You are previewing Personalized Information Retrieval and Access: Concepts, Methods, and Practices.
O'Reilly logo
Personalized Information Retrieval and Access: Concepts, Methods, and Practices

Book Description

"Global information retrieval and ""anywhere, anytime"" information access has stimulated a need to design and model the personalized information search in a flexible and agile way that can use the specific personalization techniques, algorithms, and available technology infrastructure to satisfy high-level functional requirements for personalization.

Personalized Information Retrieval and Access: Concepts, Methods and Practices surveys the main concepts, methods, and practices of personalized information retrieval and access in today's data intensive, dynamic, and distributed environment, and provides students, researchers, and practitioners with authoritative coverage of recent technological advances that are shaping the future of globally distributed information retrieval and anywhere, anytime information access"

Table of Contents

  1. Copyright
  2. Preface
    1. INFORMATION MANAGEMENT CHALLENGES
    2. TACKLING THE CHALLENGES
    3. ORGANIZATION OF THE BOOK
    4. REFERENCES
  3. Acknowledgment
  4. I. Concepts
    1. I. Learning Personalized Ontologies from Text: A Review on an Inherently Transdisciplinary Area
      1. ABSTRACT
      2. INTRODUCTION
      3. ONTOLOGIES: DEFINITIONS AND OVERVIEW
        1. The Origin
        2. The Notion of Ontologies in Computer Science
          1. Ontology Structure
          2. Lexicon for Ontology Structure
        3. Classification of Ontologies
        4. Methodologies
        5. Ontology Engineering
          1. Knowledge Base Structure
          2. Lexicon for Knowledge Base Structure
      4. ONTOLOGY LEARNING FROM TEXT
        1. Layer 1: Terms
        2. Layer 2: Synonyms
        3. Layer 3: Concepts
        4. Layer 4: Concept Hierarchies
          1. Semantic Commitment
        5. Layer 5: Relations
        6. Layer 6: Rules
      5. LEARNING ONTOLOGIES FOR PERSONALIZATION
        1. Personalization
          1. Web Data
          2. Modeling and Categorizing Web Data
          3. Analyzing Web Data
        2. The Role of Ontologies in Personalization
        3. How Personalized Ontologies Can Be Learned
          1. Formal Concept Analysis Approach
          2. Hierarchical Clustering Approach
          3. Self-Organizing Map-Based Approach
        4. Discussion
      6. FUTURE RESEARCH DIRECTIONS
        1. Contextual Information Extraction
        2. Ontology Evolution
        3. Parts-of-Speech
        4. Word Sense Disambiguation
        5. Semantic Relations and Rules
        6. Multiple Inheritance
        7. Personalized Web Services
        8. Multi-Linguistics Web Personalization
      7. REFERENCES
      8. ADDITIONAL READING
    2. II. Overview of Design Options for Neighborhood-Based Collaborative Filtering Systems
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
        1. Conceptual Definition
        2. Formal Definition
        3. Collaborative Filtering Algorithms
        4. Collaborative Filtering Stages
      4. DATA PREPARATION
        1. None
        2. Default Voting
        3. Data Blurring
        4. Dimensionality Reduction
      5. SIMILARITY CALCULATION
        1. Closeness
        2. L1-Norm
        3. Mean Square Differences
        4. Euclidian Distance
        5. Vector/Cosine Similarity
        6. Pearson Correlation
        7. Constrained Pearson Correlation
        8. Spearman Correlation
        9. Variance Weighting
        10. Clark's Distance
        11. Probabilistic Rating Pattern
        12. Other Metrics
      6. FEATURE WEIGHTING
        1. None
        2. Inverse User Frequency
        3. Entropy
      7. SIMILARITY PROCESSING
        1. None
        2. Case Amplification
        3. Significance Weighting
        4. Aspect Model
      8. NEIGHBORHOOD FORMATION/SELECTION
        1. Similarity Threshold (or Correlation Weight Threshold)
        2. Maximum Number of Neighbors
        3. Clustering-Based Selection
      9. CONTRIBUTING RATINGS NORMALIZATION
        1. None
        2. Gaussian Normalization
        3. Decoupling Normalization
        4. Belief-Distribution Normalization
      10. COMBINING RATINGS FOR PREDICTION
        1. Simple Arithmetic Mean
        2. Weighted Mean
        3. Deviation-from-Mean
        4. Z-Score
        5. Belief-Distribution Prediction
