Building Intelligent Interactive Tutors: Student-centered strategies for revolutionizing e-learning

Front Cover......Page 1
Building Intelligent Interactive Tutors......Page 2
Copyright Page......Page 3
Contents......Page 5
Preface......Page 12
PART I: INTRODUCTION TO ARTIFICIAL INTELLIGENCE AND EDUCATION......Page 14
CHAPTER 1 Introduction......Page 16
1.1 An inflection point in education......Page 17
1.2 Issues addressed by this book......Page 19
1.2.1 Computational issues......Page 20
1.2.2 Professional issues......Page 22
1.3.1 Foundations of the field......Page 23
1.3.2 Visions of the field......Page 25
1.3.3 Effective teaching methods......Page 27
1.3.4 Computers in education......Page 29
1.4 Overview of the book......Page 31
Summary......Page 32
2.1.1 AnimalWatch taught arithmetic......Page 34
2.1.2 PAT taught algebra......Page 37
2.1.3 Cardiac Tutor trained professionals to manage cardiac arrest......Page 40
2.2 Distinguishing features......Page 41
2.3.1 Practical teaching theories......Page 47
2.3.2 Learning theories as the basis for tutor development......Page 49
2.3.3 Constructivist teaching methods......Page 50
2.4 Brief theoretical framework......Page 52
2.5 Computer science, psychology, and education......Page 55
2.6 Building intelligent tutors......Page 57
Summary......Page 58
PART II: REPRESENTATION, REASONING AND ASSESSMENT......Page 60
CHAPTER 3 Student Knowledge......Page 62
3.2 Basic concepts of student models......Page 63
3.2.1 Domain models......Page 64
3.2.3 Bug libraries......Page 65
3.2.4 Bandwidth......Page 66
3.2.5 Open user models......Page 67
3.3.1 Representing student knowledge......Page 68
3.3.2 Updating student knowledge......Page 71
3.3.3 Improving tutor performance......Page 72
3.4 Examples of student models......Page 73
3.4.1.1 Pump Algebra Tutor......Page 74
3.4.1.2 AnimalWatch......Page 78
3.4.2 Modeling procedure: The Cardiac Tutor......Page 80
3.4.3 Modeling affect: Affective Learning companions and wayang outpost......Page 82
3.4.3.1 Hardware-based emotion recognition......Page 84
3.4.3.2 Software-based emotion recognition......Page 85
3.4.4 Modeling complex problems: Andes......Page 88
3.5 Techniques to update student models......Page 92
3.5.1.1 Model-tracing tutors......Page 93
3.5.1.2 Constraint-based student model......Page 94
3.5.2.1 Formal logic......Page 99
3.5.2.2 Expert-system student models......Page 102
3.5.2.3 Planning and plan-recognition student models......Page 103
3.5.2.4 Bayesian belief networks......Page 105
3.6 Future research issues......Page 106
Summary......Page 107
4.1 Features of teaching knowledge......Page 108
4.2.1 Apprenticeship training......Page 112
4.2.1.1 SOPHIE: An example of apprenticeship training......Page 113
4.2.1.2 Sherlock: An example of an apprenticeship environment......Page 114
4.2.2 Problem solving......Page 116
4.3 Teaching Models informed by learning theory......Page 118
4.3.1 Pragmatics of human learning theories......Page 119
4.3.2.1 Basic principles of Socratic learning theory......Page 120
4.3.2.2 Building Socratic tutors......Page 122
4.3.3.2 Building cognitive learning tutors......Page 123
4.3.3.2.2 Building cognitive tutors......Page 124
4.3.3.2.4 Advantages and limitations of model-tracing tutors......Page 125
4.3.4.1 Basic principles of constructivism......Page 127
4.3.4.2 Building constructivist tutors......Page 128
4.3.5.1 Basic principles of situated learning......Page 130
4.3.5.2 Building situated tutors......Page 131
4.3.6.1 Basic principles of social interaction and zone of proximal development......Page 136
4.3.6.2 Building social interaction and ZPD tutors......Page 137
