Educational Data Mining 2021

June 29

15:00 Reinforcement Learning for Education: Opportunities and Challenges

15:00 – 22:00 CEST / 9:00 – 16:00 EDT
[website] [Zoom link]

15:00 Workshop for Undergraduates in Educational Data Mining and Learning Engineering

15:00 – 22:30 CEST / 9:00 – 16:30 EDT
[website] [Zoom link]

16:00 A Workshop on Process Analysis Methods For Educational Data

16:00 – 20:30 CEST / 10:00 – 14:30 EDT
[website] [Zoom link]

16:00 5th Educational Data Mining in Computer Science Education (CSEDM) Workshop

16:00 – 22:00 CEST / 10:00 – 16:00 EDT
[website] [Zoom link]

17:00 Causal Inference in Educational Data Mining

17:00 – 20:00 CEST / 11:00 – 14:00 EDT
[website] [Zoom link]

17:30 The Second Workshop of The Learner Data Institute: Big Data, Research Challenges, & Science Convergence in Educational Data Science

17:30 – 22:30 CEST / 11:30 – 16:30 EDT
[website] [Zoom link]

June 30

14:30 Opening Session

Zoom 1

15:00 Session A1: CS Education (Programming)

A1.1 15:00 Automatically classifying student help requests: a multi-year analysis Zhikai Gao, Collin Lynch, Sarah Heckman and Tiffany Barnes

A1.2 15:20 Grouping Source Code by Solution Approaches — Improving Feedback in Programming Courses Frank Höppner

15:00 Session A2: Learner Pattern Analysis

A2.1 15:00 Student-centric Model of Login Patterns: A Case Study with Learning Management Systems Varun Mandalapu, Lujie Chen, Zhiyuan Chen and Jiaqi Gong

A2.2 15:20 Embedding navigation patterns for student performance prediction Ekaterina Loginova and Dries Benoit

15:00 Session A3: Dialogue in Collaborative Learning

A3.1 15:00 Say What? Automatic Modeling of Collaborative Problem Solving Skills from Student Speech in the Wild Samuel Pugh, Shree Krishna Subburaj, Arjun Ramesh Rao, Angela Stewart, Jessica Andrews-Todd and Sidney D’Mello

A3.2 15:20 Linguistic and Gestural Coordination: Do Learners Converge in Collaborative Dialogue? Arabella Sinclair and Bertrand Schneider

Zoom 1

16:00 Session B1: Personalized Learning, Recommendation and Sequencing (evaluation and datasets)

B1.1 16:00 Estimating the Intelligent Tutor Effects on Specific Posttest Problems Adam Sales, Ethan Prihar, Neil Heffernan and John Pane

B1.2 16:20 Learning Expert Models for Educationally Relevant Tasks using Reinforcement Learning Christopher Maclellan and Adit Gupta

B1.3 16:35 Do Common Educational Datasets contain Static Information? A Statistical Study Théo Barollet, Florent Bouchez-Tichadou and Fabrice Rastello Best Short Paper Nominee

16:00 Session B2: Personalized Learning and Recommendations

B2.1 16:00 Early Prediction of Conceptual Understanding in Interactive Simulations Jade Cock, Mirko Marras, Christian Giang and Tanja Käser Best Full Paper Nominee

B2.2 16:20 Quizzing Policy Using Reinforcement Learning for Inferring the Student Knowledge State Joy He-Yueya and Adish Singla

B2.3 16:35 Recommending Knowledge Concepts on MOOC Platforms with Meta-path-based Representation Learning Guangyuan Piao

16:00 Session B3: Community and Collaborative Learning

B3.1 16:00 SimPairing - Exploring Dynamic Pairing Policies through Historical Data Simulation and User-centered Research Kexin Yang, Xuejian Wang, Vanessa Echeverria, Luettamae Lawrence, Kenneth Holstein, Nikol Rummel and Vincent Aleven

B3.2 16:20 Fair-Capacitated Clustering Tai Le Quy, Arjun Roy, Gunnar Friege and Eirini Ntoutsi

B3.3 16:35 A Novel Algorithm for Aggregating Crowdsourced Opinions Ethan Prihar and Neil Heffernan