      11. CONCLUSION
      12. FUTURE RESEARCH DIRECTIONS
      13. REFERENCES
      14. ADDITIONAL READING
    3. III. Exploring Information Management Problems in the Domain of Critical Incidents
      1. ABSTRACT
      2. INTRODUCTION
      3. THE "INFORMATION PROBLEM"
        1. Information Heterogeneity
        2. Information Overload
        3. Information Dynamics
      4. SOLUTIONS TO THE INFORMATION PROBLEM
          1. Information Discovery and Retrieval
          2. Example 1
          3. Example 2
        1. Information Filtering
          1. Example
        2. Information Fusion
          1. Example 1
          2. Example 2
        3. Information Personalization
          1. Example 1
          2. Example 2
      5. INFORMATION ISSUES IN CRITICAL INCIDENT MANAGEMENT
        1. Information Problems in Critical Incidents
          1. Information Heterogeneity
          2. Information Overload
          3. Information Dynamics
        2. Examples of Solutions to Information Problems in Critical Incident Management
          1. Example 1
          2. Example 2
          3. Example 3
          4. Example 4
      6. CONCLUSION
      7. FUTURE RESEARCH DIRECTIONS
      8. REFERENCES
      9. ADDITIONAL READING
    4. IV. Mining for Web Personalization
      1. ABSTRACT
      2. INTRODUCTION
      3. MOTIVATION FOR PERSONALIZATION
      4. PERSONALIZATION PROCESS DECOMPOSED
        1. Data Acquisition
        2. Data Analysis
        3. Data Preparation and Preprocessing
          1. Pattern Discovery
          2. Pattern Analysis
        4. Personalized Output
      5. THEORY IN ACTION: TOOLS AND STANDARDS
      6. TRENDS AND CHALLENGES IN PERSONALIZATION RESEARCH
      7. CONCLUSION
      8. REFERENCES
      9. ENDNOTES
    5. V. Clustering Web Information Sources
      1. ABSTRACT
      2. INTRODUCTION
      3. INFORMATION SOURCES USED FOR CLUSTERING
        1. Web Documents
        2. Web Server Logs
        3. Web Proxy Logs
      4. INFORMATION PROCESSING TOWARDS CLUSTERING
        1. Documents Preprocessing
        2. Web Server Logs Preprocessing
        3. Users' Session Identification
        4. Web Proxy Logs Preprocessing
      5. CLUSTERING ALGORITHMS
        1. Identifying Web Documents Clusters
        2. Text-Based Clustering Approach
        3. Link-Based Clustering Approach
        4. Identifying XML Documents Clusters
        5. Identifying Web Users Clusters
        6. Similarity-Based vs. Model-Based
      6. VALIDATION AND INTERPRETATION OF CLUSTERS
        1. Clustering Validation
        2. Clustering Interpretation
      7. INTEGRATING CLUSTERING IN APPLICATIONS
      8. CONCLUSION
      9. REFERENCES
      10. ENDNOTES
  5. II. Methods and Practices
    1. VI. A Conceptual Structure for Designing Personalized Information Seeking and Retrieval Systems in Data-Intensive Domains
      1. ABSTRACT
      2. INTRODUCTION
      3. CONCEPTUAL DESIGN
        1. Problem Orientation
        2. Service Orientation
        3. Modeling Users' Personalized Information Needs
          1. Theoretical Foundation
          2. Modeling Personalized Information Needs
          3. Modeling Situation
          4. Modeling Task
        4. Modeling Service
          1. Methodologies for Information (Software) Systems Developments
        5. Service-Oriented Architecture and Web Service Standards
        6. Information Service
          1. Service Description
          2. Search for a Service
      4. CASE STUDY
        1. Information Seeking and Retrieval in the Processes of Crisis Response
        2. Concepts and Models
          1. Modeling the Disaster Situation
        3. Information Service
          1. Service Description
          2. Search for a Service
        4. A Proof-of-Concept Demo
        5. Implementation
          1. Jini Service Provider and Jini Lookup Server
          2. Client PC
          3. User Interface Design
        6. Functional Evaluation
      5. CONCLUSION
      6. REFERENCES
      7. ENDNOTES
    2. VII. Privacy Control Requirements for Context-Aware Mobile Services
      1. ABSTRACT
      2. INTRODUCTION
      3. PROBLEM DESCRIPTION AND RELATED WORK
      4. PRIVACY PRINCIPLES AND REQUIREMENTS
      5. A PRIVACY CONTROL FUNCTIONAL ARCHITECTURE
        1. System Architecture
        2. Privacy Control Functional Architecture and Components
        3. User Agent (Client/Server)
        4. Information Collector Agent (SP_Agent)
