This book represents a serious effort by the editor and a team of 60 reviewers, who peer-reviewed more than 30 chapters in order to obtain the final 16 that comprise this meaningful text. The chapters are aggregated into four parts.

Part 1 includes three chapters and provides an introduction to the field of educational data mining. These first three chapters build a profile for the field and concentrate on the essence of educational data mining, the preprocessing of raw data for the purposes of data mining, and governmental public policy issues that enhance education using educational data mining.

The five chapters in Part 2 explore student modeling. Knowledge discovery software is explored in chapter 4 to enable educational institutions to predict a student’s performance based on a student’s background. Chapter 5 uses learning games to understand the personality and behaviors of students. Syntactic feature vectors are extracted from the data, providing insights based on computational linguistics. In chapter 6, the authors use a multidata fusion approach to estimate student performance in order to guide the learning process by adapting educational materials and strategies.

Understanding that some students require the aid of tutors, chapter 7 utilizes predictive modeling methods to identify which students would benefit from tutorial assistance. Chapter 8 tracks the eye movements and mouse clicking counts of a student in order to model learning achievement. The authors of this chapter claim to have identified the most important metrics involved.

Part 3, which includes four chapters, concentrates on assessment methodologies. Chapter 9 addresses the real concern that students have when approaching a thesis topic or a capstone survey paper. While the instructors or the program typically provide a guide to help students embark on their various drafts, the fact is that many students feel they need constant guidance throughout the process, but find that the curriculum is not designed for such an approach. The researchers utilize latent semantic analysis to mine the domain-specific knowledge contained within the course guides and samples of successful papers from previous students. This enhances online support, which can further improve students’ writings.

In chapter 10, the authors provide a method to automatically generate tests based on concept maps, which also measures the difficulty of an individual test question. Visualization creates an exploratory environment for teachers to understand the experiences students have while learning. In chapter 11, an algorithm is presented to identify specific student activities for visualized learning. The authors of chapter 12 examine the idea that entropy from information theory enables the detection of dependencies of different questions in a given test. This information is very useful both for understanding the student experience as well as designing a more balanced exam in the first place.

Part 4 is comprised of four chapters and gives a nice overview of the trends in educational pedagogy and learning technologies. Chapter 13 reports on ReaderBench, an environment that assesses reading skills and materials to enhance the reader’s self-development. Students across the country provide comments about their teachers via both formal and informal mechanisms. Similarly, chapter 14 combs through comments to analyze how students view the learning process and rate their teachers. This could provide critical information to teachers and administrators alike. Social networking can assist teachers in understanding the collaborative efforts of students. The researchers of chapters 15 and 16 capitalize on this trend to enhance a teacher’s understanding of the learning process in a modern setting.

This book delivers on its promise to bring together the essence of educational data mining, both in terms of principle and practice. It deserves a place on the reading shelf of any researcher interested in advancing educational goals using advanced techniques and methodologies.