Educational Data Mining and Learning Analytics
Published 1 January 2014
Ryan S. Baker, Paul Salvador Inventado
Citations909
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
How these methods emerged in the early days of research in this area is discussed, which methods have seen particular interest in the EDM and learning analytics communities, and how this has changed as the field matures and has moved to making significant contributions to both educational research and practice.
Abstract
This page, from the The Center for Innovative Research in Cyberlearning (CIRCL), offers information on the related concepts of educational data mining and learning analytics, both of which focus on capturing and analyzing information about educational systems and the teaching and learning process, and efforts to make sense of and utilize that captured data. An issues list includes an introduction to some of the issues that go along with data collection in an educational setting, including privacy and ethics. The site also offers substantial lists of further resources and readings for instructors interested in the topic, and a smaller set of links to resources and organizations focused on sharing this educational data.Â
Keywords
Computer Science
Machine LearningRandom Forests
126,192 Citations2001Leo Breiman
Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Journal of the Royal Statistical Society Series B (Statistical Methodology)Controlling the False Discovery Rate: A Practical and Powerful Approach to Multiple Testing
108,736 Citations1995Yoav Benjamini, Yosef Hochberg
Elsevier eBooksData Mining: Practical Machine Learning Tools and Techniques
25,718 Citations2011Ian H. Witten, Eibe Frank
RadiologyThe meaning and use of the area under a receiver operating characteristic (ROC) curve.
21,812 Citations1982J A Hanley, Barbara J. McNeil
A representation and interpretation of the area under a receiver operating characteristic (ROC) curve obtained by the "rating" method, or by mathematical predictions based on patient characteristics, is presented and it is shown that in such a setting the area represents the probability that a randomly chosen diseased subject is (correctly) rated or ranked with greater suspicion than a random chosen non-diseased subject.
Communications of the ACMMapReduce
18,538 Citations2008Jay B. Dean, Sanjay Ghemawat
This presentation explains how the underlying runtime system automatically parallelizes the computation across large-scale clusters of machines, handles machine failures, and schedules inter-machine communication to make efficient use of the network and disks.
Choice Reviews OnlineFinding groups in data: an introduction to cluster analysis
10,614 Citations1991
The relationship between Precision-Recall and ROC curves
6,255 Citations2006Jesse Davis, Mark Goadrich
It is shown that a deep connection exists between ROC space and PR space, such that a curve dominates in R OC space if and only if it dominates in PR space.
Big data: The next frontier for innovation, competition, and productivity
5,228 Citations2011James Manyika
The amount of data in the authors' world has been exploding, and analyzing large data sets will become a key basis of competition, underpinning new waves of productivity growth, innovation, and consumer surplus, according to research by MGI and McKinsey.
Lecture notes in statisticsCausation, Prediction, and Search
4,740 Citations1993Peter Spirtes, Clark Glymour +1 more
The authors axiomatize the connection between causal structure and probabilistic independence, explore several varieties of causal indistinguishability, formulate a theory of manipulation, and develop asymptotically reliable procedures for searching over equivalence classes of causal models.
Cambridge University Press eBooksThe Cambridge Handbook of the Learning Sciences
4,590 Citations2005R. Keith Sawyer, R. Keith Sawyer +23 more
The MIT Press eBooksCausation, Prediction, and Search
4,470 Citations2001Peter Spirtes, Clark Glymour +1 more
Data & Knowledge EngineeringKnowledge engineering: Principles and methods
3,549 Citations1998Rudi Studer, V. Richard Benjamins +1 more
The paradigm shift from a transfer view to a modeling view is discussed and two approaches which considerably shaped research in Knowledge Engineering are described: Role-limiting Methods and Generic Tasks.
An Easy Guide to Factor Analysis
3,265 Citations2014Paul Kline
The use and Abuse of Factor Analysis in Research References Index is illustrated with examples from Personality Tests and a comparison of the use and abuse of factor analysis in the context of clinical trials.
