Search

The Indian Institute of Science is proud to host the fully in-person sixteenth iteration of the International Conference on Educational Data Mining (EDM) during July 11-14, 2023. EDM is the annual flagship conference of the International Educational Data Mining Society. The theme of this year's conference is "Educational data mining for amplifying human potential." Not all students or seekers of knowledge receive the education necessary to help them realize their full potential, be it due to a lack of resources or lack of access to high quality teaching. The dearth in high-quality educational content, teaching aids, and methodologies, and non-availability of objective feedback on how they could become better teachers, deprive our teachers from achieving their full potential. The administrators and policy makers lack tools for making optimal decisions such as optimal class sizes, class composition, and course sequencing. All these handicap the nations, particularly the economically emergent ones, who recognize the centrality of education for their growth. EDM-2023 has striven to focus on concepts, principles, and techniques mined from educational data for amplifying the potential of all the stakeholders in the education system. The spotlights of EDM-2023 include: (1) Five keynote talks by outstanding researchers of eminence; (2) A plenary Test of Time award talk and a Banquet talk; (3) Five tutorials (foundational as well as advanced); (4) Four thought provoking panels on contemporary themes; (5) Peer reviewed technical paper and poster presentations; (6) Doctoral students consortium; and (7) An enchanting cultural programme. [Individual papers are indexed in ERIC.]

ChatGPT and Bard, two chatbots powered by Large Language Models (LLMs), are propelling the educational sector towards a new era of instructional innovation. Within this educational paradigm, the present investigation conducts a comparative analysis of these groundbreaking chatbots, scrutinizing their distinct operational characteristics and applications as depicted in current scholarly discourse. ChatGPT emerges as an exemplary tool in task-oriented textual interactions, while Bard brandishes unique features such as Text-To-Speech (TTS) functionality, which enhances accessibility and inclusive education, as well as integration with Google Workspace applications. This research critically examines their utilization in various spheres such as pedagogy, academic research, Massive Open Online Courses (MOOCs), mathematics, and software programming. Findings accentuate ChatGPT's superior efficacy in content drafting, code generation, language translation, and providing clinically precise responses, notwithstanding Bard's significant potential encapsulated in its exclusive features. Furthermore, the study traverses' crucial ethical aspects, including privacy concerns and inherent bias, underscoring the profound implications of these Artificial Intelligence (AI) technologies on literature and advocating against the indiscriminate reliance on such models. [For the full proceedings, see ED636095.]

To support online learners at a large scale, extensive studies have adopted machine learning (ML) techniques to analyze students' artifacts and predict their learning outcomes automatically. However, limited attention has been paid to the fairness of prediction with ML in educational settings. This study intends to fill the gap by introducing a generic algorithm that can orchestrate with existing ML algorithms while yielding fairer results. Specifically, we have implemented logistic regression with the Seldonian algorithm and compared the fairness-aware model with fairness-unaware ML models. The results show that the Seldonian algorithm can achieve comparable predictive performance while producing notably higher fairness. [This paper was published in: "LAK21: 11th International Learning Analytics and Knowledge Conference (LAK21), April 12-16, 2021, Irvine, CA, USA," ACM, 2021.]

Consistency of learning behaviors is known to play an important role in learners' engagement in a course and impact their learning outcomes. Despite significant advances in the area of learning analytics (LA) in measuring various self-regulated learning behaviors, using LA to measure consistency of online course engagement patterns remains largely unexplored. This study focuses on modeling consistency of learners in online courses to address this research gap. Toward this, we propose a novel unsupervised algorithm that combines sequence pattern mining and ideas from information retrieval with a clustering algorithm to first extract engagement patterns of learners, represent learners in a vector space of these patterns and finally group them into groups with similar consistency levels. Using clickstream data recorded in a popular learning management system over two offerings of a STEM course, we validate our proposed approach to detect learners that are inconsistent in their behaviors. We find that our method not only groups learners by consistency levels, but also provides reliable instructor support at an early stage in a course. [This paper was published in: "LAK21: 11th International Learning Analytics and Knowledge Conference (LAK21), April 12-16, 2021, Irvine, CA, USA." ACM, 2021, pp. 226-236.]

