Intelligent Support for Computer Science Education : Pedagogy Enhanced by Artificial Intelligence book cover
1st Edition

Intelligent Support for Computer Science Education
Pedagogy Enhanced by Artificial Intelligence

  • Available for pre-order. Item will ship after September 23, 2021
ISBN 9781138052017
September 23, 2021 Forthcoming by CRC Press
312 Pages 29 B/W Illustrations

SAVE ~ $25.99
was $129.95
USD $103.96

Prices & shipping based on shipping country


Book Description

Intelligent Support for Computer Science Education presents the authors’ research journey into the effectiveness of human tutoring, with the goal of developing educational technology that can be used to improve introductory Computer Science education at the undergraduate level. Nowadays, Computer Science education is central to the concerns of society, as attested by the penetration of information technology in all aspects of our lives; consequently, in the last few years interest in Computer Science at all levels of schooling, especially at the college level, has been flourishing. However, introductory concepts in Computer Science such as data structures and recursion are difficult for novices to grasp.

Key Features:

  • Includes a comprehensive and succinct overview of the Computer Science education landscape at all levels of education.
  • Provides in-depth analysis of one-on-one human tutoring dialogues in introductory Computer Science at college level.
  • Describes a scalable, plug-in based Intelligent Tutoring System architecture, portable to different topics and pedagogical strategies.
  • Presents systematic, controlled evaluation of different versions of the system in ecologically valid settings (18 actual classes and their laboratory sessions).
  • Provides a time-series analysis of student behavior when interacting with the system.

This book will be of special interest to the Computer Science education community, specifically instructors of introductory courses at the college level, and Advanced Placement (AP) courses at the high school level. Additionally, all the authors’ work is relevant to the Educational Technology community, especially to those working in Intelligent Tutoring Systems, their interfaces, and Educational Data Mining, in particular as applied to human-human pedagogical interactions and to user interaction with educational software.

Table of Contents

About the Authors                                                                         




Section I    Four Scientific Pillars

Chapter   1 Introduction                                                 

1.1         AN INTERDISCIPLINARY PERSPECTIVE                         

1.2         THE STRUCTURE OF THE BOOK                                   

Chapter  2 Related Work With Stellan Ohlsson


2.1.1         Background                                                               

2.1.2         Nine Modes of Learning                                           Discussion                                                   

2.2         PRAGMATICS AND DIALOGUE PROCESSING                   


2.3.1         Elementary and Secondary Education                     

2.3.2         From high school to college                                       

2.3.3         Post-Secondary Education for CS Majors                 

2.4         INTELLIGENT TUTORING SYSTEMS (ITSS)                     

2.4.1         Natural Language Processing (NLP) for ITSs           

2.4.2         Modes of learning and ITSs                                      Positive and negative feedback                   Worked-Out  Examples                                Analogy                                                      

2.5         ITSS FOR COMPUTER SCIENCE AND NLP                     

2.5.1         ITSs for CS                                                                NLP in ITSs for CS                                    

Section II From Human Tutoring to ChiQat-Tutor

Chapter 3 Human tutoring dialogues and their analysis       

With Stellan Ohlsson, Mehrdad Alizadeh, Lin Chen, and Rachel Harsley

3.1         DATA COLLECTION                                                 

3.1.1         Learning  outcomes  in human tutoring                     

3.1.2         Measuring learning gains                                         

3.1.3         Learning effects                                                         

3.2         TRANSCRIPTION AND ANNOTATION                           

3.2.1         Annotation                                                                Validating the corpus annotation               

3.3         DISTRIBUTIONAL ANALYSIS                                     

3.3.1         Elementary Dialogue Acts                                       

3.3.2         Student Initiative                                                       

3.3.3         Episodic Strategies                                                   


3.4.1         Individual Dialog Acts (Type  1 Models)                 

3.4.2         Sequences of Dialogue Acts (Type  2 Models)            Bigram Models                                            Trigram Models                                         

3.4.3         Episodic  strategies  (Type 3 Models)                          Worked-out examples                                  Analogies                                                   

3.5         SUMMARY: INSIGHTS FROM HUMAN TUTORING ANAL YSIS                                                                     

Chapter  4 ChiQat Tutor and its architecture                      

With Omar AlZoubi and Christopher Brown

4.1         THE DOMAIN MODEL                                             

4.1.1         Problem definitions                                                  

4.1.2    Solution definitions

4.1.3    Worked-Out Examples

4.1.4    The Procedural Knowledge Model

4.2         USER INTERFACE                                                   


4.3.1         Solution evaluator                                                     

4.4         TUTOR MODULE                                                   

4.4.1         Code  feedback:  syntax and executability                 

4.4.2         Reactive  & Proactive feedback                                Reactive procedural feedback                    Proactive procedural feedback                 

