SHAP) values reveal that these perceptions not only differ by the text’s linguistic features but also by the students’ mother tongue, gender and self-estimation of German language skills. We also implement role-play prompting with ChatGPT and Claude and show that state-of-the-art large language models have difficulties in accurately assessing perceived text complexity from a student’s perspective. This work thereby contributes to the growing field of adjusting text complexity to the needs of the target audience that goes beyond quantitative linguistic features.
Developing a Feedback Taxonomy for Math: A Synergy of Perspectives through Data Mining Methods
| Seiyon Lee | University of Florida, Gainesville, USA |
| Sami Baral | Worcester Polytechnic Institute, USA |
| Hongming (Chip) Li | University of Florida, USA |
| Li Cheng | University of North Texas, USA |
| Shan Zhang | University of Florida, USA |
| Carly Siegel Thorp | Worcester Polytechnic Institute, USA |
| Jennifer St. John | Worcester Polytechnic Institute, USA |
| Tamisha Thompson | Worcester Polytechnic Institute,USA |
| Neil Heffernan | Worcester Polytechnic Institute, USA |
| Anthony F. Botelho | University of Florida, USA |
Teachers often use open-ended questions to monitor and assess students’ deeper understanding of the content. These questions are particularly useful in mathematics education as they provide more insights into students’ problem-solving processes and strategies, which is not possible through close-ended questions. While open-ended questions has the potential to promote students’ conceptual and procedural knowledge, they also present challenges for teachers to assess students’ responses and providing feedback on all problems they solve. In recent years, a growing body of research has explored methods to automatically grade students’ open responses. However, limited attention has been given to augmenting teachers’ qualitative (textual) feedback for open-ended questions in math. Also, there is a lack of consideration for how perceptions and judgments of feedback content can vary between individuals involved in designing and developing tools for automated assessment, such as teachers and researchers. In this paper, we propose a taxonomy of teacher feedback using several data mining methods (i.e., correlation, factor analysis, cluster analysis), which can serve as an analytical framework to understand the complex structure of teacher feedback. Specifically, we extract diverse perspectives from researchers and teachers who identified types of feedback content by feeding them as distinct features when building each layer of the taxonomy. With a taxonomy developed from a synergy of diverse perspectives and data mining methods, our feedback taxonomy offers a foundation for generating feedback in advanced learning systems, paving the way for tools that can design and deliver scalable, meaningful, and pedagogically effective feedback.