In contrast to simple feedback, which provides students with the correct answer, elaborated feedback provides an explanation of the correct answer with respect to the student's error. Elaborated feedback is thus a challenge for AI in education systems because it requires dynamic explanations, which traditionally require logical reasoning and knowledge engineering to generate. This study presents an alternative approach that formulates elaborated feedback in terms of long-form question answering (LFQA). An off-the-shelf LFQA system was evaluated by human raters in a 2x2x2x2 ablation design that manipulated the context documents given to the LFQA model and the post-processing of model output. Results indicate that context manipulations improve performance but that postprocessing can have detrimental results. [This paper was published in: "Proceedings of the Eighth ACM Conference on Learning @ Scale," 2021, pp. 27-36.]

Over the past decade, machine learning has become an integral part of educational technologies. With more and more applications such as students' performance prediction, course recommendation, dropout prediction and knowledge tracing relying upon machine learning models, there is increasing evidence and concerns about bias and unfairness of these models. Unfair models can lead to inequitable outcomes for some groups of students and negatively impact their learning. We show by real-world examples that educational data has embedded bias that leads to biased student modeling, which urges the development of fairness formalizations and fair algorithms for educational applications. Several formalizations of fairness have been proposed that can be classified into two types: (i) group fairness and (ii) individual fairness. Group fairness guarantees that groups are treated fairly as a whole, which might not be fair to some individuals. Thus individual fairness has been proposed to make sure fairness is achieved on individual level. In this work, we focus on developing an individually fair model for identifying students at-risk of underperforming. We propose a model which is based on the idea that the prediction for a student (identifying at-risk students) should not be influenced by his/her sensitive attributes. The proposed model is shown to effectively remove bias from these predictions and hence, making them useful in aiding all students. [For the full proceedings, see ED607784.]

This study examined how machine learning and natural language processing (NLP) techniques can be leveraged to assess the interpretive behavior that is required for successful literary text comprehension. We compared the accuracy of seven different machine learning classification algorithms in predicting human ratings of student essays about literary works. Three types of NLP feature sets: unigrams (single content words), elaborative (new) n-grams, and linguistic features were used to classify idea units (paraphrase, text-based inference, interpretive inference). The most accurate classifications emerged using all three NLP features sets in combination, with accuracy ranging from 0.61 to 0.94 (F = 0.18 to 0.81). Random Forests, which employs multiple decision trees and a bagging approach, was the most accurate classifier for these data. In contrast, the single classifier, Trees, which tends to "overfit" the data during training, was the least accurate. Ensemble classifiers were generally more accurate than single classifiers. However, Support Vector Machines accuracy was comparable to that of the ensemble classifiers. This is likely due to Support Vector Machines' unique ability to support high dimension feature spaces. The findings suggest that combining the power of NLP and machine learning is an effective means of automating literary text comprehension assessment. [This paper was published in: A. Hershkovitz & L. Paquette (Eds.), "Proceedings of the 10th International Conference on Educational Data Mining" (pp. 244-249), Wuhan, China: International Educational Data Mining Society.]

An NLP algorithm was developed to assess question quality to inform feedback on questions generated by students within iSTART (an intelligent tutoring system that teaches reading strategies). A corpus of 4575 questions was coded using a four-level taxonomy. NLP indices were calculated for each question and machine learning was used to predict question quality. NLP indices related to lexical sophistication modestly predicted question type. Accuracies improved when predicting two levels (shallow versus deep). [This paper was published in: E. Andre, R. Baker, X. Hu, M. M. T. Rodrigo, & B. du Boulay (Eds.), "Proceedings of the 18th International Conference on Artificial Intelligence in Education" (pp. 523-527). Wuhan, China: Springer.]

Expertise in a domain of knowledge is characterized by a greater fluency for solving problems within that domain and a greater facility for transferring the structure of that knowledge to other domains. Deliberate practice and the feedback that takes place during practice activities serve as gateways for developing domain expertise. However, there is a difficulty in consistently aligning feedback about a learner's practice performance with the intended learning outcomes of those activities -- especially in situations where the person providing feedback is unfamiliar with the intention of those activities. To address this problem, we propose an intelligent model to automatically label opportunities for practice (assessment questions) according to the learning outcomes intended by the course designers. As a proof of concept, we used a reduced version of Bloom's Taxonomy to define the intended learning outcomes. Using a factorial design, we employed term frequency-inverse document frequency (TF-IDF) and latent Dirichlet allocation (LDA) to transform questions from text to word weightages with support vector machine (SVM) and extreme learning machine (ELM) to train and automatically label the questions. We trained our models with 120 questions labeled by the subject matter expert of an undergraduate engineering course. Compared to existing works which create models based on a selfgenerated dataset, our proposed approach uses 30 untrained questions from online/textbook sources to validate the performance of our models. Exhaustive comparison analysis of the testing set showed that TF-IDF with ELM outperformed the other combinations by yielding 0.86 reliability (F1 measure) with the subject matter expert. [For the full proceedings, see ED596512.]

