Information Integration and Web Intelligence: 24th International Conference, iiWAS 2022, Virtual Event, November 28–30, 2022, Proceedings

Preface
Organization
Abstracts of Keynote Talks
	Data Integration, Cleaning, and Deduplication: Research versus Reality
	Are Telepresence Robots Here to Stay?
Forum
	2022 Second Annual World AI-BigData Convergence (ABC) Forum
	Contents
Keynotes
Data Integration, Cleaning, and Deduplication: Research Versus Industrial Projects*-10pt
	1 Introduction
	2 Challenge 1: Performance Optimization of ETL/DPW
		2.1 Techniques Used in Industry
		2.2 Approaches Used in Research
		2.3 UDFs in DPWs
		2.4 Final Remarks
	3 Challenge 2: Identifying Duplicate Customer Records
		3.1 Standard Data Deduplication Pipeline
		3.2 Machine Learning in Data Deduplication Pipeline
		3.3 Final Remarks
	4 Challenge 3: Integrating Medical Data
	References
Aspects of Using Telepresence Robot in a Higher Education STEAM Workshop
	1 Introduction
	2 Method
	3 Results
	4 Discussion and Conclusion
	References
Business Data and Applications
An Analysis of Data Modelling for Blockchain
	1 Introduction
	2 Background
		2.1 Blockchain
		2.2 A Blockchain Data Model
	3 Related Work
	4 Research Protocol
	5 State-of-the-Art Overview
	6 Analysis
	7 Conclusion and Research Directions
	References
Sharing Semantic Knowledge for Autonomous Robots: Cooperation for Social Robotic Systems
	1 Introduction
	2 Related Work
	3 The GWEs Approach for Social Robots
		3.1 Overall Framework
		3.2 Overview of the GWEs Approach
		3.3 Applying the GWEs Approach
		3.4 GWEs Adaptability in a Dynamic Context
	4 Case Studies
		4.1 Case Study 1: Bending Machines Workstation
		4.2 Case Study 2: Intra-shop Floor Transportation
		4.3 Example of Use Case Specification in GWEs
	5 Concluding Remarks
	References
Exploiting Named Entity Recognition for Information Extraction from Italian Procurement Documents: A Case Study
	1 Introduction
	2 Related Works
	3 Basics and Problem Statement
	4 Application Scenario: Document Management in EPICS
	5 Experiments
		5.1 Selecting the Most Accurate NER Models
		5.2 Entity-Level Accuracy of the Best NER Models
		5.3 Training Convergence of the Best NER Models
		5.4 Training Times on the NER Models
	6 Qualitative Analysis
	7 Conclusions
	References
bNaming: An Intelligent Application to Assist Brand Names Definition
	1 Introduction
	2 Background
		2.1 Vector Representation of Text
		2.2 Embedding Layer
		2.3 Text Classification
	3 The Proposed Intelligent System
		3.1 Mobile Application Implementation
		3.2 The Development of the API
	4 Proposed Machine Learning Models
		4.1 The Database Construction
		4.2 Data Pre-processing
		4.3 The Machine Learning Models
	5 Experimental Study
	6 Final Remarks
	References
Discovering Conditional Business Rules in Web Applications Using Process Mining
	1 Introduction
	2 Background
	3 Methodology
		3.1 Step1: Building the Dependency Graph
		3.2 Step2: Detecting Substitute Relations
		3.3 Step3: Mining Positive Long-Distance Dependencies
	4 Evaluation
		4.1 The Dataset
		4.2 Substitute Relations
		4.3 Positive Long-Distance Dependency Relations
	5 Conclusion
	References
Comparison of Job Titles for Specific Terms: Investigating “Data Science”
	1 Introduction
	2 Methodology
		2.1 Data Collection and Text Preprocessing
		2.2 Jobs and Similarity Identification
	3 Experiment and Results
		3.1 Data Collection
		3.2 Identifying Top Data Science Job Titles
		3.3 Comparing Job Titles
	4 Conclusion
	References
Generating Smart Contracts for Blockchain-Based Resource-Exchange Systems
	1 Introduction
	2 Framework and Generation of Smart Contracts
	3 Limitations
	4 Conclusion
	References
Analysis of Country Mentions in the Debates of the UN Security Council*-10pt
	1 Introduction
	2 Constructing the Dataset