17:00 Social: Live Music Concert

Gather Town

18:00 Keynote: Cristina Conati

Zoom 1

19:30 Session C1: CS Education (programming and prediction)

C1.1 19:30 Knowing both when and where: Temporal-ASTNN for Early Prediction of Student Success in Novice Programming Tasks Ye Mao, Yang Shi, Samiha Marwan, Thomas Price, Tiffany Barnes and Min Chi

C1.2 19:50 Learning student program embeddings using abstract execution traces Guillaume Cleuziou and Frédéric Flouvat

C1.3 20:10 Using Student Trace Logs To Determine Meaningful Progress and Struggle During Programming Problem Solving Yihuan Dong, Samiha Marwan, Preya Shabrina, Tiffany Barnes and Thomas Price

19:30 Session C2: Engagement and Self-Regulation

C2.1 19:30 Acting Engaged: Leveraging Player Persona Archetypes for Semi-Supervised Classification of Engagement Benjamin Nye, Mark G. Core, Shikhar Jaiswal, Aviroop Ghosal and Daniel Auerbach

C2.2 19:50 Early Prediction of Museum Visitor Engagement with Multimodal Adversarial Domain Adaptation Nathan Henderson, Wookhee Min, Andrew Emerson, Jonathan Rowe, Seung Lee, James Minogue and James Lester Best Full Paper Nominee

C2.3 20:10 Sharpest Tool in the Shed: Investigating SMART Models of Self-Regulation and their Impact on Learning Stephen Hutt, Jaclyn Ocumpaugh, Juliana Ma. Alexandra L. Andres, Nigel Bosch, Luc Paquette, Gautam Biswas and Ryan Baker

19:30 Session C3: Learner Knowledge and Performance Modeling

C3.1 19:30 Learning from Non-Assessed Resources: Deep Multi-Type Knowledge Tracing Chunpai Wang, Siqian Zhao and Shaghayegh Sahebi

C3.2 19:50 Student Performance Prediction Using Dynamic Neural Models Marina Delianidi, Konstantinos Diamantaras, George Chrysogonidis and Vasileios Nikiforidis

C3.3 20:10 Going Online: A simulated student approach for evaluating knowledge tracing in the context of mastery learning Qiao Zhang and Christopher MacLellan

20:40 Poster Session 1

Gather Town

Poster Session 1Poster Session 2

P1 Predictive Sequential Pattern Mining via Interpretable Convolutional Neural Networks Lan Jiang and Nigel Bosch

P2 The CommonLit Ease of Readability (CLEAR) Corpus Scott Crossley, Aron Heintz, Joon Choi, Jordan Batchelor, Mehrnoush Karimi and Agnes Malatinszky

P3 Using Data Quality to compare the Prediction Accuracy based on diverse annotated Tutor Scorings Sylvio Rüdian and Niels Pinkwart

P4 Measuring the Academic Impact of Course Sequencing using Student Grade Data Tess Gutenbrunner, Daniel Leeds, Spencer Ross, Michael Riad-Zaky and Gary Weiss

P5 Mining Course Groupings based on Academic Performance Daniel Leeds, Tianyi Zhang and Gary Weiss

P6 Predicting Executive Functions in a Learning Game: Accuracy and Reaction Time Jing Zhang, Teresa Ober, Yang Jiang, Jan Plass and Bruce Homer

Q1 Deep learning for sentence clustering in essay grading support Li-Hsin Chang, Iiro Rastas, Jenna Kanerva, Valtteri Skantsi, Sampo Pyysalo and Filip Ginter

Q2 Classroom Analytics for the Teacher, by the Teacher: Building Interpretable Descriptors for Student Posture Analysis in a Physical Classroom Lujie Chen and David Gerritsen

Q3 The Impact of Learning Analytics on Student Performance and Satisfaction in a Higher Education Course Dimitrios Tzimas and Stavros Demetriadis

Q4 Academic Integrity in Online Education during the COVID-19 Pandemic: a Social Media Mining Study Mohammad Parsa and Lukasz Golab

Q5 Is It Fair? Automated Open Response Grading John A. Erickson, Anthony F. Botelho, Zonglin Peng, Rui Huang, Meghana V. Kasal and Neil Heffernan