Augmented Graph Grammars are a graph-based rule formalism that supports rich relational structures. They can be used to represent complex social networks, chemical structures, and student-produced argument diagrams for automated analysis or grading. In prior work we have shown that Evolutionary Computation (EC) can be applied to induce empirically-valid grammars for student-produced argument diagrams based upon fitness selection. However this research has shown that while the traditional EC algorithm does converge to an optimal fitness, premature convergence can lead to it getting stuck in local maxima, which may lead to undiscovered rules. In this work, we augmented the standard EC algorithm to induce more heterogeneous Augmented Graph Grammars by replacing the fitness selection with a novelty-based selection mechanism every ten generations. Our results show that this novelty selection increases the diversity of the population and produces better, and more heterogeneous, grammars. [For the full proceedings, see ED596512.]

This study examined how machine learning and natural language processing (NLP) techniques can be leveraged to assess the interpretive behavior that is required for successful literary text comprehension. We compared the accuracy of seven different machine learning classification algorithms in predicting human ratings of student essays about literary works. Three types of NLP feature sets: unigrams (single content words), elaborative (new) n-grams, and linguistic features were used to classify idea units (paraphrase, text-based inference, interpretive inference). The most accurate classifications emerged using all three NLP features sets in combination, with accuracy ranging from 0.61 to 0.94 (F=0.18 to 0.81). Random Forests, which employs multiple decision trees and a bagging approach, was the most accurate classifier for these data. In contrast, the single classifier, Trees, which tends to "overfit" the data during training, was the least accurate. Ensemble classifiers were generally more accurate than single classifiers. However, Support Vector Machines accuracy was comparable to that of the ensemble classifiers. This is likely due to Support Vector Machines' unique ability to support high dimension feature spaces. The findings suggest that combining the power of NLP and machine learning is an effective means of automating literary text comprehension assessment. [For the full proceedings, see ED596512. For the corresponding grantee submission, see ED577127.]

The 10th International Conference on Educational Data Mining (EDM 2017) is held under the auspices of the International Educational Data Mining Society at the Optics Velley Kingdom Plaza Hotel, Wuhan, Hubei Province, in China. This years conference features two invited talks by: Dr. Jie Tang, Associate Professor with the Department of Computer Science and Technology at Tsinghua University; and Dr. Ron Cole, President of Boulder Learning Inc. The main conference invited contributions to the Research Track and Industry Track. 122 submissions were received (71 full, 47 short, 4 industry). 18 full papers papers were accepted (25% acceptance rate) and 32 short papers for oral presentation (42% acceptance rate) and an additional 39 for poster presentations, 3 demonstrations. The industry track includes all 4 submitted industry papers and 1 paper initially submitted as a full paper. The EDM conference provides opportunities for young researchers, and particularly Ph.D. students, to present their research ideas and receive feedback from the peers and more senior researchers. This year, the Doctoral Consortium features 6 such presentations. In addition to the main program, the conference includes 3 workshops: (1) Graph-based Educational Data Mining (G-EDM 2017); (2) Sharing and Reusing Data & Analytics Methods with LearnSphere; and (3) Deep Learning with Educational Data; and 2 tutorials: (1) Why Data Standards are Critical for EDM and AIED; and (2) Principal Stratification for EDM Experiments. [For the 2016 proceedings, see ED592609.]

In the last decades there have been several attempts to use computers in Music Education. New pedagogical trends encourage incorporating technology tools in the process of learning music. Between them, those systems based on Artificial Intelligence are the most promising ones, as they can derive new information from the inputs and visualize them in several meaningful ways. This paper presents an application of machine learning to music performance which is able to discover the similarities and differences between a given performance and those from other musicians. Such a system would help students to better learn how to perform a certain piece of music, allowing them to compare with other students or master performers. [For the full proceedings, see ED562127.]