	3 Detecting Geopolitical Events
	4 Conclusion
	References
Data Mining
A Comparative Performance Analysis of Fast K-Means Clustering Algorithms*-10pt
	1 Introduction
	2 K-Means Clustering Problem
	3 Fast K-Means Algorithms
		3.1 Basic Pruning Criteria
		3.2 Algorithms
	4 Performance Analysis
	5 Conclusions
	References
Mining Twitter Multi-word Product Opinions with Most Frequent Sequences of Aspect Terms
	1 Introduction
		1.1 Some Closely Related ABOM Systems
		1.2 Paper Problem Definition and Contributions
		1.3 Outline
	2 Other Related Work
	3 The Proposed Microblog MASM Miner
	4 An Application of the Proposed MASM System
	5 Experimental and Performance Analysis
	6 Conclusions and Future Work
	References
An Analysis of Human Perception of Partitions of Numerical Factor Domains*-10pt
	1 Introduction
	2 Related Work
	3 Hypotheses
	4 Design of Experiment
	5 Analysis and Result
		5.1 Step-Function
		5.2 Linear Function
		5.3 Uneven Random Function
	6 Conclusion
	References
Fast Top-k Similar Sequence Search on DNA Databases*-10pt
	1 Introduction
	2 Preliminary
	3 Proposed Method: Partition-Based Algorithm
		3.1 Main Ideas
		3.2 Partition-Based Distance Computation
		3.3 Unpromising Pair Pruning
	4 Experiments
		4.1 Experimental Setup
		4.2 Efficiency
		4.3 Accuracy
	5 Conclusion
	References
Graph Data and Knowledge Graph
GN-GCN: Combining Geographical Neighbor Concept with Graph Convolution Network for POI Recommendation
	1 Introduction
	2 Related Work
		2.1 POI Recommendation System
		2.2 Graph Convolution Network in Recommendation System
	3 Proposed Method
		3.1 Preliminary
		3.2 Overview
		3.3 Modeling Active Area Neighbor
		3.4 Geographical Neighbor Concept-Based Graph Convolution Network (GN-GCN)
		3.5 Geographical Neighbor Concept-Based Graph Convolution Network (GN-GCN) with Nonlinear Active Function
		3.6 Model Prediction for POI Recommendation Task
		3.7 Model Training
	4 Experimental Evaluation
		4.1 Datasets
		4.2 Baselines
		4.3 Metrics and Hyperparameter Settings
		4.4 Experiment Results
		4.5 Discussion on the Number of Tainable Parameters
	5 Conclusion
	References
Network Topology to Predict Bibliometrics Indices: A Case Study
	1 Introduction
	2 Co-authorship Networks
		2.1 Network Extraction
		2.2 Networks Analysis
	3 Results
		3.1 Deriving Dataset to Predict Performances
		3.2 Bibliometric Index Prediction
	4 Conclusions and Future Work
	References
A Neural Network Approach for Text Classification Using Low Dimensional Joint Embeddings of Words and Knowledge
	1 Introduction
	2 Related Works
	3 Proposed Approach
		3.1 Embedding Generation Module
		3.2 Semantic Enrichment Module
		3.3 Text Classification Module
	4 Experiments
		4.1 Experimental Setup
		4.2 Results and Discussion
	5 Conclusion
	References
Tree-Based Graph Indexing for Fast kNN Queries
	1 Introduction
		1.1 Existing Approaches and Challenges
		1.2 Our Approaches and Contributions
	2 Preliminary
	3 Proposed Method
		3.1 Tree-Based Index Construction
		3.2 kNN Query Processing
	4 Experimental Analysis
		4.1 Experimental Setting
		4.2 kNN Query Efficiency
	5 Conclusion
	References
IoT and Machine Learning
An Object Separated Storage Framework Towards Spatiotemporal Point Data Fast Query
	1 Introduction
	2 Related Works
	3 Methodology of Model Framework
		3.1 Index Design
		3.2 Prevention of Data Skew
	4 Experiments
		4.1 Settings and Data
		4.2 Comparison and Analysis of Results
	5 Conclusion and Future Work
	References
Streaming Augmented Lineage: Traceability of Complex Stream Data Analysis
	1 Introduction
	2 Related Work
		2.1 Provenance of Database Management System
		2.2 Provenance for Stream Processing
	3 Stream Processing and Lineage
		3.1 Stream Processing Model
		3.2 Streaming Lineage Framework: GeneaLog
	4 Streaming Augmented Lineage
		4.1 Definition
		4.2 Implementation
