Urban Analytics with Social Media Data: Foundations, Applications and Platforms

✍ Scribed by Tan Yigitcanlar, Nayomi Kankanamge

• Publisher: CRC Press/Chapman & Hall
• Year: 2022
• Tongue: English
• Leaves: 437
• Edition: 1
• Category: Library

✦ Synopsis

The use of data science and urban analytics has become a defining feature of smart cities. This timely book is a clear guide to the use of social media data for urban analytics.

The book presents the foundations of urban analytics with social media data, along with real-world applications and insights on the platforms we use today. It looks at social media analytics platforms, cyberphysical data analytics platforms, crowd detection platforms, City-as-a-Platform, and city-as-a-sensor for platform urbanism. The book provides examples to illustrate how we apply and analyse social media data to determine disaster severity, assist authorities with pandemic policy, and capture public perception of smart cities.

This will be a useful reference for those involved with and researching social, data, and urban analytics and informatics.

✦ Table of Contents

Cover
Half Title
Title Page
Copyright Page
Dedication
Contents
List of Figures
List of Tables
Foreword
Preface
Authors
Part I: Foundations
1. Urban Big Data and Social Media Analytics
1.1. Introduction
1.2. Literature Background
1.2.1. Big Data Analytics
1.2.2. Social Media Data Analytics
1.2.3. Urban Analytics
1.3. Methods
1.4. Results
1.4.1. General Observations
1.4.2. State-of-the-Art Technologies in Relevance to Application Areas
1.4.2.1. Big Data Analytics
1.4.2.2. Social Media Analytics
1.4.2.3. Urban Analytics
1.4.3. Opportunities and Constraints
1.4.3.1. Big Data Analytics
1.4.3.2. Social Media Analytics
1.4.3.3. Urban Analytics
1.5. Discussion
1.6. Conclusion
Appendix
References
2. Volunteer Crowdsourcing and Social Media
2.1. Introduction
2.2. Literature Background
2.2.1. Instruments of Disaster Risk Reduction
2.2.2. Characteristics of Volunteer Crowdsourcing
2.3. Methodology
2.4. Results
2.4.1. General Observations
2.4.2. Technologies for Volunteer Crowdsourcing
2.4.2.1. Geo-technology
2.4.2.2. Mobile Communication
2.4.2.3. Digital Crisis Information
2.4.2.4. Digital Volunteerism
2.4.3. Attributes of Volunteer Crowdsourcing
2.4.3.1. Multidirectional Communication
2.4.3.2. Situation Awareness
2.4.3.3. Collective Intelligence
2.5. Discussion and Conclusion
References
3. Government Social Media Channels
3.1. Introduction
3.2. Literature Background
3.2.1. Community Engagement in Disaster Management at Large
3.2.2. Community Engagement in Disaster Management via Social Media
3.3. Methodology
3.3.1. Selection of Official Social Media Pages
3.3.2. Measuring Level of Community Engagement
3.3.2.1. Indices
3.3.2.2. Community Engagement by the Types of Social Media Posts
3.3.2.3. Community Engagement by the Social Media Content
3.4. Results
3.4.1. General Observations
3.4.2. Community Engagement by the Types of Social Media Posts
3.4.3. Community Engagement by the Social Media Content
3.4.4. Social Media Content and Their Contribution to Managing Disasters
3.5. Discussion
3.5.1. How Effectively Do People Engage in Social Media in Relation to Disaster Management?
3.5.2. How Does Social Media Contribute to Disaster Management?
3.6. Conclusion
References
Part II: Applications
4. Social Media Analytics in Disaster Policy
4.1. Introduction
4.2. Literature Review
4.2.1. Existing Technologies in Disaster Management
4.2.2. Social Media as a New Technology for Disaster Management
4.3. Case Study
4.3.1. Methodology
4.3.2. Data and Tools
4.3.3. Descriptive Analysis
4.3.4. Content Analysis