Q6 To Scale or Not to Scale: Comparing Popular Sentiment Analysis Dictionaries on Educational Twitter Data Conrad Borchers, Joshua Rosenberg, Ben Gibbons, Macy Alana Burchfield and Christian Fischer

R1 SimGrade: Using Code Similarity Measures for More Accurate Human Grading Sonja Johnson-Yu, Nicholas Bowman, Mehran Sahami and Chris Piech

R2 Feedback and Self-Regulated Learning in Science Reading Effat Farhana, Andrew Potter, Teomara Rutherford and Collin F. Lynch

R3 Text Representations of Math Tutorial Videos forClustering, Retrieval, and Learning Gain Prediction Pichayut Liamthong and Jacob Whitehill

R4 The Cold Start Problem and Interpretation of Knowledge Tracing Models’ Predictive Performance Jiayi Zhang, Rohini Das, Ryan S. Baker and Richard Scruggs

R5 Are Violations of Student Privacy “Quick and Easy”? Investigating the Privacy of Students’ Images and Names in the Context of K-12 Educational Institution’s Posts on Facebook Macy Burchfield, Joshua Rosenberg, Conrad Borchers, Tayla Thomas, Benjamin Gibbons and Christian Fischer

R6 Fine-Grained Versus Coarse-Grained Data for Estimating Time-on-Task in Learning Programming Juho Leinonen, Francisco Enrique Vicente Castro and Arto Hellas

S2 Predicting Young Students' Self-Regulated Learning Deficits Through Their Activity and Self-Evaluation Traces Thomas Sergent, Morgane Daniel, François Bouchet and Thibault Carron

S3 Catalog: An educational content tagging system Saad Khan, Joshua Rosaler, Jesse Hamer and Tiago Almeida

S4 Generate: A NLG system for educational content creation Saad Khan, Jesse Hamer and Tiago Almeida

S5 Execution Trace Based Feature Engineering To Enable Formative Feedback on Visual, Interactive Programs Wengran Wang, Gordon Fraser, Tiffany Barnes, Chris Martens and Thomas Price

S6 Detecting Careless Responding to Assessment Items in a Virtual Learning Environment Using Person-fit Indices and Random Forest Sanaz Nazari, Walter Leite and Anne Huggins-Manley

July 01

14:30 Session D1: Student Performance Prediction

D1.1 14:30 Can Feature Predictive Power Generalize? Benchmarking Early Predictors of Student Success across Flipped and Online Courses Mirko Marras, Julien Tuan Tu Vignoud and Tanja Käser

D1.2 14:50 Knowledge Transfer by Discriminative Pre-training for Academic Performance Prediction Byungsoo Kim, Hangyeol Yu, Dongmin Shin and Youngduck Choi Best Short Paper Nominee

D1.3 15:05 Combining Cognitive and Machine Learning Models to Mine CPR Training Histories for Personalized Predictions Florian Sense, Michael Krusmark, Joshua Fiechter, Michael G. Collins, Lauren Sanderson, Joshua Onia and Tiffany Jastrzembski Best Short Paper Nominee

14:30 Session D2: NLP and Essay Evaluation

D2.1 14:30 Which Hammer should I Use? A Systematic Evaluation of Approaches for Classifying Educational Forum Posts Lele Sha, Mladen Rakovic, Alexander Whitelock-Wainwright, David Carroll, Victoria M. Yew, Dragan Gasevic and Guanliang Chen

D2.2 14:50 Automated Claim Identification Using NLP Features in Student Argumentative Essays Qian Wan, Scott Crossley, Michelle Banawan, Renu Balyan, Danielle McNamara and Laura Allen

D2.3 15:05 Integrating Deep Learning into An Automated Feedback Generation System for Automated Essay Scoring Chang Lu and Maria Cutumisu

14:30 Session D3: Learner Knowledge and Performance Modeling

D3.1 14:30 Behavioral Testing of Deep Knowledge Tracing Models Minsam Kim, Yugeun Shim, Seewoo Lee, Hyunbin Loh and Juneyoung Park

D3.2 14:50 Predicting Student Performance Using Teacher Observation Reports Menna Fateen and Tsunenori Mine