	5 Experiments
		5.1 Stream Processing Flows
		5.2 Synthetic Data Evaluation
		5.3 Real Data Evaluation
	6 Conclusions
	References
A Web Application for Experimenting and Validating Remote Measurement of Vital Signs*-12pt
	1 Introduction
	2 Background and Related Work
		2.1 Remote Photoplethysmography (rPPG)
		2.2 Literature Review
	3 Web Application Framework
		3.1 Subsystem 1: Front-End Web Interface
		3.2 Subsystem 2: Back-End Data Processing
		3.3 Subsystem 3: SQLite Database
		3.4 Application Deployment
	4 Experiments and Results
	5 Conclusion and Future Work
	References
Neural Kernel Network Deep Kernel Learning for Predicting Particulate Matter from Heterogeneous Sensors with Uncertainty*-12pt
	1 Introduction
	2 Background
		2.1 Urban Air Quality Data
		2.2 Urban Air Pollutants Modeling
	3 Methodology
		3.1 Data Description
		3.2 Model Pipeline
	4 Experiments
		4.1 Model Performance and Comparison
		4.2 Evaluating the Role of Low-Cost Sensors in Prediction Tasks
	5 Conclusions
	References
Ontology and Semantic Web
Comparative Ranking of Ontologies with ELECTRE Family of Multi-criteria Decision-Making Algorithms
	1 Introduction
	2 Related Work
	3 Materials and Methods
		3.1 Complexity Metrics of Ontologies
		3.2 ELECTRE
	4 Experimental Results and Discussion
		4.1 Dataset
		4.2 Computer and Software Environment
		4.3 Ranking Results
		4.4 Pros and Cons of ELECTRE Methods
	5 Conclusion
	References
Machine Learning Selection of Candidate Ontologies for Automatic Extraction of Context Words and Axioms from Ontology Corpus*-10pt
	1 Introduction
	2 Related Works
	3 Materials and Methods
		3.1 Natural Language Processing (NLP)
		3.2 Skip-gram Algorithm
	4 Experiment
		4.1 Dataset
		4.2 Tools and Environment
		4.3 Data Pre-processing
		4.4 Skip-gram Setup
		4.5 Results and Discussion
	5 Conclusion
	References
WAPITI – Web-based Assignment Preparation and Instruction Tool for Interpreters
	1 Introduction
		1.1 Background
		1.2 Approach
	2 Requirements and Proposed Architecture
	3 Functionality and Showcase
		3.1 Preparation for an Assignment
		3.2 Initializing the Framework
		3.3 Sentence Retrieval and Enrichment of Data
	4 Conclusion and Future Work
	References
Performance and Optimization
Optimization Heuristics for Cost-Efficient Long-Term Cloud Portfolio Allocations
	1 Introduction
	2 State of the Art
	3 Problem Formulation
	4 Optimization Approaches
		4.1 The Greedy Optimization Approach
		4.2 The Evolutionary Optimization Approach
	5 Evaluation
	6 Conclusion
	References
Latency-Aware Inference on Convolutional Neural Network Over Homomorphic Encryption
	1 Introduction
	2 Related Work
		2.1 CNN Inferring
		2.2 Pruning of HE-Based CNN
	3 Latency-Aware Inference
		3.1 Preliminary - Batch-Axis Packing and Channel-Wise Packing
		3.2 Comparison of Number of Homomorphic Operations
		3.3 Adoption of Structured Pruning
	4 Experimental Evaluation
		4.1 Experimental Setup
		4.2 Result
	5 Conclusion
	6 Availability of Data and Materials
	References
PR-MVI: Efficient Missing Value Imputation over Data Streams by Distance Likelihood
	1 Introduction
	2 Related Works
	3 Overview of DLM and Preliminaries
		3.1 Overview of DLM
		3.2 Distance Metric
		3.3 Distance Predicting Model
		3.4 Distance Likelihood
	4 Proposed Approach
		4.1 Overview
		4.2 Proposed Approach (PR-MVI)
	5 Experimental Evaluation
		5.1 Predicting Accuracy of Missing Attribute Values
		5.2 Predicting RMS Error of Missing Attribute Values
	6 Conclusion
	References
Discovering Relational Implications in Multilayer Networks Using Formal Concept Analysis
	1 Introduction
	2 Preliminary
		2.1 Multilayer Networks
		2.2 Formal Concept Analysis
		2.3 Implications
	3 Approach
		3.1 Constructing a Formal Context from a Multilayer Network
		3.2 Formal Concepts and Implications
	4 Results on Empirical Datasets
