Data Management Technologies and Applications (Communications in Computer and Information Science)

✍ Scribed by Alfredo Cuzzocrea (editor), Oleg Gusikhin (editor), Slimane Hammoudi (editor), Christoph Quix (editor)

• Publisher: Springer
• Year: 2023
• Tongue: English
• Leaves: 256
• Category: Library

✦ Synopsis

This book constitutes the refereed post-proceedings of the 10th International Conference and 11th International Conference on Data Management Technologies and Applications, DATA 2021 and DATA 2022, was held virtually due to the COVID-19 crisis on July 6–8, 2021 and in Lisbon, Portugal on July 11-13, 2022.

The 11 full papers included in this book were carefully reviewed and selected from 148 submissions. They were organized in topical sections as follows: engineers and practitioners interested on databases, big data, data mining, data management, data security and other aspects of information systems and technology involving advanced applications of data.

✦ Table of Contents

Preface
Organization
Contents
A Survey-Based Evaluation of the Data Engineering Maturity in Practice
1 Introduction
2 Background
3 Research Methodology
3.1 Survey Design and Execution
3.2 Data Analysis
4 Results
4.1 Data Engineering Maturity: Theory vs Practice
4.2 Data Engineering Maturity: Specific Topics
4.3 Data Engineering Maturity: Results per Phase
5 Conclusion
References
Automating Data Quality Monitoring with Reference Data Profiles
1 Introduction
2 Problem Statement and Related Work
2.1 The Theoretical Perspective: DQ Dimensions and Metrics
2.2 The Practitioners Perspective: DQ Rules and Problems
2.3 Knowledge Graphs for Data Integration
3 An Approach for Automated Data Quality Monitoring
4 DQ-MeeRKat: Monitoring Data Quality with RDPs
4.1 Components for Initialization Phase
4.2 Components for DQ Monitoring
5 Experiments and Results
5.1 Evaluation Data
5.2 Experimental Setup
5.3 Qualitative Evaluation
5.4 Experiment 1: Monitor the Quality of Batch-Loaded Data
5.5 Experiment 2: Monitor the Quality of Streaming Data
6 Conclusion and Future Work
References
Towards Comparable Ratings: Quantifying Evaluative Phrases in Physician Reviews
1 Introduction
1.1 Use Case: Online Physician Reviews
1.2 Unique Feature: Implicit Aspect Mentions
1.3 Course of Action
2 Related Literature
2.1 Online Physician Reviews
2.2 Aspect-based Sentiment Analysis
2.3 Deep Learning for ABSA
2.4 Quantifying Evaluative Phrases
2.5 Correlation with Metadata
3 Underlying Raw Data
4 Annotation Process and Dataset Preparation
4.1 Annotation Process for the Aspect Terms
4.2 Preparation of Further Datasets
5 Model Training
6 Application to Physician Reviews
6.1 Recognition of Aspect Classes, Polarity and Importance
6.2 Correlation Analyses
7 Conclusion
References
SubTempora: A Hybrid Approach for Optimising Subgraph Searching
1 Introduction
2 Notation, Background, and Problem Statement
3 Space-Efficient Subgraph Indexing
3.1 The Index Graph
3.2 Hashmap-Based Radix Tree (HRTree)
3.3 LinkedList-Based Radix Tree (LRTree)
4 Compact Candidate Graph Set Representation
4.1 Compressed Inverted Index
4.2 Compressed Bitmap Index
5 Evaluation
5.1 System Setup, Datasets and Queries
5.2 Parameter Selection
5.3 Performance Comparison
6 Related Work
7 Conclusions
References
Exploring Instagram and Youtube Data to Extract User Insights: The Greek Paradigm
1 Introduction
2 Related Work
3 Methodology
3.1 Problem Identification and Preparation
3.2 Data Collection and Storage
3.3 Data Exploration and Analysis
4 Results
4.1 Instagram Results
4.2 YouTube Results
4.3 Business and Influencer Marketing
4.4 Impact of COVID-19
5 Conclusions and Future Work
References
Automatic Detection of Facial Landmarks for Denture Models-4pt
1 Introduction
2 Materials and Methods
2.1 2D Facial Landmarks Annotation
2.2 3D Facial Landmarks Annotation
3 Results and Discussion
3.1 2D Facial Landmarks Annotation
3.2 3D Facial Landmarks Annotation
4 Related Work
4.1 2D Facial Landmarks Annotation
4.2 3D Facial Landmarks Annotation
5 Conclusions and Future Work
References
Combining Image and Text Matching for Product Classification in Retail
1 Introduction
2 Research Review
3 Dataset
4 Methods
4.1 Image-Based Product Classification
4.2 Text-Based Product Classification
4.3 Hybrid Approach
4.4 Implementation
4.5 Preparation of the Data
4.6 Performance Metrics
5 Results
5.1 Nearest Neighbor Classification
5.2 Feature Extraction
5.3 Feature Reduction
5.4 Performance Evaluation
5.5 Hybrid Classification Approach
6 Discussion
6.1 Advantages
6.2 Limitations
7 Future Research
References
Automatic Sentiment Labelling of Multimodal Data
1 Introduction
2 Related Work
2.1 Sentiment Labelling for Training and Testing Datasets
2.2 Text Sentiment Analysis
2.3 Multimodal Sentiment Analysis
3 Methodology
3.1 Datasets
3.2 Combined-Text-Features Preparation
3.3 Afinn Labelling and Tokenization
3.4 Image+Text-Features Preparation
3.5 Model Discussion
3.6 Experiment Details
4 Experimental Results and Discussion
5 Conclusion
References
From Cracked Accounts to Fake IDs: User Profiling on German Telegram Black Market Channels
1 Introduction
2 Domain Discovery
2.1 Black Market Entities
2.2 Black Market Relations
3 Corpus Composition
4 Profile Clustering Pipeline
4.1 Black Market Entity Recognition Model Training
4.2 Black Market Relation Extraction Model Training
4.3 Profile Creation
4.4 Profile Clustering
5 Case Study
6 Related Work
7 Conclusion and Future Work
References
Data Mining and Machine Learning to Predict the Sulphur Content in the Hot Metal of a Coke-Fired Blast Furnace
1 Introduction
2 Research Method
3 Results and Discussions
4 Conclusions
References
Automatic Instructional Feedback, and a Lecture Hub System: A Strategy Towards Nurturing the Acquisition of a Structured Engagement Behavior
1 Introduction
2 Related Work
3 Recommendation Workflow
4 The Lecture Hub
5 SQL Exercise Analysis
6 Concept of Comparing Slides and Exercises
7 Implementation
7.1 Recognition Strategy for Joins
8 Evaluation
8.1 Performance Measures
8.2 Baseline Evaluation
8.3 Detecting Joins
8.4 Clustering Keywords
8.5 Minimal Cosine Value
9 Discussion
10 Summary and Future Work
References
Author Index