D3.3 15:05 LANA: Towards Personalized Deep Knowledge Tracing Through Distinguishable Interactive Sequences Yuhao Zhou, Xihua Li, Yunbo Cao, Xuemin Zhao, Qing Ye and Jiancheng Lv

15:30 Session E1: Knowledge Tracing

E1.1 15:30 Deep-IRT with independent student and item networks Emiko Tsutsumi, Ryo Kinoshita and Maomi Ueno

E1.2 15:45 Context-aware knowledge tracing integrated with the exercise representation and association in mathematics Tao Huang, Mengyi Liang, Huali Yang, Zhi Li, Tao Yu and Shengze Hu

E1.3 16:00 Effects of Algorithmic Transparency in Bayesian Knowledge Tracing on Trust and Perceived Accuracy Kimberly Williamson and Rene Kizilcec

E1.4 16:15 pyBKT: An Accessible Library of Bayesian Knowledge Tracing Models Anirudhan Badrinath, Frederic Wang and Zach Pardos

15:30 Session E2: Institutional analytics

E2.1 15:30 Assessing attendance by peer information Pan Deng, Jianjun Zhou, Jing Lyu and Zitong Zhao

E2.2 15:45 Gaining Insights on Student Course Selection in Higher Education with Community Detection Erla Guðrún Sturludóttir, Eydís Arnardóttir, Gísli Hjálmtýsson and María Óskarsdóttir

E2.3 16:00 Exploring the Importance of Factors Contributing to Dropouts in Higher Education Over Time Hasan Tanvir and Irene-Angelica Chounta

E2.4 16:15 Sentiment Analysis of Student Surveys - A Case Study on Assessing the Impact of the COVID-19 Pandemic on Higher Education Teaching Haydée Guillot Jiménez, Anna Carolina Finamore, Marco Antonio Casanova and Gonçalo Simões

15:30 Session E3: JEDM

E3.1 15:30 Extending Adaptive Spacing Heuristics to MultiSkill Items Benoît Choffin, Fabrice Popineau and Yolaine Bourda

E3.2 15:45 Affect, Support and Personal Factors: Multimodal Causal Models of One-on-one Coaching Lujie Karen Chen, Joseph Ramsey and Artur Dubrawski

E3.3 16:00 Mapping Python Programs to Vectors using Recursive Neural Encodings Benjamin Paaßen, Jessica McBroom, Bryn Jeffries Grok, Irena Koprinska and Kalina Yacef

17:00 Keynote: Sidney D’Mello

Zoom 1

18:30 Session F1: Personalized Learning and Sequencing

F1.1 18:30 Topic Transitions in MOOCs: An Analysis Study Fareedah Alsaad, Thomas Reichel, Yuchen Zeng and Abdussalam Alawini

F1.2 18:50 The effects of a personalized recommendation system on students’ high-stakes achievement scores: A field experiment Nilanjana Chakraborty, Samrat Roy, Walter Leite and George Michailidis

F1.3 19:05 Finding the optimal topic sequence for online courses using SERPs as a Proxy Sylvio Rüdian and Niels Pinkwart

18:30 Session F2: Learning Knowledge & Performance Modeling in CS Education

F2.1 18:30 Just a Few Expert Constraints Can Help: Humanizing Data-Driven Subgoal Detection for Novice Programming Samiha Marwan, Yang Shi, Ian Menezes, Min Chi, Tiffany Barnes and Thomas Price Best Full Paper Nominee

F2.2 18:50 Modeling Creativity in Visual Programming: From Theory to Practice Anastasia Kovalkov, Benjamin Paassen, Avi Segal, Kobi Gal and Niels Pinkwart

F2.3 19:05 More With Less: Exploring How to Use Deep Learning Effectively through Semi-supervised Learning for Automatic Bug Detection in Student Code Yang Shi, Ye Mao, Tiffany Barnes, Min Chi and Thomas Price

18:30 Session F3: Automatic Assessment

F3.1 18:30 Generative Grading: Near Human-level Accuracy for Automated Feedback on Richly Structured Problems Ali Malik, Mike Wu, Vrinda Vasavada, Jinpeng Song, Madison Coots, John Mitchell, Noah Goodman and Chris Piech