Lecture notes in computer scienceMining sequential patterns: Generalizations and performance improvements
2,686 Citations1996Ramakrishnan Srikant, Rakesh Agrawal
This work adds time constraints that specify a minimum and/or maximum time period between adjacent elements in a pattern, and relax the restriction that the items in an element of a sequential pattern must come from the same transaction.
Psychological MethodsAn introduction to recursive partitioning: Rationale, application, and characteristics of classification and regression trees, bagging, and random forests.
2,517 Citations2009Carolin Strobl, James D. Malley +1 more
The aim of this work is to introduce the principles of the standard recursive partitioning methods as well as recent methodological improvements, to illustrate their usage for low and high-dimensional data exploration, but also to point out limitations of the methods and potential pitfalls in their practical application.
The Annals of StatisticsThe positive false discovery rate: a Bayesian interpretation and the q-value
2,305 Citations2003John D. Storey
This work introduces a modified version of the FDR called the “positive false discovery rate” (pFDR), which can be written as a Bayesian posterior probability and can be connected to classification theory.
Psychology Press eBooksThe Atomic Components of Thought
2,178 Citations2014John R. Anderson, Christian Lebière
The preface to the book describes how C.R. Anderson's Cognitive Arithmetic transformed into Knowledge Representation and how M. Lovett's choice changed the way that people viewed the world around them.
User Modeling and User-Adapted InteractionKnowledge tracing: Modeling the acquisition of procedural knowledge
2,133 Citations1995Albert T. Corbett, John R. Anderson
An effort to model students' changing knowledge state during skill acquisition and a series of studies is reviewed that examine the empirical validity of knowledge tracing and has led to modifications in the process.
IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)Educational Data Mining: A Review of the State of the Art
2,127 Citations2010Cristóbal Romero, Sebastián Ventura
The most relevant studies carried out in educational data mining to date are surveyed and the different groups of user, types of educational environments, and the data they provide are described.
Dynamic itemset counting and implication rules for market basket data
1,954 Citations1997Sergey Brin, Rajeev Motwani +2 more
A new algorithm for finding large itemsets which uses fewer passes over the data than classic algorithms, and yet uses fewer candidate itemsets than methods based on sampling and a new way of generating “implication rules” which are normalized based on both the antecedent and the consequent.
IEEE Intelligent SystemsThe Unreasonable Effectiveness of Data
1,791 Citations2009Alon Halevy, Peter Norvig +1 more
A trillion-word corpus - along with other Web-derived corpora of millions, billions, or trillions of links, videos, images, tables, and user interactions - captures even very rare aspects of human behavior.
Changing Course: Ten Years of Tracking Online Education in the United States.
1,598 Citations2013I. Elaine Allen, Jeff Seaman
This document reports on the state of online learning among higher education institutions in the United States and addresses the following key issues: massive open online courses (MOOCS), are the authors heading for online 2.0?
Psychological ScienceNew Conceptualizations of Practice: Common Principles in Three Paradigms Suggest New Concepts for Training
1,579 Citations1992Richard A. Schmidt, Robert A. Bjork
American PsychologistThe situativity of knowing, learning, and research.
1,522 Citations1998James G. Greeno
Expert Systems with ApplicationsEducational data mining: A survey from 1995 to 2005
1,464 Citations2006Cristóbal Romero, Sebastián Ventura
This paper surveys the application of data mining to traditional educational systems, particular web- based courses, well-known learning content management systems, and adaptive and intelligent web-based educational systems.
Educational ResearcherThe Interplay of Evidence and Consequences in the Validation of Performance Assessments
1,311 Citations1994Samuel Messick
Zenodo (CERN European Organization for Nuclear Research)The State of Educational Data Mining in 2009: A Review and Future Visions
1,301 Citations2009Ryan S. Baker, Kalina Yacef
ScienceThe Human Genome Project: Lessons from Large-Scale Biology
1,283 Citations2003Francis S. Collins, Michael J. Morgan +1 more
The Human Genome Project has been the first major foray of the biological and medical research communities into “big science” and many of the lessons learned will be applicable to future large-scale projects in biology.
