Web-Age Information Management

Name: Web-Age Information Management | 12th International Conference, WAIM 2011, Wuhan, China, September 14-16, 2011, Proceedings
Brand: Springer
Price: 96.29 EUR
Availability: OnlineOnly

12th International Conference, WAIM 2011, Wuhan, China, September 14-16, 2011, Proceedings

Haixun Wang Shijun Li Satoshi Oyama Xiaohua Hu Tieyun Qian(Editor)

Springer (Publisher)

Published on 26. August 2011

XVI, 667 pages

E-Book

PDF with digital watermarking

System requirements

978-3-642-23535-1 (ISBN)

€96.29incl. 7% vat

System requirements

for PDF with digital watermarking

E-Book Single Licence

Available for download

Description

More details

Other editions

Content

Title
Preface
Conference Organization
Table of Contents
Keynotes
Analytics for Info-plosion Including Information Diffusion Studies for the 3.11 Disaster
Using the Web for Collaborative Language Learning and Teaching
Data-Driven Modeling and Analysis of Online Social Networks
Introduction
Information Diffusion
Influence Maximization: The Law of the Few
Limiting Diffusion of Misinformation
Opinion Dynamics
Information Trend Analysis
Concluding Remarks
References
Session 1A: Query Processing
Efficient Filter Algorithms for Reverse k-Nearest Neighbor Query
Introduction
Related Works
The Filter Step for RkNN Query with Static Query Point
The Filter Step for Continuous RkNN Processing
Experimental Evaluation
Conclusion
References
Keyword Query Cleaning with Query Logs
Introduction
Related Work
Preliminaries
Adapting to User Preferences
The Original Approach
The First Enhanced Approach: Normalization and Weighting
Second Enhanced Approach: Boosting the Original Score
Experiments
Query Log Generation
Experimental Setting and Evaluation
Experiments on the First Enhanced Approach
Experiments on the Second Enhanced Approach
Comparison between Two Enhanced Approaches
Conclusion
References
A Self-adaptive Cross-Domain Query Approach on the Deep Web
Introduction and Motivation
Related Work
Cross-Domain Query
Identifying the Correlation among Different Domains
Recommending Top-k Cross-Domain Paths
Experiments
Conclusion
References
Session 1B: Uncertain Data
SPARQL Query Answering with RDFS Reasoning on Correlated Probabilistic Data
Introduction
Probabilistic Model pRDFS
Syntax
Semantics
pRDFS Query Evaluation
Query Evaluation on RDF Data
Query Evaluation on a pRDFS Theory without Reasoning
Query Evaluation on a pRDFS Theory with RDFS Reasoning
Experimental Study
Conclusion
References
Probabilistic Threshold Join over Distributed Uncertain Data
Introduction
Preliminaries
Probability Bloom Filters
Overview of PBF
Accuracy
Composition Operations of PBF
Distributed Probabilistic Threshold Bloomjoin Algorithm
Algorithm
Discussion
Evaluations
Theoretical Analysis
Experiment
Related Work
Conclusions
References
Bayesian Classifiers for Positive Unlabeled Learning
Introduction
Related Work
Bayesian Classifiers for Positive Unlabeled Learning
Problem Description
Positive Naive Bayes (PNB)
Positive Tree Augmented Naive Bayes (PTAN)
Positive Averaged One-Dependence Estimators (PAODE)
Positive Hidden Naive Bayes (PHNB)
Positive Full Bayesian Network Classifier (PFBC)
Experiment
PU Bayesian Algorithms vs. Supervised Bayesian Algorithms
Experiment on a
Experiment on p
Evaluation on Time and Space
Conclusion and Future Work
References
Session 1C: Social Media (1)
Measuring Social Tag Confidence: Is It a Good or Bad Tag?
Introduction
Related Work
Research on Social Tags
Research on the Confidence of Web Resources and Social Tags
Definition of Tag Confidence
Proposed Method
The Credibility of Users
Select Top N Semantically Similar Web Pages
Tag Similarity
Evaluating Tag Confidence
Performance Evaluation
Experimental Settings and Evaluation Measurement
NDCG Evaluation Result and Analysis
Evaluation Results of Web Clustering
Conclusion
References
A New Vector Space Model Exploiting Semantic Correlations of Social Annotations for Web Page Clustering
Introduction
Related Work
Language Models of Social Annotation
Semantics of Social Annotation
Social Annotation Applications
Vector Space Model Based on Semantic Correlation of Social Annotation
Problem Definition
