Course description:
An intelligent tutoring system (ITS) provides individualized computer-based instruction to students. These systems emerged from application of artificial intelligence techniques to the computer aided instruction (CAI) systems. The difference is that an ITS usually compares the student's work with expert solutions or strategies, models the student's probably knowledge of a domain, and provides coaching or advice, taking into account what the student's knowledge state, preferred learning style, etc.

In this course, students will test drive several successfully deployed ITSs, learn ideas from artificial intelligence and cognitive psychology that are needed to build these systems, review and discuss fundamental papers in the field, construct small prototypes using two state of the art authoring tools, and analyze, design and develop a prototype ITS for a practical tutoring problem.

Goals and requirements:

• To read and intelligently discuss important papers introducing the cognitive (modeling how people learn), computational (AI and user interface technology) and educational (why are these systems effective for actual students) background and research issues of intelligent tutoring systems. ignificant class time will be devoted to seminar discussions. Students will read papers, submit comments to Blackboard the night before class, and be prepared to discuss them in seminars (20%).
• To appreciate the difference between Computer Aided Instruction (CAI) systems and ITS systems and their pros and cons. Students will write a paper comparing a CAI system and an ITS (5%).
• To experience available ITSs and discuss the pros and cons of different technologies and their potential. Each student will present an ITS in class, commenting on strengths and weaknesses (5%).
• To learn how to perform a "think-aloud" study in order to develop a domain model for an ITS. Students will perform a think-aloud analysis of a domain (10%).
• To build working prototypes of tutoring systems using modern ITS authoring tools or extending existing software. Students will design a simple ITS using an example-tracing authoring tool and a constraint-based authoring tool (10% each), then student will submit an analysis and design of a more complex ITS (20%) and implement a prototype (20%).

Textbook: Beverly Woolf, Building Intelligent Tutors, manuscript available via Blackboard, and selected readings, below.

Syllabus and assignments (see selected readings and assignments below):
Aug 30, Introduction to intelligent tutoring systems; DesignFirst-ITS demo; project possibilities
Sep 6, CAI vs. ITS discussion; psychology of learning; Cognitive Algebra demo and CTAT
Sep 13, Rosh Hashana, no class
Sep 20, Domain and expert knowledge; think-aloud protocols; AnimalWatch demo
Sep 27, Constraint-based modeling; SQL-tutor demo;
Oct 4, More on student models: open learning models, emotions; Wayang Outpost demo;
Oct 11, Andes and Andes Physics demo; ASPIRE tutor due
Oct 18, Student modeling with Bayesian networks; Java problets demo;
Oct 25,Tutoring knowledge; project requirements analysis due
Nov 1, Sally Moritz's Solution Generator and Expert Evaluation; Communication knowledge--pedagogical animated agents
Nov 8, Metacognition, inquiry and collaboration; Rashi demo
Nov 15, Communication knowledge--Natural language processing; Autotutor demo; project design due
Nov 22, Thanksgiving break
Nov 29, Web-based tutors; ELM-ART demo; Learning styles in a pedagogical advisor (Shahida Parvez)
Dec 6, Evaluation and Future of tutors and student project prototype presentations
Dec 19, Final projects due (no final exam)

Selected Readings:

Readings for August 30 (three short news articles about intelligent tutoring systems):
• Katie Hafner (2004), Software Tutors Offer Help and Customized Hints, The New York Times (September 16).
• Andy Blatchford (2007), Virtual tutor adapts to student's limitations, The Gazette (April 23).
• Jim Ong and Sowmya Ramachandran, Intelligent Tutoring Systems: The What and the How, Learning Circuits (February 2000).


Readings for September 6 (e-learning vs. ITS; cognitive and example-tracing tutors):
• Woolf textbook, chapter 2, on Blackboard
• Moritz, S., Wei, F., Parvez , S., and Blank, G. D. (2005), From Objects-First to Design-First with Multimedia and Intelligent Tutoring, Proceedings of Innovation and Technology in Computer Science Education (ITiCSE) 2005, Lisbon, Portugal (June).
• Anderson, J. R., Corbett, A. Koedinger, K. and Pelletier, R. (1996), Cognitive Tutors: Lessons Learned, Journal of  the Learning Sciences, 4 (2).
• Koedinger, K., Aleven, V., Heffernan, N., McLaren, B. and Hockenberry, M. (2004). Opening the Door to Non-Programmers: Authoring Intelligent Tutor Behavior by Demonstration. Proceedings of 7th Annual Intelligent Tutoring Systems Conference, Maceio, Brazil, pp.162-173.
  