Applied Psychological MeasurementCognitive Assessment Models with Few Assumptions, and Connections with Nonparametric Item Response Theory
1,007 Citations2001Brian W. Junker, Klaas Sijtsma
Some usability and interpretability issues for single-strategy cognitive assessment models are considered and an example shows that these models can be sensitive to cognitive attributes, even in data designed to well fit the Rasch model.
Computers & EducationMining LMS data to develop an “early warning system” for educators: A proof of concept
1,006 Citations2009Leah P. Macfadyen, Shane Dawson
This study affirms that pedagogically meaningful information can be extracted from LMS-generated student tracking data, and discusses how these findings are informing the development of a customizable dashboard-like reporting tool for educators that will extract and visualize real-time data on student engagement and likelihood of success.
Learning analytics and educational data mining
969 Citations2012George Siemens, Ryan S. Baker
This paper argues for increased and formal communication and collaboration between these communities in order to share research, methods, and tools for data mining and analysis in the service of developing both LAK and EDM fields.
Educational PsychologistThe role of cognitive engagement in classroom learning and motivation
851 Citations1983Lyn Corno, Ellen B. Mandinach
Cognition and InstructionInventing to Prepare for Future Learning: The Hidden Efficiency of Encouraging Original Student Production in Statistics Instruction
739 Citations2004Daniel L. Schwartz, Taylor Martin
Two studies on teaching descriptive statistics to 9th-grade students examined whether invention activities may prepare students to learn found that invention activities, when coupled with subsequent learning resources like lectures, led to strong gains in procedural skills, insight into formulas, and abilities to evaluate data from an argument.
Child DevelopmentAll Other Things Being Equal: Acquisition and Transfer of the Control of Variables Strategy
734 Citations1999Zhe Chen, David Klahr
This study addressed an important issue in scientific reasoning and cognitive development: how children acquire a domain-general processing strategy (Control of Variables Strategy or CVS) and generalize it across various contexts.
Cognitive ScienceThe Knowledge‐Learning‐Instruction Framework: Bridging the Science‐Practice Chasm to Enhance Robust Student Learning
726 Citations2012Kenneth R. Koedinger, Albert T. Corbett +1 more
The Knowledge-Learning-Instruction framework is described, which promotes the emergence of instructional principles of high potential for generality, while explicitly identifying constraints of and opportunities for detailed analysis of the knowledge students may acquire in courses.
ACM SIGMOD RecordDynamic itemset counting and implication rules for market basket data
611 Citations1997Sergey Brin, Rajeev Motwani +2 more
Handbook of Educational Data Mining
571 Citations2010Cocea, Mihaela, Weibelzahl, Stephan
A Response-Time Model for Bottom-Out Hints as Worked Examples and Recommendation in E-Learning Systems Based on Content-Based Student Profiles.
Lecture notes in computer scienceLearning Factors Analysis – A General Method for Cognitive Model Evaluation and Improvement
567 Citations2006Hao Cen, Kenneth R. Koedinger +1 more
A semi-automated method for improving a cognitive model called Learning Factors Analysis is proposed that combines a statistical model, human expertise and a combinatorial search to evaluate an existing cognitive model and to generate and evaluate alternative models.
Cognitively Diagnostic Assessment
489 Citations2012Paul D. Nichols, Susan F. Chipman +1 more
This book discusses how to model students' Cognitive Structures and their development using the "Fill-in-the-Structure" (FITS) Technique, and an Evaluation of Approaches to Diagnostic Assessment.
User Modeling and User-Adapted InteractionAddressing the assessment challenge with an online system that tutors as it assesses
466 Citations2009Mingyu Feng, Neil T. Heffernan +1 more
The results show that the ASSISTment system can do a reliably better job predicting student end-of-year exam scores by leveraging the interaction data, and the model based on only the interaction information makes better predictions than the traditional assessment model that uses only information about correctness on the test items.