Weighted Matrix of Social Annotation
Tag Similarity
Semantic Correlation between Tags and Words
Extended Vector Space Model
Experiments and Numerical Results
Data Collections
Evaluation Measure and Gold Standard
Experiment Settings
Experimental Results and Analysis
Conclusion
References
A Generalization Based Approach for Anonymizing Weighted Social Network Graphs
Introduction
Motivation
Challenges
Related Work
Problem Definition
Generalization Based Anonymization
Generating Anonymization Groups
Edge Generalization
Experiments
Runtime
Data Utilities
Conclusion
References
Session 2A: Semantics
Incremental Reasoning over Multiple Ontologies
Introduction
Problem Description
Our Proposed Approach
Managing Inferred Results Uniformly
Incremental Reasoning on an RDB-Based Inference Network
Reasoning over Multiple Named Graphs
Performance Study
Incremental Reasoning Performance
Reasoning Performance: SOR v2.0 vs. SOR
Related Work
Conclusion
References
General-Purpose Ontology Enrichment from the WWW
Introduction
Related Work
General Overview
Detailed Steps of the Proposed Framework
Natural Language Processing and Entity Recognition
Statistical Information about the Missing Background Knowledge
Semantic-Based Analysis of the Obtained Statistical Information
General-Purpose Ontology Enrichment
Experimental Results
Conclusion and Future Works
References
QuerySem: Deriving Query Semantics Based on Multiple Ontologies
Introduction
Related Work
General Overview
Theoretical Basis
From Keywords to Semantic Networks
Experimental Results
Conclusion and Future Work
References
Session 2B: Data Mining (1)
Getting Critical Categories of a Data Set
Introduction
Contributions
Problem Definition
Our Solution
A Basic Solution
An Advanced Solution
Experiments
Related Work
Conclusion
References
MFCluster: Mining Maximal Fault-Tolerant Constant Row Biclusters in Microarray Dataset
Introduction
Problem Definition
The MFCluster Algorithm
Construct the Weighted Undirected Relational Graph
Mining Maximal FT-Biclusters
Experiments
Dataset
Efficiency Comparison
Conclusions
References
Expansion Finding for Given Acronyms Using Conditional Random Fields
Introduction
Condition Random Fields
Expansion Identification Model Based on Conditional Random Fields
Expansion Identification Task
Neural Network and CRF Hybrid Model
Features
Experiments
Evaluation Corpus
Evaluation Criteria
Results
Conclusion
References
Session 2C: Social Media (2)
Leveraging Communication Information among Readers for RFID Data Cleaning
Introduction
Related Work
Preliminary
Application Scenario
Notations and Definitions
Communication Protocol
Cell Event Sequence Tree and Probabilistic Cell Events
Cell Event Sequence Tree
Probabilistic Cell Events
RFID Data Cleaning Strategy
Duplicate Data Reducing Method
Missing Data Interpolating Method
Positive Data Reducing Method
Experimental Evaluation
Experimental Setup
Evaluation Criteria
Evaluations of Duplicate Data Reducing Algorithm (D-DR)
Evaluations of Missing Data Interpolating Algorithm (Top-kPDI, M-PDI)
Evaluations of Positive Data Reducing Algorithm (P-DR)
Conclusion
References
Web Article Quality Assessment in Multi-dimensional Space
Introduction
Problem Setting and Preliminary
Modelling Dimension Evolution of Sections
Contributor's Quality Dimension Factors
Modelling Accuracy Evolution
Modelling Completeness Evolution
Modelling Consistency Evolution
RankingArticles
Extracting Corpus for Each Quality Class
Classifying an Article into Quality Class
Experiment
Effectiveness of Our Ranking Approaches
Comparisons with Previous Works
Conclusion
References
DRScribe: An Improved Topic-Based Publish-Subscribe System with Dynamic Routing
Introduction
Topic-Based Pub/Sub Systems
Motivation
Background
System Design
Subscription Installation and Management
Event Dissemination
Multicast Tree Maintenance
Additional Explanations
Experimental Evaluation
Experimental Setup
Experimental Results
Conclusions and Future Work
References
Session 3A: Cloud Data
An Efficient Quad-Tree Based Index Structure for Cloud Data Management
Introduction
Related Work
Data Management of Cloud Computing
MX-CIF Quad-Tree
QT-Chord Index
System Overview
IMX-CIF Quad-Tree Structure
The Mapping and Publishing Scheme of QT-Chord