F3.2 18:50 Automatic short answer grading with SBERT on out-of-sample questions Aubrey Condor, Max Litster and Zachary Pardos

F3.3 19:05 ALL-IN-ONE: Multi-Task Learning BERT models for Evaluating Peer Assessments Qinjin Jia, Jialin Cui, Yunkai Xiao, Chengyuan Liu, Parvez Rashid and Edward Gehringer

19:30 Session G1: Evaluation and Statistical Methods

Zoom 1

G1.1 19:30 Investigating the Validity of Methods Used to Adjust for Multiple Comparisons in Educational Data Mining Jeffrey Matayoshi and Shamya Karumbaiah

G1.2 19:50 Experimental Evaluation of Similarity Measures for Educational Items Jaroslav Čechák and Radek Pelánek

19:30 Session G2: Industry Track

Zoom 2

H1.1 19:30 Online Estimation of Student Ability and Item Difficulty with Glicko-2 Rating System on Stratified Data Jaesuk Park

G2.1 19:50 Methods for Language Learning Assessment at Scale: Duolingo Case Study Lucy Portnoff, Erin Gustafson, Joseph Rollinson and Klinton Bicknell

19:30 Doctoral Consortium

Zoom 3

DC1 19:30 A Longitudinal Approach to Detect Patterns and Predict Help-Seeking Behaviour in Adaptive Educational Systems Raquel Horta-Bartomeu, Olga C. Santos

DC2 19:50 Mixed Data Sampling in Learning Analytics Julian Langenhagen

DC3 20:10 Towards fair, explainable and actionable clustering for learning analytics Tai Le Quy, Eirini Ntoutsi

DC4 20:30 Towards a Conception and Integration of an Educational Social Network into an Institutional Learning Platform Romaric Bassole, Frédéric T. Ouedraogo, Laurence Capus

21:00 Panel: Diversity, Equity, and Inclusion in EDM Research

Zoom 1

July 02

14:10 Poster Session 2

Gather Town

Poster Session 2

P7 Leveraging Survey and Motion Sensors Data to Promote Gender Inclusion in Makerspaces Edwin Chng, Stephanie Yang, Gahyun Sung, Tyler Yoo and Bertrand Schneider

P8 Identifying Hubs in Undergraduate Course Networks Based on Scaled Co-Enrollments Gary Weiss, Nam Nguyen, Karla Dominguez and Daniel Leeds

P9 A New Readability Assessment Tool Rebecca Watson and Ekaterina Kochmar

P10 Early Detection of At-risk Students based on Knowledge Distillation RNN Models Ryusuke Murata, Tsubasa Minematsu and Atsushi Shimada

P11 Demonstrating REACT: a Real-time Educational AI-powered Classroom Tool Ajay Kulkarni and Olga Gkountouna

P12 Tracing Knowledge for Tracing Dropouts: Multi-Task Training for Study Session Dropout Prediction Seewoo Lee, Kyu Seok Kim, Jamin Shin and Juneyoung Park

P13 Deep learning for sentence clustering in essay grading support Li-Hsin Chang, Iiro Rastas, Jenna Kanerva, Valtteri Skantsi, Sampo Pyysalo and Filip Ginter

Q7 Sex-Related Behavioral Differences in Online Math Classes: An Epistemic Network Analysis Yufei Gu and Kun Xu

Q8 Restructuring Curricular Patterns Using Bayesian Networks Ahmad Slim, Gregory Heileman, Chaouki Abdallah, Ameer Slim and Najem Sirhan

Q9 Linguistic Features of Discourse within an Algebra Online Discussion Board Michelle Banawan, Renu Balyan, Jinnie Shin, Walter Leite and Danielle McNamara

Q10 Towards Difficulty Controllable Selection of Next-Sentence Prediction Questions Jingrong Feng and Jack Mostow

Q11 Towards Explainable Student Group Collaboration Assessment Models Using Temporal Representations of Individual Student Role and Behavioral Cues Anirudh Som, Sujeong Kim, Bladimir Lopez-Prado, Svati Dhamija, Nonye Alozie and Amir Tamrakar

