de
en
Schliessen
Detailsuche
Bibliotheken
Projekt
Impressum
Datenschutz
Schliessen
Publizieren
Besondere Sammlungen
Digitalisierungsservice
Hilfe
Impressum
Datenschutz
zum Inhalt
Detailsuche
Schnellsuche:
OK
Ergebnisliste
Titel
Titel
Inhalt
Inhalt
Seite
Seite
Im Werk suchen
Leveraging Social Media in disaster situations / Hamada Mohamed Abdelsamee Zahera ; 1. Reviewer: Prof. Dr. Axel-Cyrille Ngonga Ngomo, 2. Reviewer: Prof. Dr. Michael Cochez. Paderborn, 2023
Inhalt
Titlepage
Abstract
Acknowledgement
Contents
1 Introduction
1.1 Social Media during Disasters
1.2 Mining and Processing Social Media Data
1.3 Motivation
1.4 Research Questions and Contributions
1.5 Thesis Outline
1.6 Own publications
1.7 Source Code
2 Background
2.1 Concepts and Terminology
2.2 Collecting and Processing Social Media Data
2.3 Representation Learning Approaches
2.3.1 Traditional Representation
2.3.2 Embeddings-based Representation
2.4 Deep Learning Models for Natural Language Processing
2.4.1 Convolutional Neural Network
2.4.2 Recurrent Neural Network
2.4.3 Long-Short Term Memory
2.4.4 Graph Attention Network
2.5 Knowledge Graphs
2.6 Performance Evaluation
2.6.1 Accuracy, Precision, Recall, F1
2.6.2 Alert Accumulative Worth
2.6.3 Keyphrase Extraction Evaluation
2.7 Datasets
2.8 Applications
2.9 Summary
3 State-of-the-Art
3.1 Early Event Detection
3.1.1 Traditional Approaches
3.1.2 State-of-the-art approaches
3.2 Filtering Informative Tweets
3.2.1 Traditional Approaches
3.2.2 State-of-the-art Approaches
3.3 Summarizing Disaster-related Tweets
3.3.1 Traditional Approaches
3.3.2 State-of-the-art Approaches
3.4 Summary
4 Joint Learning from Environmental Data and Social Media
4.1 Overview
4.2 Data Analysis and Preliminaries
4.3 Our Approach
4.3.1 Problem Formulation
4.3.2 Semantic-enriched Word Embeddings
4.3.3 Model I: Feature Extractor
4.3.4 Model II: Typhoon Classifier
4.4 Experiments
4.4.1 Baselines
4.4.2 Evaluation Setup
4.4.3 Discussion and Result Analysis
4.5 Summary and Conclusion
5 Classifying Social Media into Multiple Information Types
5.1 Overview
5.2 Our Approach
5.2.1 Tweets Preprocessing
5.2.2 Fine-tuning BERT Model
5.3 Experiments
5.3.1 Dataset
5.3.2 Baselines
5.3.3 Evaluation Metrics
5.3.4 Results and Discussion
5.4 Summary and Conclusion
6 Identifying Actionable Information From Social Media
6.1 Overview
6.2 Our Approach
6.2.1 Problem Formulation
6.2.2 The I-AID Architecture
6.3 Experiments
6.3.1 Datasets
6.3.2 Baselines
6.3.3 Implementation and Preprocessing
6.3.4 Evaluation Metrics
6.3.5 Evaluating Actionable Information
6.3.6 Results and Discussion
6.3.7 Ablation Study
6.4 Summary and Conclusion
7 Keyphrases Extraction from Disaster-related Tweets
7.1 Overview
7.2 Our Approach
7.2.1 Problem Formulation
7.2.2 Present Keyphrase Extraction
7.2.3 Absent Keyphrase Generation
7.2.4 Keyphrases Semantic Matching
7.3 Experiments
7.3.1 Experimental Setup
7.3.2 Present Keyphrase Evaluation
7.3.3 Absent Keyphrase Evaluation
7.3.4 Ablation Study
7.3.5 Use Case: Keyphrase Extraction from Crisis Tweets
7.4 Summary and Conclusion
8 Conclusion
8.1 Summary
8.1.1 Research Contributions
8.2 Open Challenges and Future Work
Bibliography
Die detaillierte Suchanfrage erfordert aktiviertes Javascript.