Query Processing
Point Query Processing
Range Query Processing
KNN Query Processing
Experiment Evaluation
Performance of Point Queries
Performance of Range Queries
Performance of KNN Queries
Effect of Dimensionality
Effect of Changing d$_min$
Conclusions
References
Efficient Duplicate Detection on Cloud Using a New Signature Scheme
Introduction
Problem Definition and Preliminaries
Problem Definition
Properties of Jaccard Similarity Function
Signature Scheme
Signature Generation
Pruning Method
Duplicate Detection Processing
Experimental Evaluation
Experiment Setup
Signature Scheme Evaluation
Effect of Threshold
Effect of Node Number
Related Work
Conclusions and Future Work
References
A Secure and Efficient Role-Based Access Policy towards Cryptographic Cloud Storage
Introduction
Preliminaries
RBAC
CP-ABE
Construction
Security Assumption
System Setup
Handling Dynamic Policies
Security Analysis
Performance
Average Performance
Benefits from Propagation
Conclusion
References
Session 3B: Multimedia Data
Tagging Image by Exploring Weighted Correlation between Visual Features and Tags
Introduction
Related Works
Correlation between Visual Words and Tags
Visual Word Vocabulary
Correlation Estimation
Visual Word Weighting
Visual Word Association Graph
Visual Word Ranking and Weighting
Image Tagging
Evaluation
Dataset and Evaluation Metrics
Experiment Results
Conclusion
References
Credibility-Oriented Ranking of Multimedia News Based on a Material-Opinion Model
Introduction
Related Work
Framework of Material-Opinion Model
Credibility-Oriented Ranking of Multimedia News by Using Stakeholder Model Representing the Contents
Material Dissimilarity
Opinion Dissimilarity
Clustering by Material Dissimilarities
Clustering by Opinion Dissimilarities
Computing Credibility Score
Experiments
Experiment of Comparing Materials
Experiment of Comparing Opinions
Experiment of Ranking Multimedia News by Credibility Scores
Conclusion
References
Actions in StillWeb Images: Visualization, Detection and Retrieval
Introduction and Motivation
Related Work
Web Image Retrieval Re-ranking
Action Detection and Classification
Framework
Defining Exemplarlet
Refining Discriminative Exemplarlets
Learning Detectors via MKL
Building Visual Inverted Index
Retrieval
Experimental Setup
Dataset
Appearance Descriptors
Implementation Details
Results
Analysis of MKL
The Discrimination of Exemplarlets
The Detection Results
The Retrieval Results
Conclusions
References
Session 3C: User Models
Social Analytics for Personalization in Work Environments
Introduction
Deriving User Context Profile from Online Social Activities
Data Cleaning: Semantically Repairing Broken Tags
Information Retrieval and Integration
Semantic Enrichment
Evaluation
Personalized Tag Recommendation
Personalized Search
Conclusion
References
Finding Appropriate Experts for Collaboration
Introduction
Problem Definition
Expert Authority
Closeness
Models
Filtering Out Model (FOM)
Linear Combination Model (LCM)
Friend Recommendation Model (FRM)
Experiment Settings
Scenario and Data Set
Modeling Authority
Modeling Closeness
Evaluation Method and Metrics
Experimental Results
Filtering Out Model
Linear Combination Model
Friend Recommendation Model
Related Work
Conclusion and Future Work
References
Location Privacy Protection in the Presence of Users' Preferences
Introduction
Prior Work
HilAnchor
Framework of HilAnchor
RCA Creation
HilAnchor$^+$
Hilbert Encoding under Privacy Constraint
Algorithm HilAnchor$^+$
Empirical Evaluation
Comparing with Casper
Comparing with SpaceTwist
Conclusion
References
Session 4A: Data Management
Layered Graph Data Model for Data Management of DataSpace Support Platform
Introduction
Related Work
Overview of the Layered Graph Data Model
Definitions
Entity Data Graph (G$_D$)
Entity Schema Graph (G$_S$)
Associations Building Process
Association Constraint Validation
Associations Mining Strategy
Experiments
Data Set
Efficiency and Effectiveness Evaluation
Comparison of Association Mining Strategies
Conclusion and Future Work
References
A Study of RDB-Based RDF Data Management Techniques
Introduction
Storage Efficiency
RDF Data Storage Methods
Index-Based Storage Methods
RDF Data Characteristics