Q12 Mining sequential patterns with high usage variation Yingbin Zhang and Luc Paquette

Q13 The Cold Start Problem and Interpretation of Knowledge Tracing Models’ Predictive Performance Jiayi Zhang, Rohini Das, Ryan S. Baker and Richard Scruggs

R7 Analysis of Factors Influencing User Contribution and Predicting Involvement of Users on Stack Overflow Maliha Mahbub, Najia Manjur, Mahjabin Alam and Julita Vassileva

R8 Analyzing Ranking Strategies to Characterize Competition for Co-Operative Work Placements Shivangi Chopra and Lukasz Golab

R9 AQuAA: Analytics for Quality Assurance in Assessment Manqian Liao, Yigal Attali and Alina A. von Davier

R10 Analysis of stopping criteria for Bayesian Adaptive Mastery Assessment Androniki Sapountzi, Sandjai Bhulai, I. Cornelisz and Chris Van Klaveren

R11 Automatic Domain Model Creation and Improvement Philip I. Pavlik Jr., Luke Eglington and Liang Zhang

R12 LMS Log Data Analysis from Fully-Online Flipped Classrooms: An Exploratory Case Study via Regularization Jin Eun Yoo and Minjeong Rho

R13 Towards automated content analysis of feedback: A multi-language study Ikenna Osakwe, Alexander Whitelock-Wainwright, Guanliang Chen, Rafael Ferreira Mello, Anderson Pinheiro Cavalcanti and Dragan Gašević

S7 Recommendation System for Engineering Programs Candidates Bruno Mota da Silva and Claudia Antunes

S8 Mining Course Groupings based on Academic Performance Daniel Leeds, Tianyi Zhang and Gary Weiss

S9 Predictive Sequential Pattern Mining via Interpretable Convolutional Neural Networks Lan Jiang and Nigel Bosch

S10 To Scale or Not to Scale: Comparing Popular Sentiment Analysis Dictionaries on Educational Twitter Data Conrad Borchers, Joshua Rosenberg, Ben Gibbons, Macy Alana Burchfield and Christian Fischer

S11 The Impact of Learning Analytics on Student Performance and Satisfaction in a Higher Education Course Dimitrios Tzimas and Stavros Demetriadis

S12 Classroom Analytics for the Teacher, by the Teacher: Building Interpretable Descriptors for Student Posture Analysis in a Physical Classroom Lujie Chen and David Gerritsen

15:30 Social: Crêpe Party

Zoom 2

16:30 Keynote: Pierre Dillenbourg

Zoom 1

18:00 Test of Time Award: Cristobal Romero

Zoom 1

19:30 Session H1: Industry

H1.2 19:30 Benefits of alternative evaluation methods for Automated Essay Scoring Øistein E. Andersen, Rebecca Watson, Zheng Yuan and Kevin Yet Fong Cheung

H1.3 19:45 UPreG: An Unsupervised approach for building the Concept Prerequisite Graph Varun Sabnis, Kumar Abhinav, Venkatesh Subramania, Alpana Dubey and Padmaraj Bhat

19:30 Session H2: Learner Knowledge and Performance Modeling

H2.1 19:30 Toward Improving Student Model Estimates through Assistance Scores in Principle and in Practice Napol Rachatasumrit and Kenneth Koedinger

H2.2 19:45 Analyzing Student Success and Mistakes in Virtual Microscope Structure Search Tasks Benjamin Paaßen, Andreas Bertsch, Katharina Langer-Fischer, Sylvio Rüdian, Xia Wang, Rupali Sinha, Jakub Kuzilek, Stefan Britsch and Niels Pinkwart

H2.3 20:00 Studying Retrieval Practice in an Intelligent Tutoring System Jeffrey Matayoshi, Hasan Uzun, Eric Cosyn Best Paper Award at L@S 2020

19:30 Session H3: Learner Cognitive and Behavior Modeling

H3.1 19:30 Using Keystroke Analytics to Understand Cognitive Processes during Writing Mo Zhang, Hongwen Guo and Xiang Liu Best Short Paper Nominee

H3.2 19:45 Speeding up without Loss of Accuracy: Item Position Effects on Examinees’ Performance in University Exams Leonardo Vida, Maria Bolsinova and Matthieu J. S. Brinkhuis

