Incremental document clustering for web page classification.

by Wong, Wai-Chiu.Thesis (M.Phil.)--Chinese University of Hong Kong, 2000.Includes bibliographical references (leaves 89-94).Abstracts in English and Chinese.Abstract --- p.iiAcknowledgments --- p.ivChapter 1 --- Introduction --- p.1Chapter 1.1 --- Document Clustering --- p.2Chapter 1.2 --- DC-tree --- p.4Chapter 1.3 --- Feature Extraction --- p.5Chapter 1.4 --- Outline of the Thesis --- p.5Chapter 2 --- Related Work --- p.8Chapter 2.1 --- Clustering Algorithms --- p.8Chapter 2.1.1 --- Partitional Clustering Algorithms --- p.8Chapter 2.1.2 --- Hierarchical Clustering Algorithms --- p.10Chapter 2.2 --- Document Classification by Examples --- p.11Chapter 2.2.1 --- k-NN algorithm - Expert Network (ExpNet) --- p.11Chapter 2.2.2 --- Learning Linear Text Classifier --- p.12Chapter 2.2.3 --- Generalized Instance Set (GIS) algorithm --- p.12Chapter 2.3 --- Document Clustering --- p.13Chapter 2.3.1 --- B+-tree-based Document Clustering --- p.13Chapter 2.3.2 --- Suffix Tree Clustering --- p.14Chapter 2.3.3 --- Association Rule Hypergraph Partitioning Algorithm --- p.15Chapter 2.3.4 --- Principal Component Divisive Partitioning --- p.17Chapter 2.4 --- Projections for Efficient Document Clustering --- p.18Chapter 3 --- Background --- p.21Chapter 3.1 --- Document Preprocessing --- p.21Chapter 3.1.1 --- Elimination of Stopwords --- p.22Chapter 3.1.2 --- Stemming Technique --- p.22Chapter 3.2 --- Problem Modeling --- p.23Chapter 3.2.1 --- Basic Concepts --- p.23Chapter 3.2.2 --- Vector Model --- p.24Chapter 3.3 --- Feature Selection Scheme --- p.25Chapter 3.4 --- Similarity Model --- p.27Chapter 3.5 --- Evaluation Techniques --- p.29Chapter 4 --- Feature Extraction and Weighting --- p.31Chapter 4.1 --- Statistical Analysis of the Words in the Web Domain --- p.31Chapter 4.2 --- Zipf's Law --- p.33Chapter 4.3 --- Traditional Methods --- p.36Chapter 4.4 --- The Proposed Method --- p.38Chapter 4.5 --- Experimental Results --- p.40Chapter 4.5.1 --- Synthetic Data Generation --- p.40Chapter 4.5.2 --- Real Data Source --- p.41Chapter 4.5.3 --- Coverage --- p.41Chapter 4.5.4 --- Clustering Quality --- p.43Chapter 4.5.5 --- Binary Weight vs Numerical Weight --- p.45Chapter 5 --- Web Document Clustering Using DC-tree --- p.48Chapter 5.1 --- Document Representation --- p.48Chapter 5.2 --- Document Cluster (DC) --- p.49Chapter 5.3 --- DC-tree --- p.52Chapter 5.3.1 --- Tree Definition --- p.52Chapter 5.3.2 --- Insertion --- p.54Chapter 5.3.3 --- Node Splitting --- p.55Chapter 5.3.4 --- Deletion and Node Merging --- p.56Chapter 5.4 --- The Overall Strategy --- p.57Chapter 5.4.1 --- Preprocessing --- p.57Chapter 5.4.2 --- Building DC-tree --- p.59Chapter 5.4.3 --- Identifying the Interesting Clusters --- p.60Chapter 5.5 --- Experimental Results --- p.61Chapter 5.5.1 --- Alternative Similarity Measurement : Synthetic Data --- p.61Chapter 5.5.2 --- DC-tree Characteristics : Synthetic Data --- p.63Chapter 5.5.3 --- Compare DC-tree and B+-tree: Synthetic Data --- p.64Chapter 5.5.4 --- Compare DC-tree and B+-tree: Real Data --- p.66Chapter 5.5.5 --- Varying the Number of Features : Synthetic Data --- p.67Chapter 5.5.6 --- Non-Correlated Topic Web Page Collection: Real Data --- p.69Chapter 5.5.7 --- Correlated Topic Web Page Collection: Real Data --- p.71Chapter 5.5.8 --- Incremental updates on Real Data Set --- p.72Chapter 5.5.9 --- Comparison with the other clustering algorithms --- p.73Chapter 6 --- Conclusion --- p.75Appendix --- p.77Chapter A --- Stopword List --- p.77Chapter B --- Porter's Stemming Algorithm --- p.81Chapter C --- Insertion Algorithm --- p.83Chapter D --- Node Splitting Algorithm --- p.85Chapter E --- Features Extracted in Experiment 4.53 --- p.87Bibliography --- p.8