Fundamentals of Predictive Text Mining

Cover......Page 1
front-matter......Page 2
Preface......Page 5
For Instructors......Page 6
Acknowledgements......Page 7
Contents......Page 8
What's Special About Text Mining?......Page 13
Structured or Unstructured Data?......Page 14
Is Text Different from Numbers?......Page 15
What Types of Problems Can Be Solved?......Page 17
Information Retrieval......Page 18
Clustering and Organizing Documents......Page 19
Information Extraction......Page 20
Prediction and Evaluation......Page 21
Summary......Page 22
Historical and Bibliographical Remarks......Page 23
Questions and Exercises......Page 24
Collecting Documents......Page 25
Document Standardization......Page 27
Tokenization......Page 28
Lemmatization......Page 29
Stemming to a Root......Page 31
Vector Generation for Prediction......Page 33
Multiword Features......Page 38
Labels for the Right Answers......Page 40
Sentence Boundary Determination......Page 41
Part-of-Speech Tagging......Page 43
Phrase Recognition......Page 44
Parsing......Page 45
Feature Generation......Page 47
Historical and Bibliographical Remarks......Page 48
Questions and Exercises......Page 50
Using Text for Prediction......Page 51
Recognizing that Documents Fit a Pattern......Page 53
How Many Documents Are Enough?......Page 54
Document Classification......Page 55
Learning to Predict from Text......Page 56
Similarity and Nearest-Neighbor Methods......Page 57
Document Similarity......Page 58
Decision Rules......Page 60
How to Find the Best Decision Rules......Page 64
Decision Trees......Page 66
Scoring by Probabilities......Page 67
Linear Scoring Methods......Page 70
How to Find the Best Scoring Model......Page 72
Estimating Current and Future Performance......Page 78
Applications......Page 81
Historical and Bibliographical Remarks......Page 82
Questions and Exercises......Page 84
Is Information Retrieval a Form of Text Mining?......Page 86
Key Word Search......Page 87
Nearest-Neighbor Methods......Page 88
Word Count and Bonus......Page 89
Cosine Similarity......Page 90
Web-based Document Search......Page 91
Link Analysis......Page 92
Inverted Lists......Page 96
Evaluation of Performance......Page 98
Historical and Bibliographical Remarks......Page 99
Questions and Exercises......Page 100
Finding Structure in a Document Collection......Page 102
Clustering Documents by Similarity......Page 104
Similarity of Composite Documents......Page 105
k-Means Clustering......Page 107
Centroid Classifier......Page 109
Hierarchical Clustering......Page 110
The EM Algorithm......Page 113
What Do a Cluster's Labels Mean?......Page 116
Applications......Page 118
Evaluation of Performance......Page 119
Historical and Bibliographical Remarks......Page 121
Questions and Exercises......Page 122
Goals of Information Extraction......Page 124
Finding Patterns and Entities from Text......Page 126
Entity Extraction as Sequential Tagging......Page 127
Tag Prediction as Classification......Page 128
The Maximum Entropy Method......Page 129
Linguistic Features and Encoding......Page 134
Local Sequence Prediction Models......Page 135
Global Sequence Prediction Models......Page 139
Coreference Resolution......Page 140
Relationship Extraction......Page 142
Template Filling and Database Construction......Page 143
Information Retrieval......Page 144
Commercial Extraction Systems......Page 145
Intelligence......Page 146
Summary......Page 147
Historical and Bibliographical Remarks......Page 148
Questions and Exercises......Page 149
Ideal Data for Prediction......Page 151
Hybrid and Mixed Data......Page 152
Practical Data Sourcing......Page 154
Prototypical Examples......Page 155
Web-based XML Data......Page 156
Product Reviews......Page 158
Sentiment Analysis......Page 160
Hybrid Example: Independent Sources of Numerical and Text Data......Page 161
Mixed Data in Standard Table Format......Page 162
Summary......Page 163
Questions and Exercises......Page 164
The Problem......Page 166
Solution Overview......Page 167
Methods and Procedures......Page 168
System Deployment......Page 169
The Problem......Page 170
Solution Overview......Page 171
Methods and Procedures......Page 172
System Deployment......Page 173
Solution Overview......Page 174
Methods and Procedures......Page 175
System Deployment......Page 177
Methods and Procedures......Page 178
System Deployment......Page 182
Solution Overview......Page 183
Methods and Procedures......Page 184
Solution Overview......Page 186
Methods and Procedures......Page 187
System Deployment......Page 188
Solution Overview......Page 190
Methods and Procedures......Page 191
The Problem......Page 193
Solution Overview......Page 194
Methods and Procedures......Page 195
Summary......Page 196
Questions and Exercises......Page 197
Summarization......Page 198
Active Learning......Page 201
Learning with Unlabeled Data......Page 202
Ensembles and Voting Methods......Page 203
Online Learning......Page 205
Cost-Sensitive Learning......Page 206
Distributed Text Mining......Page 207
Learning to Rank......Page 209
Question Answering......Page 210
Summary......Page 211
Historical and Bibliographical Remarks......Page 212
Questions and Exercises......Page 213
Summary of Software......Page 215
Download Instructions......Page 216
References......Page 218
Author Index......Page 225
Subject Index......Page 229