4.5         TRAINING THE PKM GRAPHS                                   

Chapter  5 Evaluation in the classroom                            

With Rachel Harsley and Stellan Ohlsson

5.1         EVALUATION METRICS                                           


5.2.1         Insights on learning from student behavior and perceptions of ChiQat-Tutor-v1                                Student  behavior                                      Student  satisfaction                                 

5.2.2            Chiqat-Tutor, Version  1: Summary of findings     

5.3         LEARNING WITH WORKED OUT EXAMPLES AND ANAL OGY                                                                   

5.3.1         WOE  and Analogy Conditions                                Standard WOEs                                        Length and usage  of WOEs                      Analogical  content in WOEs                     

5.3.2    Learning Linked Lists among non-majors

5.3.3    Learning Linked Lists among majors

5.3.4    Learning and Initial Student Knowledge    Mining the logs: Predicting Knowledge

5.3.5     Chiqat-Tutor, Version  2: Summary of findings      

Section III Extending ChiQat-Tutor

Chapter 6 Beyond Linked Lists: Binary Search Trees and Recursion    

With Mehrdad Alizadeh and Omar AlZoubi


6.1.1    Pilot evaluation


6.2.1    Models for Teaching Recursion    Conceptual Models    Program Visualization

6.2.2    A Hybrid Model for Teaching Recursion ChiQat-Tutor

6.2.3    Evaluation of the recursion module    Experimental Protocol    Experiments at CMU Qatar    Experiments at UIC

6.2.4    Analysis of students’ interactions with the system 160

6.3   SUMMARY                                                            

Chapter 7 A practical guide to extending ChiQat Tutor     

7.1         AN IMPLEMENTATION ARCHITECTURE                       

7.2         CASE STUDY: THE STACK TUTOR PLUGIN                    

7.2.1         Stack Plugin Design                                                

7.2.2         Class  structure                                                        

7.2.3         Setting up the stage                                                 

7.2.4         Graphical interface                                                  

7.2.5         Stack problem logic and feedback                           

Chapter 8 Conclusions                                                 

8.1         WHERE WE ARE, AND LESSONS LEARNED                    

8.2         FUTURE WORK                                                      

8.2.1         Extending the curriculum                                       

8.2.2         Enhancing communication with the student           

8.2.3         Mining the user logs, and deep learning                  

Appendix A A primer on data structures                                                         

Appendix  B Pre /post tests                                             

Appendix C Annotation Manuals                                     

Appendix D Linked List Problem Set                             

Appendix  E Stack Plugin Full Code                                 


View More



Barbara Di Eugenio is Professor in the Department of Computer Science at the University of Illinois at Chicago (UIC), Chicago, IL, USA. There she leads the NLP laboratory ( Dr. Di Eugenio holds a Ph.D. in Computer Science from the University of Pennsylvania (1993); she joined UIC in 1999. Her interests focus on the theory and practice of Natural Language Processing, with applications to educational technology, health care, human robot interaction, and social media. Dr. Di Eugenio is an NSF CAREER awardee (2002), and a UIC University Scholar (2018-21). Her research has been supported by the National Science Foundation, the National Insti- tute of Health, the Office of Naval Research, Motorola, Yahoo!, Politecnico di Torino, and the Qatar Research Foundation. She has graduated 12 PhD students and 30 Master's students, and published more than one hundred refereed publications.

Davide Fossati is currently a Senior Lecturer in Computer Science at Emory University in Atlanta, GA, USA. Prior to joining the faculty at Emory in 2016, Dr. Fossati held positions at the Georgia Institute of Technology (2009-2010) and Carnegie Mellon University (2010-2015). He received his Ph.D. in Computer Science from the University of Illinois at Chicago in 2009. He also holds an M.Sc. degree in Computer Engineering from the Po-
litecnico di Milano, Italy (2004), and an M.Sc. in Computer Science from the University of Illinois at Chicago (2003). Dr. Fossati's primary scholarly focus is Technology Enhanced Learning, with particular interest in the development of Artificial Intelligence systems to support Computer Science education.

Nick Green is a technology professional with 20 years of research and development experience in academia and industry. Dr. Green received his Ph.D. in Computer Science from the University of Illinois at Chicago in 2017, where he focused on educational technology, natural language processing, and software engineering. Outside of academia, he has worked for companies such as Sony Interactive Entertainment and Facebook. He has a passion for the startup scene where he is also a serial entrepreneur having founded companies in fields such as security and precision agriculture.