4.4 Teaching models facilitated by technology......Page 139
4.4.1 Features of animated pedagogical agents......Page 140
4.4.2 Building animated pedagogical agents......Page 142
4.4.2.2 Life quality......Page 144
4.5 Industrial and Military Training......Page 145
4.6 Encoding multiple teaching strategies......Page 146
Summary......Page 147
5.1 Communication and teaching......Page 149
5.2.1 Synthetic humans......Page 151
5.2.2 Virtual reality environments......Page 155
5.2.3 Sophisticated graphics techniques......Page 162
5.3 Social intelligence......Page 163
5.3.1 Visual recognition of emotion......Page 164
5.3.2 Metabolic indicators......Page 166
5.3.3 Speech cue recognition......Page 168
5.4 Component interfaces......Page 169
5.5.1 Classification of natural language-based intelligent tutors......Page 171
5.5.1.1 Mixed initiative dialogue......Page 172
5.5.1.2 Single-initiative dialogue......Page 174
5.5.1.3 Directed dialogue......Page 177
5.5.1.4 Finessed dialogue......Page 178
5.5.2.1 Basic principles in natural language processing......Page 180
5.5.2.2 Tools for building natural language tutors......Page 182
5.6.1 Speech understanding......Page 185
5.6.1.1 LISTEN: The Reading Tutor......Page 186
5.6.1.2 Building speech understanding systems......Page 187
5.6.2 Syntactic processing......Page 188
5.6.3 Semantic and pragmatic processing......Page 190
5.6.4 Discourse processing......Page 192
Summary......Page 194
6.1 Principles of intelligent tutor evaluation......Page 196
6.1.2 Identify goals of the evaluation......Page 197
6.1.3.1 Build an evaluation methodology......Page 201
6.1.3.2 Consider alternative evaluation comparisons......Page 204
6.1.3.3 Outline the evaluation design......Page 206
6.1.4.1 Consider the variables......Page 209
6.1.4.3 Select control measures......Page 210
6.1.5 Present results......Page 211
6.2.1 Sherlock: A tutor for complex procedural skills......Page 213
6.2.2 Stat Lady: A statistics tutor......Page 215
6.2.3 LISP and PAT: Model tracing tutors......Page 217
6.2.4 Database tutors......Page 222
6.2.5 Andes: A physics tutor......Page 225
6.2.6 Reading Tutor: A tutor that listens......Page 228
6.2.7 AnimalWatch: An arithmetic tutor......Page 230
Summary......Page 233
PART III: TECHNOLOGIES AND ENVIRONMENTS......Page 234
7.1 Motivation for machine learning......Page 236
7.2.1 Machine learning components......Page 241
7.2.2 Supervised and unsupervised learning......Page 243
7.3.1 Expand student and domain models......Page 245
7.3.2 Identify student learning strategies......Page 247
7.3.4 Predict student performance......Page 248
7.3.5 Make teaching decisions......Page 249
7.4.1 Uncertainty in tutoring systems......Page 252
7.4.1.1 Basic probability notation......Page 254
7.4.1.2 Belief networks in tutors......Page 255
7.4.2 Bayesian belief networks......Page 257
7.4.2.1 Bayesian belief networks in intelligent tutors......Page 260
7.4.2.2 Examples of Bayesian student models......Page 261
7.4.2.2.1 Expert-centric Bayesian models......Page 262
7.4.2.2.2 Data-centric Bayesian models......Page 266
7.4.2.2.3 Efficiency-centric Bayesian models......Page 267
7.4.2.3.1 Define the structure of the Bayesian network......Page 268
7.4.2.3.2 Initialize values in a Bayesian network......Page 270
7.4.2.3.3 Update probabilities in a Bayesian network......Page 271
7.4.2.4 Advantages of Bayesian networks and comparison with model-based tutors......Page 276
7.4.3 Reinforcement learning......Page 277
7.4.3.1 Examples of reinforcement learning......Page 278
7.4.3.2 Building reinforcement learners......Page 279
7.4.3.3 Reinforcement learning in intelligent tutors......Page 280