ETS Research Report SeriesA BRIEF INTRODUCTION TO EVIDENCE‐CENTERED DESIGN
451 Citations2003Robert J. Mislevy, Russell G. Almond +1 more
This paper presents the high-level models of the Conceptual Assessment Framework (CAF) and the Four-process Delivery Architecture for assessment delivery systems.
Off-task behavior in the cognitive tutor classroom
449 Citations2004Ryan S. Baker, Albert T. Corbett +2 more
Analysis of students who choose to game the system suggests that learned helplessness or performance orientation might be better accounts for why students choose this behavior than lack of interest in the material.
Performance Factors Analysis --A New Alternative to Knowledge Tracing
449 Citations2009Philip I. Pavlik, Hao Cen +1 more
Finding Motifs in Time Series
447 Citations2002Jessica Lin
An efficient motif discovery algorithm for time series would be useful as a tool for summarizing and visualizing massive time series databases and could be used as a subroutine in various other data mining tasks, including the discovery of association rules, clustering and classification.
International Journal of Artificial Intelligence in EducationToward Meta-cognitive Tutoring: A Model of Help Seeking with a Cognitive Tutor
395 Citations2006Vincent Aleven, Bruce M. McLaren +2 more
Predicting Students Drop Out: A Case Study
354 Citations2009GW Gerben Dekker, Mykola Pechenizkiy +1 more
The experimental results show that rather simple and intuitive classifiers (decision trees) give a useful result with accuracies between 75 and 80%, and the usefulness of cost-sensitive learning and thorough analysis of misclassifications is demonstrated.
Social learning analytics
353 Citations2012Simon Buckingham Shum, Rebecca Ferguson
It is proposed that the design and implementation of effective Social Learning Analytics (SLA) present significant challenges and opportunities for both research and enterprise, in three important respects.
Journal of Policy Analysis and ManagementThe Fifth Generation: Artificial Intelligence and Japan's Computer Challenge to the World
345 Citations1983M. Granger Morgan, Edward A. Feigenbaum +1 more
Lecture notes in computer scienceDetecting Student Misuse of Intelligent Tutoring Systems
343 Citations2004Ryan S. Baker, Albert T. Corbett +1 more
A machine-learned Latent Response Model is presented that can identify if a student is gaming the system in a way that leads to poor learning and will be useful both for re-designing tutors to respond appropriately to gaming, and for understanding the phenomenon of gaming better.
The American StatisticianData Mining: Statistics and More?
342 Citations1998David J. Hand
Data mining is a new discipline lying at the interface of statistics, database technology, pattern recognition, machine learning, and other areas concerned with the secondary analysis of large databases in order to find previously unsuspected relationships which are of interest or value to the database owners.
Psychological ScienceMaintenance of Foreign Language Vocabulary and the Spacing Effect
338 Citations1993Harry P. Bahrick, Lorraine E. Bahrick +2 more
Predicting student performance: an application of data mining methods with an educational web-based system
333 Citations2004Behrouz Minaei‐Bidgoli, Deborah A. Kashy +2 more
An approach to classifying students in order to predict their final grade based on features extracted from logged data in an education Web-based system is presented and an appropriate weighting of the features used via a genetic algorithm is demonstrated to improve prediction accuracy.
User Modeling and User-Adapted InteractionAutomatic detection of learner’s affect from conversational cues
319 Citations2007Sidney K. D’Mello, Scotty D. Craig +3 more
The reliability of detecting a learner’s affect from conversational features extracted from interactions with AutoTutor, an intelligent tutoring system (ITS) that helps students learn by holding a conversation in natural language, is explored.
IEEE Transactions on Knowledge and Data EngineeringClustering and Sequential Pattern Mining of Online Collaborative Learning Data
291 Citations2009Dinuka Perera, Judy Kay +3 more
The goal is to enable the groups and their facilitators to see relevant aspects of the group's operation and provide feedback if these are more likely to be associated with positive or negative outcomes and indicate where the problems are.