Data Characteristics in RDF Benchmarks
Empirical Analysis
Query Evaluation
Query Patterns
Query Patterns in Benchmarks
Empirical Study
Conclusion
References
Requirement-Based Query and Update Scheduling in Real-Time Data Warehouses
Introduction
Related Work
SystemModel
System Components
Task Model
Performance Metrics
Scheduling Algorithm
First-Level Scheduling
Second-Level Scheduling
Experiments
Experimental Setup
Performance Comparison
Conclusions
References
Session 4B: Graph Data
Answering Subgraph Queries over Large Graphs
Introduction
Related Work
Problem Definition
Subgraph Search Algorithm
Vertex Codes
Framework of the Algorithm
Subgraph Query Algorithm
Subgraph Query Based on Partition
Offline Processing
Online Query Based On Partition
Experimental Evaluation
Experiment Preparation
Experimental Results
Conclusions
References
Finding Relevant Papers Based on Citation Relations
Introduction
Related Work
Paper Relatedness in Citation Graph
Paper Recommendation
Problem Formulation
Preliminary
Citation Link
Local Relation Strength
Paper RelevanceMeasurement
Extracting Relevant Candidates
Experiment
Experimental Setup
Offline Evaluation
Expert Evaluation
Conclusions
References
ASAP: Towards Accurate, Stable and Accelerative Penetrating-Rank Estimation on Large Graphs
Introduction
Preliminaries
An Overview of P-Rank
Notations
Formulation of P-Rank Model
Accuracy Estimate on P-Rank Iteration
Stability Analysis of P-Rank Model
P-Rank Matrix Representation
Conditional Number of P-Rank
An Efficient Algorithm for P-Rank Estimating on Undirected Graphs
Experimental Evaluation
Related Work
Conclusions
References
Session 4C: Name Disambiguation
Efficient Name Disambiguation in Digital Libraries
Introduction
Related Work
Our Approach
Web Pages Identification
Mixed Model
Evaluations
Evaluation Results
Comparison with Baseline Methods
Performance Comparison
Conclusions
References
A Classification Framework for Disambiguating Web People Search Result Using Feedback
Introduction
Related Work
Name Disambiguation
Relevance Feedback
The Classification Framework
Features
Key Tokens
Topics
Learning Methods
Experiments
Experiment Setup
Experiment on Features
Experiment on Learning Methods
Conclusion and Future Work
References
Incorporating User Feedback into Name Disambiguation of Scientific Cooperation Network
Introduction
Related Works
Problem Formulation
Problem Definition
User Feedback
Feedback Training Stream
Feature Definition
Incorporating User Feedback into Constraint-Based Perceptron
Experiment
Dataset
Evaluation Measures
Experiment Results
Conclusion
References
Session 5A: Performance
Multi-core vs. I/O Wall: The Approaches to Conquer and Cooperate
Introduction
Related Work
Disk Resident DDTA-OLAP for Multi-core
DDTA-OLAP Model
Storage Model for Multi-core Processing
Multi-Core DDTA-OLAP
Cost Model for Multi-core DDTA-OLAP
Experiments
Basic DDTA-OLAP Performance for DRDB
Intra-Parallel DDTA-OLAP for DRDB
Inter-parallel DDTA-OLAP for DRDB
Conclusions and Future Work
References
W-Order Scan: Minimizing Cache Pollution by Application Software Level Cache Management for MMDB
Introduction
Related Work
Application Software-Based Cache Partitioning Mechanism
Motivation
Physical Address Layout for Cache and Main Memory
W-Order Scan for Main Memory Database
The Realization of W-Order Scan
Experiments
Design of Experiments
Platform and Datasets
Performance Evaluation
Conclusion
References
Index Structure for Cross-Class Query in Object Deputy Database
Introduction
Related Works
Object Deputy Database
Concepts for Path Expression
Path Expression Evaluation
Object Deputy Path Index
Structure of ODPI
Creation of ODPI
Using ODPI
Maintenance of ODPI
Performance Evaluation
Exp-1: Varying Length of Path without Predications
Exp-2: Fixed Length of Path with Predications
Conclusions
References
Session 5B: Data Mining (2)
Ensemble Pruning via Base-Classifier Replacement
Introduction
Related Work
Ensemble Pruning via Base-Classifier Replacement
Problem Definition and the Idea of EPR
Property Analysis
The Proposed Metric
Algorithm
Experiments
Data Sets and Experimental Setup
Experimental Results
Conclusion
References
Efficient Approximate Similarity Search Using Random Projection Learning
