Data Mining in E-learning

The development of e-learning systems, particularly web-based education systems, has increased exponentially in recent years. In the last years, researchers have begun to investigate various data mining methods to help teachers improve e-learning systems. These methods allow them to discover new knowledge based on students' usage data. Following this line, one of the most promising areas is the application of knowledge extraction. As one of the first of its kind, this book presents an introduction to e-learning systems, data mining concepts and the interaction between both areas. It consists of both openly solicited and invited chapters, written by international researchers and leading experts on the application of data mining techniques in e-learning systems. The main purpose of this book is to show the current state of this research area. It includes an introduction to e-learning systems, data mining and the interaction between areas, as well as several case studies and experiences of applying data mining techniques in e-learning systems.

Table of Contents:
Part 1: An introduction to e-learning systems, data mining and their interactions Chapter 1 - Web-based educational hypermedia Introduction; Adaptive (educational) hypermedia; The AHAM reference architecture; A general-purpose adaptive web-based platform; Questions, quizzes and tasks; Adapting to learning styles; Conclusions Chapter 2 - Web mining for self-directed e-learning Introduction; Why self-directed learning?; Web-based self-directed e-learning applications; Gaps in existing technology; Web mining; Future directions of research; Conclusion Chapter 3 - Data mining for the anlaysis of content interaction in web-based learning and training systems Introduction; Interaction and behaviour; Data and web usage mining; Session statistics; Session classification; Behavioral patterns; Time series; Conclusions Chapter 4 - On using data mining for browsing log analysis in learning environments Introduction; Data mining; Recommended systems; The research framework; Construction of browsing content structure; Personalized recommendation based on association mining; Concluding remarks Part 2: Case studies experiences of applying data mining techniques in e-learning systems Chapter 5 - Recommended systems for e-learning: towards non-intrusive web mining Introduction; Collaborative filtering: how most systems work; Desired recommender systems in an online learning environment; Non-intrusive methods for recommendation; Hybrid methods for recommendations; Conclusion Chapter 6 - Active, context-dependent, data-centered techniques for e-learning: a case study of a research paper recommender system Introduction; A research paper recommender system; Two experiments in paper recommendation; The ecological approach; Conclusion Chapter 7 - Applying web usage mining for the analysis of behaviour in web-based learning environments Introduction; The process of WUM; WUM challenges in practice: a case study; LogPrep: a customizable pre-processing tool; OR3: ontology-based rule rummaging and retrieval tool; Discussions; Conclusions and future work Chapter 8 - Association analysis for a web-based educational system Introduction; Background; Contrast rules; Algorithm; Experiments; Conclusion Chapter 9 - Data mining in personalizing distance education courses Introduction; General paradigms for ITSs; Data description; Correlations and Linear Regression Models; Association rules and probabilistic models; Evaluating the predictive power by cross-validation; Conclusions Chapter 10 - Rule mining with GBGP to improve web-based adaptive educational systems Introduction; Data mining in e-learning systems; Students' usage data; Knowledge discovery process; EPRules tool; Experimental results; Conclusions and future work Chapter 11 - Identifying gifted students and their learning paths using data mining techniques Introduction; Data mining in education; Identification of gifted students using neural network and data mining; Web mining for extracting learning path; Conclusions Chapter 12 - Data mining to support tutoring in virtual learning communities: experiences and challenges Introduction; Data mining; Defining data mining tasks for supporting tutoring; Data pre-processing; Building predictive models; Building descriptive models; Challenges and lessons learned; Concluding remarks Chapter 13 - Analysis of user navigational behaviour for e-learning personalization Introduction; E-learning environments; Navigational behaviour analysis; Experimental results; Conclusions Chapter 14 - Automatically constructing an e-textbook via web mining Introduction; System architecture; Building concept hierarchies; Topic content identification; Ranking algorithm; Conclusions Chapter 15 - Outline outlier detection of learners' irregular learning processes Introduction; Learning management system 'Samuarai'; Online outlier detection; Simulation experiments; System; Evaluation; Animated agent to enhance learning; Conclusions Chapter 16 - Use of data mining to examine an outreach call center's effectiveness and build a predictive model for classifying future marketing targets Background; Three key questions addressed; Data sources; Design and method; Findings; Discussion