The 9th International Conference on Educational Data Mining (EDM 2016) is held under the auspices of the International Educational Data Mining Society at the Sheraton Raleigh Hotel, in downtown Raleigh, North Carolina, in the USA. The conference, held June 29-July 2, 2016, follows the eight previous editions (Madrid 2015, London 2014, Memphis 2013, Chania 2012, Eindhoven 2011, Pittsburgh 2010, Cordoba 2009 and Montreal 2008). The EDM conference is the leading international forum for high-quality research that leverages educational data, learning analytics, and machine learning to answer research questions that shed light on the learning processes. This year's conference features three invited talks by: Rakesh Agrawal, President and Founder of Data Insights Laboratories; Marcia C. Linn, Professor of the University of California at Berkeley; and Judy Kay, Professor of the University of Sydney. Judy Kay's invited paper entitled "Enabling people to harness and control EDM for lifelong, life-wide learning" is also presented in the proceedings. Together with the "Journal of Educational Data Mining" ("JEDM"), the EDM 2016 conference supports a "JEDM" Track that provides researchers a venue to deliver more substantial mature work than is possible in a conference proceedings and to present their work to a live audience. The papers submitted to this track followed the "JEDM" peer review process; three papers have been accepted to the track and were presented at the conference. The abstracts of the invited talks, panels and accepted "JEDM" Track papers can be found in these proceedings. [For the 2015 proceedings, see ED560503.]

The IADIS CELDA 2012 Conference intention was to address the main issues concerned with evolving learning processes and supporting pedagogies and applications in the digital age. There had been advances in both cognitive psychology and computing that have affected the educational arena. The convergence of these two disciplines is increasing at a fast pace and affecting academia and professional practice in many ways. Paradigms such as just-in-time learning, constructivism, student-centered learning and collaborative approaches have emerged and are being supported by technological advancements such as simulations, virtual reality and multi-agents systems. These developments have created both opportunities and areas of serious concerns. This conference aimed to cover both technological as well as pedagogical issues related to these developments. The IADIS CELDA 2012 Conference received 98 submissions from more than 24 countries. Out of the papers submitted, 29 were accepted as full papers. In addition to the presentation of full papers, short papers and reflection papers, the conference also includes a keynote presentation from internationally distinguished researchers. Individual papers contain figures, tables, and references.