		4.1 Datasets
		4.2 Construction of Formal Context
		4.3 Discovered Implications
	5 Application in Link Prediction
		5.1 Preparation
		5.2 Prediction
		5.3 Evaluation
		5.4 Results
		5.5 Discussion
	6 Conclusion
	References
Inexpensive and Effective Data Fusion Methods with Performance Weights
	1 Introduction
	2 Proposed Methods
	3 Experiments
		3.1 Data Sets Used
		3.2 Experimental Procedures and Results
	4 Analysis
	5 Conclusion
	References
GPU Accelerated Parallel Implementation of Linear Programming Algorithms*-12pt
	1 Introduction
	2 Related Works
	3 Linear Programming
	4 Solving Multiple Linear Programs on GPU
	5 Experimental Analysis
	6 Conclusion
	References
Towards Explaining DL Non-entailments by Utilizing Subtree Isomorphisms*-12pt
	1 Introduction
	2 Background and Motivation
	3 Methodology
	4 Conclusion
	References
Query Optimization in NoSQL Databases Using an Enhanced Localized R-tree Index*-12pt
	1 Introduction
	2 Related Work and Motivation
	3 Methodology
		3.1 Enhanced Range Query for Localized Index
	4 Experimental Results
		4.1 Index Construction
		4.2 Range Queries
		4.3 kNN Queries
	5 Conclusions and Future Work
	References
Handling Exit Node Vulnerability in Onion Routing with a Zero-Knowledge Proof
	1 Introduction
	2 Background and Related Work
	3 Exit Node Routing in the Onion Network with ZKP
	4 Proof of Concept
	References
Privacy and Security
An Accurate, Flexible and Private Trajectory-Based Contact Tracing System on Untrusted Servers
	1 Introduction
	2 Related Work
	3 Privacy-Preserving Calculation of Infection Probability
	4 Experiments
	5 Conclusion
	References
Bilateral Bargaining for Healthcare Data Sharing
	1 Introduction
	2 Related Work
	3 Bilateral Bargaining
	4 Evaluation
	5 Conclusion
	References
Modifying Neo4j's Object Graph Mapper Queries for Access Control
	1 Introduction
	2 Authorization Requirements
	3 Related Work
	4 Types of Operations
	5 Modifying Queries
	6 Performance
	7 Conclusion and Future Work
	References
Recommendation Systems
A Recommendation Method for Recipes Containing Unskillful Elements Using Naïve Bayes Classifier to Improve Cooking Skills
	1 Introduction
	2 Related Work
		2.1 Recipe Recommendation
		2.2 Assistance for Beginner Cooks
	3 Proposed Method
		3.1 Components of a Cooking Recipe
		3.2 Overview
		3.3 Naïve Bayes Classifier and Calculation of the Mastery Score
		3.4 Recipe Recommendation with Unskillful Elements
	4 Example of Recipe Recommendation
		4.1 Usage Data
		4.2 Calculation of the Degree of Mastery
		4.3 Recipe Recommendation Results
	5 Conclusion
	References
Extraction of Complementary Topics Based on Phrase Importance and Co-occurrence in Technical Blogs
	1 Introduction
	2 Related Work
	3 Proposed Method
		3.1 Extraction of Phrases Representing a Topic from a Set of Articles
		3.2 Calculation for Learning of Unknown Phrases
		3.3 Elimination of Redundancy in Phrases
	4 Evaluation Experiment
		4.1 Experimental Settings
		4.2 Results and Discussion
	5 Summary and Future Issues
	References
Feature Relevance Analysis of Product Reviews to Support Online Shopping
	1 Introduction
	2 Related Work
	3 Scoring Method by Features
		3.1 Processing Steps of the Feature Analysis Method for Review Videos
	4 Evaluation Experiment
		4.1 Accuracy Evaluation of Feature Analysis Method for Video
		4.2 System Usability Evaluation
	5 Conclusion
	References
Annotation System for Dialogue Datasets of Older Adult's with Photos and Storytelling
	1 Introduction
		1.1 System Architecture
	2 Experiment
		2.1 Method
		2.2 Result
	3 Discussion and Conclusion
	References
Evaluation Axes for Automatically Generated Product Descriptions
	1 Introduction
	2 Related Work
	3 The Product Description Evaluation Axes
	4 Experiment
		4.1 Experimental Conditions
		4.2 Results and Discussion of the Experiment
