Educational Data Mining: Applications and Trends

✍ Scribed by Nabila Bousbia, Idriss Belamri (auth.), Alejandro Peña-Ayala (eds.)

• Publisher: Springer International Publishing
• Year: 2014
• Tongue: English
• Leaves: 477
• Series: Studies in Computational Intelligence 524
• Edition: 1
• Category: Library

✦ Synopsis

This book is devoted to the Educational Data Mining arena. It highlights works that show relevant proposals, developments, and achievements that shape trends and inspire future research. After a rigorous revision process sixteen manuscripts were accepted and organized into four parts as follows:

· Profile: The first part embraces three chapters oriented to: 1) describe the nature of educational data mining (EDM); 2) describe how to pre-process raw data to facilitate data mining (DM); 3) explain how EDM supports government policies to enhance education.

· Student modeling: The second part contains five chapters concerned with: 4) explore the factors having an impact on the student's academic success; 5) detect student's personality and behaviors in an educational game; 6) predict students performance to adjust content and strategies; 7) identify students who will most benefit from tutor support; 8) hypothesize the student answer correctness based on eye metrics and mouse click.

· Assessment: The third part has four chapters related to: 9) analyze the coherence of student research proposals; 10) automatically generate tests based on competences; 11) recognize students activities and visualize these activities for being presented to teachers; 12) find the most dependent test items in students response data.

· Trends: The fourth part encompasses four chapters about how to: 13) mine text for assessing students productions and supporting teachers; 14) scan student comments by statistical and text mining techniques; 15) sketch a social network analysis (SNA) to discover student behavior profiles and depict models about their collaboration; 16) evaluate the structure of interactions between the students in social networks.

This volume will be a source of interest to researchers, practitioners, professors, and postgraduate students aimed at updating their knowledge and find targets for future work in the field of educational data mining.

✦ Table of Contents

Front Matter....Pages i-xviii
Front Matter....Pages 1-1
Which Contribution Does EDM Provide to Computer-Based Learning Environments?....Pages 3-28
A Survey on Pre-Processing Educational Data....Pages 29-64
How Educational Data Mining Empowers State Policies to Reform Education: The Mexican Case Study....Pages 65-101
Front Matter....Pages 103-103
Modeling Student Performance in Higher Education Using Data Mining....Pages 105-124
Using Data Mining Techniques to Detect the Personality of Players in an Educational Game....Pages 125-150
Students’ Performance Prediction Using Multi-Channel Decision Fusion....Pages 151-174
Predicting Student Performance from Combined Data Sources....Pages 175-202
Predicting Learner Answers Correctness Through Eye Movements with Random Forest....Pages 203-226
Front Matter....Pages 227-227
Mining Domain Knowledge for Coherence Assessment of Students Proposal Drafts....Pages 229-255
Adaptive Testing in Programming Courses Based on Educational Data Mining Techniques....Pages 257-287
Plan Recognition and Visualization in Exploratory Learning Environments....Pages 289-327
Finding Dependency of Test Items from Students’ Response Data....Pages 329-342
Front Matter....Pages 343-343
Mining Texts, Learner Productions and Strategies with ReaderBench ....Pages 345-377
Maximizing the Value of Student Ratings Through Data Mining....Pages 379-410
Data Mining and Social Network Analysis in the Educational Field: An Application for Non-Expert Users....Pages 411-439
Collaborative Learning of Students in Online Discussion Forums: A Social Network Analysis Perspective....Pages 441-466
Back Matter....Pages 467-468

✦ Subjects

Computational Intelligence; Artificial Intelligence (incl. Robotics)