The Second International Conference on Educational Data Mining (EDM2009) was held at the University of Cordoba, Spain, on July 1-3, 2009. EDM brings together researchers from computer science, education, psychology, psychometrics, and statistics to analyze large data sets to answer educational research questions. The increase in instrumented educational software and databases of student test scores, has created large repositories of data reflecting how students learn. The EDM conference focuses on computational approaches for using those data to address important educational questions. The broad collection of research disciplines ensures cross fertilization of ideas, with the central questions of educational research serving as a unifying focus. This publication presents the following papers: (1) A Comparison of Student Skill Knowledge Estimates (Elizabeth Ayers, Rebecca Nugent, Nema Dean); (2) Differences Between Intelligent Tutor Lessons, and the Choice to Go Off-Task (Ryan S.J.d. Baker); (3) A User-Driven and Data-Driven Approach for Supporting Teachers in Reflection and Adaptation of Adaptive Tutorials (Dror Ben-Naim, Michael Bain, and Nadine Marcus); (4) Detecting Symptoms of Low Performance Using Production Rules (Javier Bravo and Alvaro Ortigosa); (5) Predicting Students Drop Out: A Case Study (Gerben W. Dekker, Mykola Pechenizkiy and Jan M. Vleeshouwers); (6) Using Learning Decomposition and Bootstrapping with Randomization to Compare the Impact of Different Educational Interventions on Learning (Mingyu Feng, Joseph E. Beck and Neil T. Heffernan); (7) Does Self-Discipline impact students' knowledge and learning? (Yue Gong, Dovan Rai, Joseph E. Beck, and Neil T. Heffernan); (8) Consistency of Students' Pace in Online Learning (Arnon Hershkovitz and Rafi Nachmias); (9) Student Consistency and Implications for Feedback in Online Assessment Systems (Tara M. Madhyastha and Steven Tanimoto); (10) Edu-mining for Book Recommendation for Pupils (Ryo Nagata, Keigo Takeda, Koji Suda, Junichi Kakegawa, and Koichiro Morihiro); (11) Conditional Subspace Clustering of Skill Mastery: Identifying Skills that Separate Students (Rebecca Nugent, Elizabeth Ayers, and Nema Dean); (12) Determining the Significance of Item Order In Randomized Problem Sets (Zachary A. Pardos and Neil T. Heffernan); (13) Learning Factors Transfer Analysis: Using Learning Curve Analysis to Automatically Generate Domain Models (Philip I. Pavlik Jr., Hao Cen, Kenneth R. Koedinger); (14) Detecting and Understanding the Impact of Cognitive and Interpersonal Conflict in Computer Supported Collaborative Learning Environments (David Nadler Prata, Ryan S.J.d. Baker, Evandro d.B. Costa, Carolyn P. Rose, Yue Cui, Adriana M.J.B. de Carvalho); (15) Using Dirichlet priors to improve model parameter plausibility (Dovan Rai, Yue Gong, Joseph E. Beck); (16) Reducing the Knowledge Tracing Space (Steven Ritter, Thomas K. Harris, Tristan Nixon, Daniel Dickison, R. Charles Murray, and Brendon Towle); (17) Automatic Detection of Student Mental Models During Prior Knowledge Activation in MetaTutor (Vasile Rus, Mihai Lintean, and Roger Azevedo); (18) Automatic Concept Relationships Discovery for an Adaptive E-course (Marian Simko, Maria Bielikova); (19) Unsupervised MDP Value Selection for Automating ITS Capabilities (John Stamper and Tiffany Barnes); (20) Recommendation in Higher Education Using Data Mining Techniques (Cesar Vialardi, Javier Bravo Agapito, Leila Shafti, Alvaro and Ortigosa); (21) Developing an Argument Learning Environment Using Agent-Based ITS (ALES) (Safia Abbas and Hajime Sawamura); (22) A Data Mining Approach to Reveal Representative Collaboration Indicators in Open Collaboration Frameworks (Antonio R. Anaya and Jesus G. Boticario); (23) Dimensions of Difficulty in Translating Natural Language into First-Order Logic (Dave Barker-Plummer, Richard Cox, and Robert Dale); (24) Predicting Correctness of Problem Solving from Low-level Log Data in Intelligent Tutoring Systems (Suleyman Cetintas, Luo Si, Yan Ping Xin, and Casey Hord); (25) Back to the future: a non-automated method of constructing transfer models (Ming Feng and Joseph Beck); (26) How do Students Organize Personal Information Spaces? (Sharon Hardof-Jaffe, Arnon Hershkovitz, Hama Abu-Kishk, Ofer Bergman, and Rafi Nachmias); (27) Improving Student Question Classification (Cecily Heiner and Joseph L. Zachary); (28) Why, What, and How to Log? Lessons from LISTEN (Jack Mostow and Joseph E. Beck); (29) Process Mining Online Assessment Data (Mykola Pechenizkiy, Nikola Trcka, Ekaterina Vasilyeva, Wil van der Aalst, and Paul De Bra); (30) Obtaining Rubric Weights For Assessments By More Than One Lecturer Using A Pairwise Learning Model (J. R. Quevedo and E. Montanes); (31) Collaborative Data Mining Tool for Education (Enrique Garcia, Cristobal Romero, Sebastian Ventura, Miguel Gea, and Carlos de Castro); (32) Predicting Student Grades in Learning Management Systems with Multiple Instance Genetic Programming (Amelia Zafra and Sebastian Ventura); and (33) Visualization of Differences in Data Measuring Mathematical Skills (Lukas Zoubek and Michal Burda). Individual papers contain tables, figures, footnotes, references and appendices.