Introduction
Random Projection Learning
The Framework
Random Projection
The Algorithm
Complexity Analysis
Experimental Study
Experimental Setup
Effectiveness
Efficiency
Comparison
Related Work
Conclusions
References
Informed Prediction with Incremental Core-Based Friend Cycle Discovering
Introduction
Related Works
Problem Definition
Core-Based Friend Cycle Searching Algorithms
Global Friend Cycle Finding Algorithm
Rapid Incremental Algorithm
Experiments and Discussion
Data Sets and Experiments Configuration
Effectiveness Experiments
Scalability Experiments
Conclusions
References
Session 5C: Temporal Data
Early Prediction of Temporal Sequences Based on Information Transfer
Introduction
Related Work
Kinetic Model of Information Transfer
Learning Parameter k$_optimal$
The Construction of Classifier
Experimental Evaluation
Conclusions
References
Mining Event Temporal Boundaries from News Corpora through Evolution Phase Discovery
Introduction
Related Work
Problem Formulation
Evolution Phases Discovery
System Framework for EPD
Snippet Extraction
Features Selection
Phases Cluster
Decision of the Number of Phases
Experiments
Performance of Snippets Phases Clustering
Performance of Event Phases Discovery
An Application Demonstration
Conclusion
References
Event Detection over Live and Archived Streams
Introduction
Related Work
Preliminaries and Problem Formalization
Event Model
Event Query Definition Language
Types of Hybrid Patterns
SystemDesign
Storage Management
Partial Match Materialization
Event Detection Scheduling Algorithms
Experimental Analysis
Conclusion
References
Session 6A: XML
Renda-RX: A Benchmark for Evaluating XML-Relational Database System
Introduction
Related Work
Requirements of Database Benchmark
Renda-RX Benchmark
Scenario
The Definition of Tables
XML Data
DTD
Workload Design
Transactions
Renda-RX Scalability
The Architecture of Renda-RX Benchmark
One Sample Test on System-X
Summary and Conclusion
References
Energy-Conserving Fragment Methods for Skewed XML Data Access in Push-Based Broadcast
Introduction
Related Works
Document Fragment
Subtree-Level Scheme
Horizontal Fragment Algorithm
Threshold Fragment Algorithm
Modification of the Two-Tier Index Scheme
Experiments
Experimental Setup
Results and Discussion
Conclusions
References
Session 6B: Spatial Data
Evaluating Probabilistic Spatial-Range Closest Pairs Queries over Uncertain Objects
Introduction
Related Work
Probabilistic Queries over Uncertain Data
Closest Pair Queries over Spatial Objects
Problem Definition
Evaluation of PSRCP Query
Pruning Strategies
PSRCP Query Algorithm
Experimental Evaluation
Conclusion
References
Synthesizing Routes for Low Sampling Trajectories with Absorbing Markov Chains
Introduction
Related Work
Preliminaries
Algorithms for Synthesizing Routes
Retrieve Transfer Network
Baseline Algorithm
Turning Edge Maximum Probability Product Method
Hub Node Transfer Method
Experiments
Conclusions
References
Approximate Continuous K-Nearest Neighbor Queries for Uncertain Objects in Road Networks
Introduction
Related Work
Moving State of Uncertain Object (MSUO) Model
Moving State Based ACKNN (MACKNN) Algorithm
Pruning Phase
Refining Phase
Experimental Evaluation
Conclusions
References
Session 6C: Event Detection
Parallel Detection of Temporal Events from Streaming Data
Introduction
Related Work
Temporal Operators on Events
Parallel Processing of Temporal Operators
Stream Partitioning
Analysis of The Two Partitioning Strategies
Performance Study
Experiments on Synthetic Stream Data
Experiments on Real GPS Data
Conclusion
References
Towards Effective Event Detection, Tracking and Summarization on Microblog Data
Introduction
Related Work
Approach Details
Clustering-Based Event Detection from Topical Words
Graph-Based Event Tracking
Event Summarization
Experiments
Data Collection and Preprocessing
Evaluation of Event Detection
Evaluation of Event Tracking
Evaluation of Event Summarization
Conclusion
References
Author Index

System requirements

Save as PDF Copy link into clipboard

Schweitzer Fachinformationen

Web-Age Information Management

Description

More details

Other editions

Additional editions

Content

System requirements