Interactive Learning EnvironmentsA Large‐Scale Evaluation of an Intelligent Discovery World: Smithtown
277 Citations1990Valerie J. Shute, Robert Glaser
An evaluation of Smithtown in two studies of individual differences in learning shows that Smithtown fared very well when compared to traditional instruction on economics and delineated the performance indicators which separated better from worse learners in this discovery environment.
Cognition and InstructionPoint and Click or Grab and Heft: Comparing the Influence of Physical and Virtual Instructional Materials on Elementary School Students' Ability to Design Experiments
271 Citations2003Lara M. Triona, David Klahr
The widespread availability of computers in elementary schools makes them an appealing option for presenting instructional materials in laboratory science, but there are neither theoretical nor empirical grounds for predicting whether virtual or physical presentation of instructional materials will be more effective.
Lecture notes in computer scienceAdapting to When Students Game an Intelligent Tutoring System
243 Citations2006Ryan S. Baker, Albert T. Corbett +8 more
A system which gives a gaming student supplementary exercises focused on exactly the material the student bypassed by gaming, and which also expresses negative emotion to gaming students through an animated agent is introduced.
Educational Technology & SocietyA Study of the Relationship between Student Social Networks and Sense of Community.
231 Citations2008Shane Dawson
Qualitative analyses indicate that an individual's pre-existing external social network influences the type of support and information exchanges an individual requires and therefore, the degree of sense of community ultimately experienced.
The Information SocietyExploring Multiplexity: Social Network Structures in a Computer-Supported Distance Learning Class
230 Citations2001Caroline Haythornthwaite
A case study is presented of the social networks of interactions and media use among members of a class of computer-supported distance learners, suggesting the need to structure exchanges to balance class-wide sharing of ideas with subgroup interactions that facilitate project completion, and to provide media that support these two modes of interaction.
Modeling and understanding students' off-task behavior in intelligent tutoring systems
230 Citations2007Ryan S. Baker
A machine-learned model that can automatically detect when a student using an intelligent tutoring system is off-task, i.e., engaged in behavior which does not involve the system or a learning task is presented.
Sensing and modeling human networks using the sociometer
227 Citations2004Tanzeem Choudhury, Alex Pentland
This paper shows how sensor measurements from the sociometer can be used to build computational models of group interactions, andresent results on how the structure of face-to-face interactions within groups, detect when members are in face- to-face proximity and also when they are having a conversation.
Multivariate Behavioral ResearchThe TETRAD Project: Constraint Based Aids to Causal Model Specification
214 Citations1998Richard Scheines, Peter Spirtes +3 more
This work begins by drawing the analogy between parameter estimation and model specification search, and describes how the specification of a structural equation model entails familiar constraints on the covariance matrix for all admissible values of its parameters.
Journal of the Learning SciencesUsing Learning Analytics to Understand the Learning Pathways of Novice Programmers
213 Citations2013Matthew Berland, Taylor Martin +3 more
This work explores how students progress from exploration, through tinkering, to refinement, a pathway that is term EXTIRE, and identifies a role of tinkering in novices' learning and presents a data-driven approach to creating process descriptions.
Journal of the Learning SciencesFrom Log Files to Assessment Metrics: Measuring Students' Science Inquiry Skills Using Educational Data Mining
200 Citations2013Janice D. Gobert, Michael São Pedro +2 more
Evidence is presented that this detector developed in 1 scientific domain can be used—with no modification or retraining—to effectively detect science inquiry skill in another scientific domain, density.
The Q-matrix Method: Mining Student Response Data for Knowledge
153 Citations2005Tiffany Barnes
The q-matrix method is proposed, where data from student behavior is “mined” to create concept models of the material being taught, and preliminary results imply that the method can effectively predict which concepts need further review.