H3.3 20:00 What you apply is not what you learn! Examining students’ strategies in German capitalization tasks Nathalie Rzepka, Hans-Georg Müller and Katharina Simbeck

20:30 Session I1: Automatic Assessment

I1.1 20:30 Improving Automated Scoring of Student Open Responses in Mathematics Sami Baral, Anthony F Botelho, John A Erickson, Priyanka Benachamardi and Neil T Heffernan Best Full Paper Nominee

I1.2 20:50 Automatic Assessment of the Design Quality of Python Programs with Personalized Feedback Walker Orr and Nathaniel Russell

I1.3 21:05 On the Limitations of Human-Computer Agreement in Automated Essay Scoring Afrizal Doewes and Mykola Pechenizkiy

20:30 Session I2: Domain Knowledge Models and Math Education

I2.1 20:30 Math Operation Embeddings for Open-ended Solution Analysis and Feedback Mengxue Zhang, Zichao Wang, Richard Baraniuk and Andrew Lan

I2.2 20:50 Math Question Solving and MCQ Distractor Generation with attentional GRU Networks Neisarg Dave, Riley Owen Bakes, Bart Pursel and C. Lee Giles

I2.3 21:05 Targeting Design-Loop Adaptivity Stephen Fancsali, Hao Li, Michael Sandbothe and Steven Ritter

20:30 Session I3: Behavior Modeling

I3.1 20:30 Student Strategy Prediction using a Neuro-Symbolic Approach Anup Shakya, Vasile Rus and Deepak Venugopal

I3.2 20:50 Student Practice Sessions Modeled as ICAP Activity Silos Adam Gaweda and Collin Lynch

I3.3 21:05 From Detail to Context: Modeling Distributed Practice Intensity and Timing by Multiresolution Signal Analysis Cheng-Yu Chung and I-Han Hsiao

21:30 Awards & Closing

Zoom 1

Code of Conduct

The annual conference of the Educational Data Mining society is intended to foster community and exchange of ideas among those working in the field of educational data mining.

Everyone involved in the conference -- from organizers to presenters to attendees to sponsors -- is expected to adhere to the code of conduct throughout the conference, both in their formal and informal participation in the conference and in all channels of interaction and communication, including social media. The EDM 2021 code of conduct described here is inspired by and adapted from similar codes of conduct from recent international conferences on machine learning and artificial intelligence (ICLR, ICML).

Everyone has a right to participate in the conference free from harassment and intimidation, and in an environment that recognizes the inherent worth of all people and their potential to contribute valuable ideas to the scientific discussion. Everyone has the right to a safe and discimination-free conference regardless of race, ethnicity, national origin, gender identity, gender expression, socioeconomic status, sexual orientation, disability status, religion or lack of religion, physical appearance, technology choices, or other identities or beliefs. What may be intended as “joking” can be offensive and demeaning. Bullying, intimidation, personal attacks, harassment, sustained disruption of talks or other events, and behavior that interferes with another participant's full participation will not be tolerated. This includes but is not limited to sexual harassment, unwelcome repeated contacts, harassing photography or recording, unwelcome sexual attention, display of belittling or gratuitous images in public spaces, public vulgar exchanges, and diminutive characterizations, which are all unwelcome in this community. Revealing private information in a public setting without permission, such as posting a participant’s personal information, is not permitted.

If you see someone engaging in any of these behaviors, please ask them to stop. If you experience or observe any behavior you’re concerned about or that you believe may constitute harassment or discrimination, please report it to program co-chairs Sharon Hsiao ( and Shaghayegh (Sherry) Sahebi ( via email with subject line “EDM’21 - concerning observation”. During the conference, we will follow up within 24 hours, and outside the days of the conference, we will respond within two business days.

Consequences for violating this code of conduct will be decided by the program and general chairs and may include a formal or informal warning, expulsion from the virtual conference with no refund, barring from participation in future conferences or the EDM organization, reporting the incident to the offender’s local institution or funding agencies, or other actions. A response of "just joking" will not be accepted; behavior can be harassing without an intent to offend. If action is taken, an appeals process will be made available.