7.4.3.4 Animal learning and reinforcement learning......Page 281
7.4.4 Hidden Markov models......Page 282
7.4.5 Decision theoretic reasoning......Page 287
7.4.6 Fuzzy logic......Page 292
7.5.1.1 Sources of uncertainty and structure of the Andes-Bayesian network......Page 294
7.5.1.2 Infer student knowledge......Page 296
7.5.1.3 Self-Explain Tutor......Page 299
7.5.2 AnimalWatch: Reinforcement learning to predict student actions......Page 302
7.5.2.1 Reinforcement learning in AnimalWatch......Page 303
7.5.2.2 Gather training data for the machine learner......Page 305
7.5.2.4 Evaluation of the reinforcement learning tutor......Page 306
7.5.2.5 Limitations of the AnimalWatch reinforcement learner......Page 309
Summary......Page 310
8.1 Motivation and research issues......Page 311
8.2 Inquiry Learning......Page 312
8.2.1 Benefits and challenges of inquiry-based learning......Page 313
8.2.2.1 Tools that structure inquiry......Page 315
8.2.2.2 Tools that monitor inquiry......Page 318
8.2.2.3 Tools that offer advice......Page 320
8.2.2.3.1 Belvedere......Page 321
8.2.2.3.2 Rashi......Page 323
8.2.3 Phases of the inquiry cycle......Page 328
8.3 Collaborative Learning......Page 329
8.3.1 Benefits and challenges of collaboration......Page 330
8.3.2 Four levels of collaboration support......Page 332
8.3.2.1 Tools that structure collaboration......Page 333
8.3.2.2 Tools that mirror collaboration......Page 334
8.3.2.3 Tools that provide metacognitive support......Page 337
8.3.2.4 Tools that coach students in collaboration......Page 343
8.3.3 Phases of Collaboration......Page 346
8.4 Summary and discussion......Page 348
9.1 Educational inflection point......Page 350
9.2 Conceptual framework for Web-based learning......Page 353
9.3 Limitation of Web-based instruction......Page 356
9.4 Variety of Web-based resources......Page 357
9.4.1 Adaptive systems......Page 358
9.4.1.1 Example of an adaptive system......Page 359
9.4.1.2 Building iMANIC......Page 360
9.4.1.3.1 Adaptive navigation: Customize travel to new pages......Page 364
9.4.1.3.2 Adaptive Presentation: Customize page content......Page 367
9.4.2 Tutors ported to the Web......Page 368
9.5 Building the Internet......Page 369
9.6 Standards for Web-based resources......Page 372
9.7 Education Space......Page 374
9.7.1 Education Space: Services description......Page 376
9.7.2 Education Space: Nuts and bolts......Page 378
9.7.2.1 Semantic Web......Page 379
9.7.2.2 Ontologies......Page 382
9.7.2.3 Agents and networking issues......Page 385
9.7.2.4 Teaching Grid......Page 386
9.8 Challenges and technical issues......Page 387
9.9 Vision of the Internet......Page 390
Summary......Page 391
10.1 Perspectives on educational futures......Page 393
10.1.1 Political and social viewpoint......Page 394
10.1.2 Psychological perspective......Page 396
10.1.3 Classroom teachers\' perspective......Page 397
10.2.1 Hardware and software development......Page 399
10.2.2 Artificial intelligence......Page 401
10.2.3 Networking, mobile, and ubiquitous computing......Page 402
10.2.4 Databases......Page 405
10.2.5 Human-computer interfaces......Page 406
10.3 Where are all the intelligent tutors?......Page 407
10.3.1 Example authoring tools......Page 408
10.3.2 Design tradeoffs......Page 411
10.3.3 Requirements for building intelligent tutor authoring tools......Page 412
10.4 Where are we going?......Page 414
References......Page 416
A......Page 464
B......Page 465
C......Page 466
D......Page 467
E......Page 468
H......Page 469
I......Page 470
K......Page 471
L......Page 472
M......Page 473
O......Page 474
P......Page 475
S......Page 476
T......Page 478
Z......Page 480