This book examines modern paradigms of disease control based on social network surveillance applications, including electronic sentinel surveillance and wireless application-based surveillance science. It also highlights topics that integrate statistical and epidemiological sciences with surveillance practice and, in order to reflect the evolution of social networking practices, discusses topics concerning the challenges for surveillance theory and practice.
In turn, the book goes a step further by providing insights on how we need to analyse epidemiological trends by following best practices on distinguishing useful information from noise, namely fake news, false reporting of disease incidents and events, etc. At the same time, we need to be able to protect health-focused applications and communication tools via cybersecurity technologies and to ensure that anonymity of reporting and privacy are preserved. In closing, the book discusses the role and impact of social media on disease surveillance, as well as the current role of communities in infectious disease surveillance and control.
Author(s): Thirimachos Bourlai, Panagiotis Karampelas, Reda Alhajj
Series: Lecture Notes in Social Networks
Publisher: Springer
Year: 2022
Language: English
Pages: 236
City: Cham
Preface
Disease Control Through Social Network Surveillance
Chapter Contributions
Contents
Editors and Contributors
About the Editors
Contributors
Analysis of Public Perceptions Towards the COVID-19 Vaccination Drive: A Case Study of Tweets with Machine Learning Classifiers
1 Introduction
2 A Brief Literature Survey
3 Data Collection, Pre-processing and Methodology
3.1 Raw-Data Acquisition
3.2 Data Pre-processing
3.3 Data Visualization
3.3.1 Geographical Analytics of Tweets
3.3.2 Users with Maximum Tweets
3.3.3 Most Frequent Hashtags
3.3.4 Monthly Statistics of Tweets
3.3.5 Textual Analysis of Tweets
3.3.6 Word and Phrase Associations
4 Experimental Design, Results and Discussions
4.1 Feature Selection
4.2 Platform Employed and Performance Evaluation Parameters
5 Conclusions
References
Spreader-Centric Fake News Mitigation Framework Based on Epidemiology
1 Introduction
2 Related Work
3 Epidemiology Inspired Framework
4 Preliminaries
4.1 Trustingness and Trustworthiness
4.2 Believability
4.3 Community Health Assessment Model
5 Vulnerability Assessment
6 Identification of Infected Population
7 Risk Assessment of Population
8 Infection Control and Prevention
9 Conclusion
References
Understanding How Readers Determine the Legitimacy of Online Medical News Articles in the Era of Fake News
1 Introduction
2 Background and Related Work
2.1 Presentation and Content in True and Fake News Articles
2.2 Detecting Fake News Articles: The Reader's Side
3 Methodology
3.1 Survey 1
3.2 Survey 2
3.3 Survey 3
3.4 Clustering Analysis
4 Results
4.1 Survey 1
4.2 Survey 2
4.3 Survey 3
5 Discussion
6 Conclusion
References
Trends, Politics, Sentiments, and Misinformation: Understanding People's Reactions to COVID-19 During Its Early Stages
1 Introduction
1.1 Contributions
1.2 Organization
2 Related Work
3 Reactions to COVID-19 During its Early Stages: Social Media Analytics
3.1 Dataset and Implementation Environment
3.2 Analysis Results
3.2.1 Number of Posts Related to COVID-19 Over Time
3.2.2 Number of Published News Per Web Site, Per Month
3.2.3 Geographic Distribution of Shared News
3.2.4 Geographic and Temporal Trends in Fake News
3.2.5 Opinions About Public Figures
4 Conclusion
References
Citation Graph Analysis and Alignment Between Citation Adjacency and Themes or Topics of Publications in the Area of Disease Control Through Social Network Surveillance
1 Introduction
2 Literature Review
3 The Citation Graph Methodology
4 Data
4.1 Data Collection
4.2 Derived Networks
5 Discussion of Nodal Attributes of the DCSNS Citation Graph
5.1 Degrees
5.2 Types
5.3 Themes
5.4 Topics
5.5 Relationships Between Nodal Attributes
5.6 Degree and Attribute Assortativities
6 Conclusions
References
Privacy in Online Social Networks: A Systematic Mapping Study and a Classification Framework
1 Introduction
2 Related Work
3 Systematic Mapping
3.1 Definition of Key Terms
3.2 Definition of Research Questions: Step 1
3.3 Conduct Search for Primary Studies and Screening of Papers for Inclusion and Exclusion: Steps 2 and 3
3.4 Classification Scheme and Mapping: Steps 3 and 4
3.4.1 RQ1 and RQ2: Topics in OSN Privacy Research
3.4.2 RQ3 and RQ4: Theoretical Contributions in OSN Privacy Research
3.4.3 RQ5 and RQ6: RE Research Papers in OSN Privacy Research
3.4.4 RQ7 and RQ8: Venues in OSN Privacy Research
4 Classification Framework for the Design and Action Theoretical Contributions
5 Discussion
6 Conclusion
References
Beyond Influence Maximization: Volume Maximization in Social Networks
1 Introduction
2 Related Work
3 Method
3.1 Data
3.2 Volume Maximization
3.3 Independent Cascade (IC) Diffusion Model
3.4 Reinforcement Learning Framework
3.5 Reward for the RL Framework
3.5.1 Diffusion Degree
3.5.2 Maximum Influence Degree
3.6 RL Learning Model
3.6.1 Q-Learning
3.6.2 SARSA
3.7 IBL Framework
3.7.1 Instance-Based Learning (IBL) Model
3.8 CELF-Volume Algorithm
3.9 Baseline Algorithms
3.10 Model Calibration
3.11 Expectation
4 Result
5 Discussion and Conclusion
References
Concerns of Indian Population on Covid-19 Vaccine Shortage Amidst Second Wave Infection Rate Spikes: A Social Media Opinion Analysis
1 Introduction
2 Literature Review
3 Methodological Approach
3.1 Preprocessing
3.2 Topic Modeling Process
4 Results
5 Discussion
6 Conclusions
References
The Effects of Face Masks on the Performance of Modern MWIR Face Detectors
1 Introduction
1.1 Goals and Contributions
2 Related Work
3 Methodology
3.1 Deep Learning Models
3.1.1 SSD MobileNet V2
3.1.2 SSD ResNet50 V1
3.1.3 CenterNet HourGlass104
3.1.4 CenterNet ResNet50 V2
3.1.5 Faster R-CNN Inception-ResNet V2
4 Experiments and Results
4.1 Datasets
4.2 Experimental Protocol
4.3 Results
4.4 Face Recognition Experiments
5 Conclusions and Future Work
References
Multispectral Face Mask Compliance Classification Duringa Pandemic
1 Introduction
2 Related Work
2.1 Masked Face Recognition
2.2 Mask Detection and Classification
3 Methodology
3.1 Classification Models
3.2 Dataset
3.3 Experimental Setup
3.4 Evaluation Metrics
4 Results and Discussion
4.1 Visible Results
4.2 Thermal Results
4.3 FMLD Test Set Results
4.4 Limitations
5 Conclusion and Future Work
References
On the Effectiveness of Visible and MWIR-Based Periocular Human Authentication When Wearing Face Masks
1 Introduction
1.1 Goals and Contributions
2 Related Research
3 Methodology
3.1 Pre-processing
3.1.1 MTCNN
3.2 FaceNet
3.3 VGG Face
3.4 Selecting Pre-trained Model
4 Experimental Results
4.1 Datasets
4.1.1 MILAB(B)-VTF
4.1.2 RMFD
4.2 Effects of Different Datasets
4.3 Data Preprocessing
4.4 Visible vs Thermal Data
4.5 Performance of Different Models
5 Conclusion and Future Work
References