Affective states and state tests
153 Citations2013Zachary A. Pardos, Ryan S. Baker +3 more
Investigating the correspondence between student affect in a web-based tutoring platform throughout the school year and learning outcomes at the end of the year, on a high-stakes mathematics exam finds that boredom during problem solving is negatively correlated with performance, as expected; however, boredom is positively correlation with performance when exhibited during scaffolded tutoring.
International Journal of Human-Computer StudiesStudent assessment using Bayesian nets
152 Citations1995J. J. Martin, Kurt VanLehn
OLAE is described as an assessment tool that collects data from students solving problems in introductory college physics, analyses that data with probabilistic methods that determine what knowledge the student is using, and flexibly presents the results of analysis.
Towards Sensor-Free Affect Detection in Cognitive Tutor Algebra.
152 Citations2012Ryan S. Baker, Sujith M. Gowda +8 more
This paper presents models which can detect student engaged concentration, confusion, frustration, and boredom solely from students' interactions within a Cognitive Tutor for Algebra, designed to operate solely on the information available through students’ semantic actions within the interface.
Educational Data Mining: a Case Study
150 Citations2005Agathe Merceron, Kalina Yacef
These findings can be used both to help teachers with managing their class, understand their students' learning and reflect on their teaching and to support learner reflection and provide proactive feedback to learners.
Inferring learning and attitudes from a Bayesian Network of log file data
140 Citations2005Ivon Arroyo, Beverly Park Woolf
This research evaluates the accuracy of a Bayesian Network to infer a student's hidden attitude toward learning, amount learned and perception of the system from log-data to develop tutors that self-improve their student models and their teaching.
SNAPP
139 Citations2011Aneesha Bakharia, Shane Dawson
The functional features included in SNAPP 2.0 are detailed and how they relate to learning activity intent and participant monitoring.
International Journal of Artificial Intelligence in EducationSupporting Collaborative Learning and E-Discussions Using Artificial Intelligence Techniques
130 Citations2010Bruce M. McLaren, Oliver Scheuer +1 more
This work contributes to the fields of computer-supported collaborative learning and artificial intelligence in education by introducing sophisticated and empirically evaluated automated analysis techniques that combine structural, textual, and temporal data.
ScholarWorks@UMassAmherst (University of Massachusetts Amherst)Repairing Disengagement With Non-Invasive Interventions
127 Citations2007Ivon Arroyo, Kimberly Ferguson +7 more
Results show that the general trend over time is for students to become more disengaged while using a tutor, yet students can be coaxed into reengagement after viewing interventions that promote self-reflection and self-monitoring -- a simple open-learner model accompanied by suggestions and encouragement.
Lecture notes in computer scienceDoes Help Help? Introducing the Bayesian Evaluation and Assessment Methodology
123 Citations2008Joseph E. Beck, Kai-Min Chang +2 more
How help can both scaffold the current problem attempt as well as teach the student knowledge that will transfer to later problems is described, suggesting that the Bayesian Evaluation and Assessment framework is the strongest of the three.
Chapman & Hall/CRC data mining and knowledge discovery seriesA Response-Time Model for Bottom-Out Hints as Worked Examples
123 Citations2010Benjamin Shih, Kenneth R. Koedinger +1 more
It is shown that this model not only predicts learning, but captures behaviors related to self-explanation from bad student use of bottom-out hints by means of logged response times.
Lecture notes in computer scienceContextual Slip and Prediction of Student Performance after Use of an Intelligent Tutor
116 Citations2010Ryan S. Baker, Albert T. Corbett +6 more
This paper compares the Contextual-Guess-and-Slip variant on Bayesian knowledge tracing to classical four-parameter Bayesian Knowledge Tracing and the Individual Difference Weights variant of Bayesianknowledge Tracing, investigating how well each model variant predicts post-test performance.
Journal of Experimental Psychology GeneralImmediate and delayed transfer of training effects in statistical reasoning.