  Readings for September 20 (model-tracing tutors and talk-aloud protocols):
• Woolf textbook, chapter 3, sections 3.2, 3.3.1, 3.4.1, 3.5.1.1 and 3.5.1.2, on Blackboard
• Corbett, A., Koedinger, K., and Anderson, J. (1997). Intelligent Tutoring Systems. In Helander , M., Landauer, T., and Prabhu, P. (Ed.), Handbook of Human-Computer Interaction, Amsterdam, The Netherlands: Elsevier Science B. V., pp. 849-874.
• Ericsson, K. A. and Simon, H. A., Verbal Reports as Data, Psychological Review, 27(3), May 1950. Here is a short summary of task and think aloud analysis.
  
  Readings for September 27 (constraint-based tutors):
• Woolf textbook, chapter 3, section 3.5.1.2
• Mitrovic, A. (2003), An Intelligent SQL Tutor on the Web, International Journal of Artificial Intelligence in Education, 13, 171-195.
• Kodaganallur, V., R.Weitz, and D. Rosenthal, A Comparison of Model-Tracing and Constraint-Based Intelligent Tutoring Paradigms, IJAIED, Vol. 15, No. 2 (2005), pp. 117-144.
• Mitrovic, A. and S. Ohlsson, A Critique of Kodaganallur, Weitz and Rosenthal, “Comparison of Model-Tracing and Constraint-Based Intelligent Tutoring Paradigms,” IJAIED, Vol. 16, No. 3 (2006), pp. 277-289.
• Kodaganallur, V., R.Weitz, and D. Rosenthal, An Assessment of Constraint-Based Tutors: A Response to Mitrovic and Ohlsson's Critique of "A Comparison of Model-Tracing and Constraint-Based Intelligent Tutoring Paradigms" IJAIED (2006), 16, 291-321.
• Mitrovic, A., P. Suraweera, B. Martin, K. Zakharov, N. Milik, and J. Holland, Authoring Constraint-based Tutors in ASPIRE, Proceedings of the 8th International Conference on Intelligent Tutoring Systems, Taiwan (June).
  
  Readings for October 4 (more on Student Models)
• Woolf textbook, rest of chapter 3, except section 3.4.4
• Wei, F. (2007), A Student Model For An Intelligent Tutoring System Helping Novices Learn Object Oriented Design, Ph.D. dissertation, Lehigh University. Read sections 3.1 and 3.2.
• Mabbott, A. and Bull, S. (2006). Student Preferences for Editing, Persuading and Negotiating the Open Learner Model , in M. Ikeda, K. Ashley & T-W. Chan (eds), Intelligent Tutoring Systems: 8th International Conference, Springer-Verlag, Berlin Heidelberg, 481-490.
• Arroyo, I. and Woolf, B. (2005). Inferring learning and attitudes from a Bayesian Network of log file data, Proceedings of the 12th International Conference on Artificial Intelligence in Education. Amsterdam.
  
  Readings for October 11 (Bayesian networks for student models):
• Woolf textbook, section 3.4.4 (Andes)
• Conati, C., Gertner, A., and VanLehn, K. Using Bayesian networks to manage uncertainty in student modeling, User Modeling and User-Adapted Interaction, Vol. 12, No. 4 (2002), 371-417.
• Wei, F. (2007), A Student Model For An Intelligent Tutoring System Helping Novices Learn Object Oriented Design, Ph.D. dissertation, Lehigh University. Read section 3.3 and chapter 4.
  
  Readings for October 18 (tutoring knowledge):
• Woolf textbook, chapter 4, on Blackboard
• VanLehn, K. (2006), The Behavior of Tutoring Systems, International Journal of Artificial Intelligence in Education, Vol. 16.
• Kumar, A.N., Explanation of step-by-step execution as feedback for problems on program analysis,and its generation in model-based problem-solving tutors, Technology, Instruction, Cognition and Learning (TICL) Journal, Special Issue on Problem Solving Support in Intelligent Tutoring Systems (to appear).
  
  Readings for October 25 (Communication knowledge--Animated Pedagogical Agents):
• Woolf textbook, chapter 5.1-5.3, on Blackboard
• Johnson, W., Rickel, J., and Lester, J. (2000). Animated pedagogical agents: face-to-face interaction in interactive learning environments. International Journal of Artificial Intelligence in Education, 11, 47-78.
• Lester, J., S. Converse, S. Kahler, T. Barlow, B. Stone, and R. Bhoga, The Persona Effect: Affective Impact of Animated Pedagogical Agents, Proceedings of CHI '97, pp. 359-366, Atlanta, March 1997.
• Rosenberg, R. B., Plant, E. A., Baylor, A. L., amd Doerr, C. E. (2007), Changing Attitudes and Performance with Computer-generated Social Models, Artificial Intelligence in Education, Ed. R. Luckin, K. Koedinger and J. Greer, IOS Press, 2007.
  