        5. Context Manager
        6. Privacy Manager
      6. EXPERIMENTAL WORK
      7. EVALUATION TESTS
      8. FUTURE TRENDS
      9. CONCLUSION
      10. ACKNOWLEDGMENT
      11. REFERENCES
    3. A. APPENDIX A: QUESTIONNAIRE
    4. VIII. User and Context-Aware Quality Filters Based on Web Metadata Retrieval
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND
        1. Brief Introduction to Fuzzy Theory
        2. Quality and Information Quality
        3. Metadata
        4. Quality Dimensions
        5. Context
      4. A USER AND CONTEXT-AWARE QUALITY FILTER BASED ON WEB METADATA RETRIEVAL
        1. Web Document Class
        2. Metadata Class
        3. Quality Dimension and Linguistic Term Classes
        4. Content Class
        5. User Class
        6. Context Class
      5. SYSTEM ARCHITECTURE AND TECHNICAL DETAILS
      6. EXPECTED RESULTS
      7. FUTURE TRENDS
      8. CONCLUSION
      9. REFERENCES
      10. ENDNOTES
    5. IX. Personalized Content-Based Image Retrieval
      1. ABSTRACT
      2. INTRODUCTION
      3. CONTENT-BASED IMAGE RETRIEVAL
        1. Similarity Measure
        2. Image Segmentation
      4. RELEVANCE FEEDBACK LEARNING
        1. Relevance Feedback Learning Strategies
      5. PROBABILISTIC REGION RELEVANCE LEARNING
        1. Region Relevance Measure
        2. Estimation of Region Relevance
        3. Usage Scenario
        4. Experimental Results
      6. CONCLUSION
      7. FUTURE RESEARCH DIRECTIONS
      8. REFERENCES
      9. ADDITIONAL READING
    6. X. Service-Oriented Architectures for Context-Aware Information Retrieval and Access
      1. ABSTRACT
      2. LITERATURE REVIEW
      3. OUR APPROACH AND PROPOSAL
      4. CONFERENCE ASSISTANT EXAMPLE
      5. MODELING THE ENVIRONMENT
      6. REMINDING SERVICE
      7. MESSAGING SERVICE
      8. THE WHOLE SYSTEM
      9. CONCLUSION
      10. FUTURE RESEARCH DIRECTIONS
      11. REFERENCES
      12. ADDITIONAL READING
    7. XI. On Personalizing Web Services Using Context
      1. ABSTRACT
      2. INTRODUCTION AND MOTIVATIONS
      3. BASIC SCENARIO
      4. SOME DEFINITIONS
      5. WEB SERVICES PERSONALIZATION: FOUNDATIONS AND OPERATION
        1. Foundations
        2. Types and Roles of Context
        3. Operation
      6. MANAGING PERSONALIZATION THROUGH POLICIES
      7. SUPPORTING PERSONALIZATION THROUGH CONVERSATIONS
      8. IMPLEMENTATION STATUS
      9. RELATED WORK
      10. CONCLUSION
      11. REFERENCES
      12. ENDNOTES
    8. 1. APPENDIX 1. XML CODE OF U-CONTEXT
    9. XII. Role-Based Multi-Agent Systems
      1. ABSTRACT
      2. INTRODUCTION
      3. REVIEW OF ROLE CONCEPTS IN AGENT SYSTEMS
      4. FUNDAMENTAL PRINCIPLES OF RMAS
        1. Object Principles
        2. Agent Principles
        3. Role Principles
        4. Group Principles
      5. THE REVISED E-CARGO MODEL FOR RMAS
        1. Object and Class
        2. Agent
        3. Message
        4. Role
        5. Environment
        6. Group
      6. ARCHITECTURE OF RMAS
        1. Architecture Design
        2. Agent Implementation
        3. System Integration
      7. AGENT EVOLUTION IN RMAS
        1. Future Roles
        2. The Current Roles and Active Roles
        3. Past Roles
        4. Role-Playing Rules
      8. CASE STUDY
      9. INFORMATION PERSONALIZATION WITH ROLES
      10. FUTURE RESEARCH DIRECTIONS AND CONCLUSION
      11. REFERENCES
      12. ADDITIONAL READING
    10. XIII. Towards a Context Definition for Multi-Agent Systems
      1. ABSTRACT
      2. INTRODUCTION
      3. BACKGROUND: CONTEXT AND AI
        1. Context and Logic
        2. Context and Knowledge Representation and Reasoning (KRR)
        3. Context and Agent
        4. Context and Personalized Information Retrieval
        5. Discussion
      4. DEFINING CONTEXT FOR MULTI-AGENT SYSTEM
        1. Generic Context Definition
        2. Specializing Context Definition for MAS
          1. Conceptualization
          2. Knowledge Representation
          3. Building and Using Context by an Agent
        3. Case Study: Agent-Based Virtual Environment of Accident Emergency Rescue
          1. Description of the Case Study
          2. Agentification
          3. Agent Knowledge Representation and Reasoning Based on Context Model
      5. FUTURE TRENDS
      6. CONCLUSION
      7. FUTURE RESEARCH DIRECTIONS
      8. REFERENCES
      9. ADDITIONAL READING
  6. Compilation of References
  7. About the Contributors