114 Citations1991Geoffrey T. Fong, Richard E. Nisbett
Zenodo (CERN European Organization for Nuclear Research)Combining Unsupervised and Supervised Classification to Build User Models for Exploratory Learning Environments
110 Citations2009Saleema Amershi, Cristina Conati
Initial evidence is provided that the data-based user modeling framework can automatically identify meaningful student interaction behaviors and can be used to build user models for the online classification of new student behaviors online.
Lecture notes in computer scienceAn Interactive Teacher’s Dashboard for Monitoring Groups in a Multi-tabletop Learning Environment
107 Citations2012Roberto Martínez Maldonado, Judy Kay +2 more
An interactive dashboard is presented that summarises student data captured from a multi-tabletop learning environment and allows teachers to drill down to more specific information when required and consists of a set of visual real-time indicators of the groups' activity and collaboration.
User Modeling and User-Adapted InteractionSMART: Student modeling approach for responsive tutoring
106 Citations1995Valerie J. Shute
The premise is that a single, principled approach to student modeling, involving both theoretical and empirical methods, can render automated instruction more efficacious across a broad array of instructional domains.
Frontiers in artificial intelligence and applicationsThe Impact of Off-task and Gaming Behaviors on Learning: Immediate or Aggregate?
103 Citations2009Mihaela Cocea, Arnon Hershkovitz +1 more
It is shown that gaming tends to have immediate harmful impact while off-task tends to has aggregated harmful impact on learning.
Educational Data MiningPredicting College Enrollment from Student Interaction with an Intelligent Tutoring System in Middle School.
102 Citations2013Maria Ofelia Clarissa Z. San Pedro, Ryan S. Baker +2 more
This paper predicts college attendance from detectors of specific aspects of student learning and engagement in the context of 3,747 students using the ASSISTment system in New England, producing detection that is both successful and potentially more actionable than previous approaches.
Scholarworks (University of Massachusetts Amherst)Analyzing the longitudinal K-12 grading histories of entire cohorts of students: Grades, data driven decision making, dropping out and hierarchical cluster analysis
96 Citations2020Alex J. Bowers
Educational Data MiningInterestingness Measures for Associations Rules in Educational Data.
96 Citations2008Agathe Merceron, Kalina Yacef
It is argued in this paper that cosine and added value (or equivalently lift) are well suited to educational data, and that teachers can interpret their results easily.
Is Over Practice Necessary? --Improving Learning Efficiency with the Cognitive Tutor through Educational Data Mining
94 Citations2007Hao Cen, Kenneth R. Koedinger +1 more
Using the LFA findings on the Cognitive Tutor geometry curriculum, the curriculum was optimized with the goal of improving student learning efficiency, and findings support the use of this data mining technique to improve learning efficiency with other computer-tutor-based curricula.
User Modeling and User-Adapted InteractionLeveraging machine-learned detectors of systematic inquiry behavior to estimate and predict transfer of inquiry skill
93 Citations2011Michael A. Sao Pedro, Ryan S. Baker +3 more
Machine-learned models that can detect when students test their articulated hypotheses, design controlled experiments, and engage in planning behaviors using two inquiry support tools are generated, and their skill estimates were significant predictors of the two types of inquiry transfer tests.
Lecture notes in computer scienceA Bayes Net Toolkit for Student Modeling in Intelligent Tutoring Systems
92 Citations2006Kai-Min Chang, Joseph E. Beck +2 more
An effort to model a student's changing knowledge state during skill acquisition using a tool called BNT-SM, which reduces the number of lines of code required to use a DBN by a factor of 5 and supports more flexible models.
User Modeling and User-Adapted InteractionAn analysis of students’ gaming behaviors in an intelligent tutoring system: predictors and impacts
92 Citations2011Kasia Müldner, Winslow Burleson +2 more
This work developed a computational gaming detector for automatically labeling the Andes data, and applied several data mining techniques, including machine learning of Bayesian network parameters, to address the research question: What is a better predictor of gaming, problem or student?