  Readings for November 1 (Sally Moritz's Solution Generator and continue Animated Pedagogical Agents):
• Moritz, S., Design-First ITS Instructor Tool. See http://moritz.cse.lehigh.edu/its/instr1.php for tool
  
  Readings for November 8 (Metacognition and inquiry):
• Woolf textbook, chapter 8 (pages 286-342 in manuscript on Blackboard)
  
  Readings for November 15 (Communication knowledge--natural language processing; Evaluation of tutoring systems):
• Woolf textbook, chapter 5.4, 6, on Blackboard
• Graesser, A., et al., AutoTutor: A tutor with dialogue in natural language, Behavior Research Methods, Instruments, & Computers, 2004.


Readings for November 29 (Web-based tutoring systems):
• Brusilovsky, P. and Weber, G. Collaborative Example Selection in an Intelligent Example-Based Programming Environment, International Conference on the Learning Sciences, 1996.
• Brusilovsky, P. and Vassileva, J., Course sequencing techniques for large-scale web-based education, Int. J. Cont. Engineering Education and Lifelong Learning, Vol. 13, Nos. 1/2, 2003.
  

Readings for December 6 (Learning styles and Evaluation of tutoring systems):


• Parvez, S. and Blank, G. (2007), Individualizing tutoring with learning style based feedback.
• Woolf textbook, chapter 9, on Blackboard
• VanLehn, K., Lynch, C., Schulze, K. Shapiro, J., Shelby, R., Taylor, L., Treacy, D., Weinstein, A., & Wintersgill, M., The Andes physics tutoring system: Five years of evaluations, Proceedings of the 12th International Conference on Artificial Intelligence in Education. Amsterdam: IOS Press, 2005.
  

Intelligent tutoring systems on the web:
· AnimalWatch (screen shots and downloadable zip file) teaches math concepts by investigating animals
· SQL-Tutor Constraint-based tutoring system for learning database Structured Query Language (login as glenn blank)
· Wayang Outpost (screen shots and Flash-based web site) helps students prepare for math SATs
· Andes physics tutor provides step-by-step feedback and hints on physics homework problems
· StatTutor facilitates understanding of statistical ideas and analysis (CMU)
· Java Programming Problets exercise understanding of Java concepts
· ELM-ART (Episodic Learner Model Lisp Tutor)
· Rashi inquiry-based tutors for supporting or refuting hypotheses (watch the intro Flash movie first)
· Professor Blank has AnimalWatch and Autotutor on CDROM

Conventional e-learning (CAI) on the web:
· E-learning and customer loyalty article claims: "Customer education can be a vital tool for both acquiring and retaining customers."
· Mrs. Glosser’s Math goodies
· Interactive patient (medicine) lessons
· Learn2.com's demo, introducing Java
· w3schools courses (including HTML, Javascript, XML, SQL, etc.)
· Webmonkey e-learning lessons (including JavaScript, HTML, etc.)
· Quia teaches facts about state capitols drill and practice by matching.
· Mathdork for Algebra I teaches concepts with animation in these lessons. teaches procedures on various technical tools and concepts.
· Lesson on computer networks, from The Universal Computer with Flash animation, text, sound, and interactivity (login as gdb0 0bdg)

Homework assignments:
#1, due Thursday, 9/6, 10am: Write 1-2 page paper comparing an Intelligent Tutoring System and a Computer Aided Instructional (or e-learning) system (select one from the above lists). Compare and contrast interesting pedagogical features, pros and cons. Upload your paper to Blackboard (assignments, #1, attach file).

#2, due Wednesday, 9/19, 1pm : Using CTAT, create an example-tracing tutor that provides pedagogical feedback to students learning how to subtract fractions. To make it interesting, the problem should deal with carrying across multiple columns. Upload your behavior recorded file (a file with extension “. brd ” inside of the “Problem Organizer” folder) to to Blackboard (assignments, #2, attach file).

#3, due Thursday, 9/27, 10am: Think Aloud Protocol Analysis for Tic-Tac-Toe (TTT). See Blackboard for details after September 20.

#4, due Thursday, 10/11, 10am: Using the ASPIRE authoring tool, create a constraint-based tool for subtracting two fractions. See Blackboard for details after September 27.