	5 Conclusion
	References
Similarity Measures and Metrics
CISQA: Corporate Smart Insights Question Answering System
	1 Introduction
	2 Related Work
	3 System Overview
		3.1 Query Translation
		3.2 Query Execution
		3.3 Curation
	4 Results and Discussion
	5 Conclusion and Future Work
	References
Symmetry Metrics for Pairwise Entity Similarities
	1 Introduction
	2 Related Work
	3 Methods
		3.1 Transform Pairs of Vectors to Joint Vectors
		3.2 Transform Joint Vectors to GAF Images
		3.3 Train CNN Image Classification Models
		3.4 Get Similarity Metrics by Interpreting Trained Model Results
	4 Experiments
		4.1 Climate Time Series Data for Training the Model and Data Analysis
		4.2 Dissimilar Word Pair Detection
	5 Conclusion
	References
A New Method to Measure Similarity of Words in Japanese Twitter Based on Related Images
	1 Introduction
	2 Related Work
	3 Framework
		3.1 Retrieval of Related Images
		3.2 Similarity Computation
	4 Data
	5 Experiment
		5.1 Experimental Setup
		5.2 Results
		5.3 Analysis
	6 Conclusions and Future Work
	References
Topic and Text Matching
Hybrid Phishing URL Detection Using Segmented Word Embedding
	1 Introduction
	2 Related Work
	3 Segmentation-Based Phishing URL Detection
		3.1 Overview
		3.2 URL-Tokenizer
		3.3 Recursive-Tokenizer
	4 NLP Features and Hybrid Model Architecture
		4.1 NLP Features
		4.2 Hybrid Model Architecture
	5 Experimental Evaluation
	6 Conclusion
	References
A Scheme for News Article Classification in a Low-Resource Language
	1 Introduction
	2 Related Work
		2.1 Techniques for Low-Resource Languages
		2.2 Data Augmentation for Texts
	3 Dataset
	4 Data Augmentation
	5 Text Classification Using a Pre-trained Language Model
	6 Experimental Evaluation
		6.1 Experimental Setup
		6.2 Experimental Results
	7 Conclusions
	References
Expertise Computation for Automatic Reviewer Assignment
	1 Introduction
	2 Related Work
	3 Problem Definition
	4 Methodology for Expertise Computation
		4.1 Matching Manuscript Topics with Reviewer Publications
		4.2 Create Reviewer Profile
		4.3 Consolidating Reviewer Expertise
		4.4 Expertise Computation Algorithm
	5 Experimental Evaluation
		5.1 Results
	6 Conclusion
	References
Detection of Hot Topics Using Multi-view Text Clustering
	1 Introduction
	2 Detection of Hot Topics Using Multi-view Text Clustering
		2.1 Basic Concepts of SOM
		2.2 Multi-view Mapping Using SOM
		2.3 Merging and Splitting
	3 Experimental Results
		3.1 Data Set Description
		3.2 Evaluation Measures
		3.3 Experimental Results
	4 Conclusion
	References
Virtual Reality/Augmented Reality
Interactive Visualization of Comic Character Correlation Diagrams for Understanding Character Relationships and Personalities
	1 Introduction
	2 Data Set Creation
	3 Visualization Method
	4 Experimental Validation
	5 Discussion
	6 Conclusion
	References
Two Case Studies on Guiding Human Behavior Using Virtualization Technologies in Distributed Virtual Shopping Malls
	1 Introduction
	2 Background and Related Work
		2.1 Bandwagon and Snob Effects
		2.2 Behavior Economics
		2.3 Guiding Human Behavior Through Digital Technologies
	3 Guiding Human Behavior Through Visualizing a Virtual Crowd
	4 Guiding Human Behavior Through Presenting Nudges
	5 Conclusion: Towards a Generic Framework for Virtualizing the Real World
	References
Central Figures in the Climate Change Discussion on Twitter
	1 Introduction
	2 Methods
		2.1 Data Collection and Preprocessing
		2.2 Network of Co-mentions
	3 Results
		3.1 Data Overview
		3.2 Network of People
		3.3 Network of Brands
	4 Discussion and Conclusion
	References
E-Tracer: A Smart, Personalized and Immersive Digital Tourist Software System
	1 Introduction
	2 Related Work
	3 E-Tracer System
	4 User Evaluation
	5 Conclusion and Future Work
	References
Author Index