IEEE Transactions on Learning TechnologiesAutomatic Detection of Off-Task Behaviors in Intelligent Tutoring Systems with Machine Learning Techniques
90 Citations2009Suleyman Cetintas, Luo Si +2 more
An extensive set of experiment results demonstrates the power of using multiple types of evidence, the personalized model, and the robust Ridge Regression algorithm to address data sparseness problem.
ACM SIGKDD Explorations NewsletterThe sum is greater than the parts
84 Citations2012Pardos Zachary A., Sujith M. Gowda +2 more
This work explores the potential for improving student performance prediction with ensemble methods in a data set drawn from a different tutoring system, the ASSISTments Platform, which contains 15 times the number of responses of the Genetics Tutor data set.
Zenodo (CERN European Organization for Nuclear Research)Identifying Key Features of Student Performance in Educational Video Games and Simulations through Cluster Analysis
84 Citations2012Deirdre Kerr, Gregory K. W. K. Chung
In this study, cluster analysis was able to consistently identify key features of student performance in the form of solution strategies and error patterns across levels, which contained few extraneous actions and explained a sufficient amount of the data.
Journal of Educational Computing ResearchA Cognitive Tutor for Genetics Problem Solving: Learning Gains and Student Modeling
83 Citations2010Albert T. Corbett, Linda R. Kauffman +3 more
A pretest/posttest evaluation of student learning gains for individual tutor modules across multiple colleges and universities yielded average gains equivalent to almost two letter grades, and the accuracy of student modeling in predicting students' test performance was empirically validated.
User Modeling and User-Adapted InteractionActivity sequence modelling and dynamic clustering for personalized e-learning
83 Citations2011Mirjam Köck, Alexandros Paramythis
This article presents an approach based on the modeling of learners’ problem solving activity sequences, and on the use of the models in targeted, and ultimately automated clustering, resulting in the discovery of new, semantically meaningful information about the learners.
Lecture notes in computer scienceWhen Off-Task is On-Task: The Affective Role of Off-Task Behavior in Narrative-Centered Learning Environments
82 Citations2011Jennifer Sabourin, Jonathan Rowe +2 more
Results from an empirical study of students interacting with the CRYSTAL ISLAND environment indicate that off-task behavior generally has negative impacts on learning, but analyses of students' affective transitions suggest that some students may be using off- task behavior as a strategy to regulate negative emotions.
Classifying learner engagement through integration of multiple data sources
82 Citations2006Carole R. Beal, Lei Qu +1 more
Automated Student Model Improvement
80 Citations2012Kenneth R. Koedinger, Elizabeth A. McLaughlin +1 more
This work presents a technique for automated improvement of student models that leverages the DataShop repository, crowd sourcing, and a version of the Learning Factors Analysis algorithm to discover improved models based on better test-set prediction in cross validation.
Lecture notes in computer scienceThe Big Five and Visualisations of Team Work Activity
78 Citations2006Judy Kay, Nicolas Maisonneuve +2 more
A set of novel visualisations of group activity that mirror activity of individuals and their interactions, based upon readily available authentic data are created, which provide a powerful and valuable mirroring role with potential to help groups learn to improve their effectiveness.
Frontiers in artificial intelligence and applicationsEducational Software Features that Encourage and Discourage “Gaming the System”
78 Citations2009Baker Ryan S.J.d., Adriana M. J. B. de Carvalho +4 more
A set of tutor features are discovered that explain 56% of the variance in gaming, over five times the degree of variance explained in any prior study of student individual differences and gaming.
Computers & EducationUniversity students' achievement goals and help-seeking strategies in an intelligent tutoring system
74 Citations2013Bram E. Vaessen, Frans J. Prins +1 more
Students' help-seeking behaviors in an intelligent tutoring system were analyzed and it was investigated whether the use of these strategies could be predicted by achievement goal scores.
Journal of Educational MeasurementComparing Multidimensional and Unidimensional Proficiency Classifications: Multidimensional IRT as a Diagnostic Aid
72 Citations2003Cindy M. Walker, S. Natasha Beretvas
…