Bjoern Koester: FooCA - Web Information Retrieval with Formal Concept Analysis

ISBN 9783-935924-06-1 (3-935924-06-2)
128 Seiten. Softcover.
18,00 EUR


Schlagwörter / Keywords:

Formale Begriffsanalyse (FBA) / Formal Concept Analysis (FCA), Wissensverarbeitung / Conceptual Knowledge Processing, Verbandstheorie / Lattice Theory, Web-Suchmaschinen / Web Search Engines, Information Retrieval (IR), Data Mining, User Interfaces, Conceptual Structures (Information Theory)


Buch-Bestellungen / Book Orders:

Verlag Allgemeine Wissenschaft - HRW e.K.
Prof. Dr. Rudolf Wille
Tannenstraße 8
D-64367 Mühltal
Tel. +49-6151-147164
Fax +49-6151-147164

Bjoern Koester:

FooCA – Web Information Retrieval with Formal Concept Analysis

Erschienen im Verlag Allgemeine Wissenschaft, Mühltal, 2006.

This book deals with Formal Concept Analysis (FCA) and its application to Web Information Retrieval. It explains how Web search results retrieved by major Web search engines such as Google or Yahoo can be conceptualized leading to a human-oriented form of representation.

The variety of factors involved to produce a search result list of a Web Information Retrieval process is qualitatively investigated. The quality of current Web search results and their makeup are highlighted in order to develop an understanding of why certain results appear.

A generalization of Web search results is conducted, leading to an FCA-based introduction of FooCA. FooCA is an application in the field of Conceptual Knowledge Processing and supports the idea of a holistic representation of Web Information Retrieval. FooCA operates on Web search results, using the itemset consisting of the title, a short description, and the URL to build a formal context and an appropriate concept lattice. In order to generate a well-arranged concept lattice, using line diagrams to retrieve and analyze the data, it is shown step by step how the prior context can be iteratively explored and enhanced. Besides serving as a tool for holistic data exploration, FooCA also enables the regular user to learn step by step how to run new, optimized search queries for his personal information needs on the Web.

In a nutshell, this book gives an introduction into the basics of Formal Concept Analysis and Web Information Retrieval, combining theory with an innovative application.


1 Introduction
1.1 Knowledge Engineering
1.2 Conceptual Knowledge Processing
1.3 Web Mining
1.4 Overview

2 Foundations
2.1 Ordered Sets and Lattices
2.1.1 Ordered Sets
2.1.2 Lattices as Ordered Sets
2.2 Formal Concept Analysis
2.2.1 Formal Context
2.2.2 Formal Concept
2.2.3 Gaining Sets of Concepts from Contexts
2.2.4 Conceptual Hierarchy
2.2.5 Concept Lattice
2.2.6 Line diagram of a Concept Lattice
2.2.7 Dealing with Complexity
2.3 Summary

3 Web Search
3.1 Web Objects
3.2 Web Search
3.2.1 Search Query
3.2.2 Search Result List
3.2.3 Formalization of Web Search Results
3.3 Web Information Retrieval
3.3.1 Web Information Retrieval System
3.3.2 Relevance
3.3.3 Feature Engineering
3.4 Web Search Engines
3.4.1 Major Web Search Engines
3.4.2 Catalog vs. Crawler
3.4.3 Generations
3.5 Summary

4 Quality of Search Results
4.1 Snippets
4.1.1 Concordances and Keywords in Context
4.1.2 Types of Snippets
4.2 Ranking
4.2.1 Relevance
4.2.2 Precision vs. Recall
4.2.3 HITS
4.2.4 PageRank
4.2.5 Other Ranking Criteria
4.3 Search Engine Overlap & Size of the Web
4.4 Commercial Interests
4.5 Summary

5 FooCA: A Conceptual Search Engine
5.1 Background
5.2 Clustering and FCA
5.3 Retrieval via a Standard Web Search Engine
5.4 From Ranked Lists to Conceptual Structures
5.5 Architecture
5.6 Feature Extraction
5.7 Frome a Search Engine Retrieval to a Context
5.8 Representing the Context in a Cross Table
5.9 Search Preferences and Strategies
5.9.1 Choice of Search Engine
5.9.2 Interval of the Search Result Retrieval
5.9.3 Language Restriction
5.9.4 Removal of Stop Words
5.9.5 Stemming
5.9.6 Clarification of the Context
5.9.7 User-based Query Refinement
5.9.8 Limiting by an Object Count for Attributes
5.9.9 Minimum Attribute Length
5.9.10 Attribute Ranking
5.9.11 Exporting the Context
5.10 Web-based Visualization of the Concept Lattice
5.11 Summary

6 Examples and Evaluation
6.1 Use-Case Scenario
6.1.1 Stepwise Context Size Reduction via a Cross Table
6.1.2 Stepwise Context Refinement via a Cross Table
6.1.3 Visualization of the Concept Lattice using a Line Diagram
6.2 Examples of FooCA generated Concept Lattices
6.3 Complexity
6.4 Usability
6.5 Summary

7 Conclusions
7.1 Discussion
7.2 Related Work
7.3 Future Work
7.4 Outlook




Dipl.-Inform. Bjoern Koester > FooCA - Web Information Retrieval with Formal Concept Analysis