The main aim of the Organisational Committee of the international scientific colloquium Mathematics and Children is to encourage additional scientific research in the field of mathematics teaching in Croatia. The development of science and education is a part of a long-term Education Sector Development Plan 2005-2010. Following the example of Europe and the rest of the world, special attention in the field of education is given to mathematical literacy of children (PISA programme) as well as to mathematics teacher training (quality insurance in higher education). Mathematics teaching in Croatia faces modified strategic, organizational, social and technical conditions. Introducing one-shift classes in primary schools, including children with special needs (talented ones and those with difficulties) in regular classes, extended day program for all students, two teachers per class, greater mobility of children and teachers in schools and new teaching technologies demand changes in the methodology of mathematical education of both children and future teachers of mathematics. It is important to develop a life-long learning programme for teachers of mathematics that includes doctoral studies. Research in the field of mathematics teaching implies multi- and interdisciplinarity. Therefore a cooperation with scientists outside the field of mathematics (psychologists, special-ed teachers, educators) is an imperative, although we strongly believe that improvements in mathematics teaching should be encouraged within the field of mathematics. A precondition for developing new approaches and methodologies in mathematics teaching in Croatia is a first-hand experience with the results of international research and standards in mathematics teaching and defining doctoral studies within the same field. We believe that the lectures, discussions and experience exchange between Croatian and international participants of the Mathematics and Children meeting will initiate and intensify scientific cooperation in the field of mathematics teaching on the international level. We would also like for this event to initiate the start of doctoral studies in the field of mathematics teaching in Croatia following the examples from Europe and worldwide. We are very grateful to numerous Croatian and international scientists who have recognized the importance of this event and managed to find the time to attend this gathering. We would also like to thank the heads and entrepreneurs of the local community who financed this event for the most part. Papers include: (1) An Overview of the Authorised Curriculum in Teaching Mathematics Harmonised with the Bologna Declaration at the Department of Mathematics, University of Sarajevo (Sefket Arslanagic); (2) Role of Different Representations of Mathematical Concepts for Learning with Understanding (Tatjana Hodnik-Cadez); (3) The Scientific Frameworks of Teaching Mathematics (Zdravko Kurnik); (4) An Evergreen Problem (Emil Molnar); (5) Mathematically Gifted Children: What Can We Teach Them and What Can We Learn? (Vesna Vlahovic-Stetic); (6) Difficulties in Teaching Mathematics in the Second Grade of Primary School (Josip Cindric and Maja Cindric); (7) Children and Simple Combinatorial Situations (Maja Cotic and Darjo Felda); (8) National Curriculum Framework for Primary Mathematics Education--European Experiences and Trends (Aleksandra Cizmesija); (9) Dynamic Mathematics Class and the Smart Board (Sasa Duka and Damir Tomic); (10) The Dyscalculic Child, Mathematics and Teacher Study Students (Lidija Goljevacki and Aleksandra Krampac-Grljusic); (11) Is the Language of Mathematics Difficult? (The level of technical language use among teacher training college students) (Eva Kopasz); (12) Assessment and Evaluation in Mathematics Education (Zeljka Milin-Sipus); (13) Origami and Mathematics (Franka Miriam-Bruckler); (14) Attitudes of the Students of Teaching Studies towards Mathematics (Irena Misurac-Zorica); (15) Partnership among Faculties, Schools and Families for the Improvement of Mathematics Education of the Gifted Children (Ksenija Mogus and Silvija Mihaljevic); (16) Expert System for Detecting a Child's Gift in Mathematics (Margita Pavlekovic, Marijana Zekic-Susac, and Ivana Durdevic); (17) Boris Pavkovic (portrait of a distinguished methodologist and popularizer of mathematics) (Mirko Polonijo); (18) Mathematics in Play and Leisure Activities--LEGO Building Bricks (Tomislav Rudec); (19) Basic Knowledge of Mathematics and Teacher Training (Sanja Rukavina); (20) Solving Linear Equations Using Computer's Drawing Tools (Miljenko Stanic); (21) Developing the Problem-Solving Skills of Children Suffering from Dyscalculia through Mathematical Tasks with a Text (Aniko Straubingerne Kemler); (22) The Concept of the Square and the Rectangle at the Age 10-11 (Ibolya Szilagyne Szinger); (23) The Use of Computers in Teaching Mathematics (Sanja Varosanec); and (24) From Active Experimenting to Abstract Notion Concept (Amalija Zakelj and Aco Cankar). (Individual papers contain tables, graphs, and references.) [Papers are presented in both English and Croatian. These proceedings were published by the University Josip Juraj Strossmayer in Osijek, Faculty of Philosophy in Osijek. Abstract was modified to meet ERIC guidelines