4.3.5. Spatial Analysis
4.4. Results
4.4.1. Descriptive Analysis
4.4.1.1. Twitter Statistics
4.4.1.2. User Analysis
4.4.1.3. URL Analysis
4.4.2. Content Analysis
4.4.3. Spatial Analysis
4.5. Discussion
4.5.1. Ways That Social Media Can Be Utilised for Better Managing Disaster Stages
4.5.2. Myths and Facts About Using Social Media Data for Disaster Management
4.6. Conclusion
References
5. Social Media Analytics in Pandemic Policy
5.1. Introduction
5.2. Literature Background
5.2.1. Epidemic and Pandemic
5.2.2. Stages of a Pandemic Spread
5.2.2.1. Pre-concave
5.2.2.2. Concave-Up
5.2.2.3. Linear
5.2.2.4. Concave-Down
5.2.3. Global Suppression Measures
5.2.3.1. Flattening the Curve
5.2.3.2. Hammer and Dance
5.2.4. Social Media Analytics
5.3. Research Design
5.3.1. Case Study
5.3.2. Methodological Approach
5.3.3. Data and Tools
5.4. Results
5.4.1. General Observations
5.4.2. Suppression Measures
5.4.3. Positive Community Perceptions
5.4.3.1. Pre-concave
5.4.3.2. Concave-Up
5.4.3.3. Linear
5.4.3.4. Concave-Down
5.4.4. Negative Community Perceptions
5.4.4.1. Pre-concave
5.4.4.2. Concave-Up
5.4.4.3. Linear
5.4.4.4. Concave-Down
5.5. Discussion
5.6. Conclusion
References
6. Social Media Analytics in Capturing Perceptions
6.1. Introduction
6.2. Literature Background
6.3. Research Design
6.3.1. Case Study
6.3.2. Data
6.3.3. Descriptive Analysis
6.3.4. Content Analysis
6.3.5. Network Analysis
6.3.6. Policy Analysis
6.4. Results
6.4.1. What are the Trending Smart City Concepts and Technologies?
6.4.2. What Are the Relationships Between Smart City Concepts and Technologies?
6.4.3. What Are the Official Smart City Policies That Influence Perception and Utilisation of Smart City Concepts and Technologie
6.5. Discussion and Conclusion
References
7. Social Media Analytics in Analysing Perceptions
7.1. Introduction
7.2. Literature Background
7.2.1. Artificial Intelligence
7.2.2. Artificial Intelligence Technologies
7.2.3. Artificial Intelligence Application Areas in Urban Planning and Development
7.3. Research Design
7.3.1. Case Study
7.3.2. Methodology
7.4. Results
7.4.1. General Observations
7.4.2. Community Sentiments
7.4.3. Artificial Intelligence Technologies
7.4.4. Artificial Intelligence Related Urban Planning and Development Concepts
7.4.5. Relationships Between Artificial Intelligence Technologies and Urban Planning and Development Concepts
7.5. Discussion
7.6. Conclusion
References
Part III: Platforms
8. Social Media Analytics Platforms
8.1. Introduction
8.1.1. Smart Cities, Transportation and Social Sensing
8.1.2. Aim and Approach
8.2. Literature Review
8.2.1. Traffic Events Detection Using Social Data (Any Language)
8.2.2. Traffic Events Detection Using Social Data (Arabic Language)
8.2.3. Solution for Labelling Large-Scale Dataset (Any Language)
8.2.4. Research Gap, Novelty, Contributions and Utilisation
8.3. Methodology and Design
8.3.1. Tools and Libraries
8.3.2. Data Collection and Storage Component
8.3.3. Data Pre-processing Component
8.3.3.1. Irrelevant Characters Removal
8.3.3.2. Tokeniser and Normaliser
8.3.3.3. Stop-Words Removal
8.3.3.4. Stemmer
8.3.4. Tweets Labelling Component
8.3.4.1. Automatic Labelling for Events Tweets
8.3.4.2. Automatic Labelling for Irrelevant Tweets
8.3.5. Feature Extractor Component
8.3.6. Tweets Filtering Component
8.3.6.1. Model Training
8.3.6.2. Hyperparameter Tuning
8.3.6.3. Classification Model Evaluation
8.3.7. Events Detection Component
8.3.8. Spatio-Temporal Extractor Component
8.3.8.1. Text, Hashtag and Username
8.3.8.2. Tweets Geo Attributes
8.3.8.3. User Profile
8.3.9. Reporting and Visualisation Component
8.3.10. External and Internal Validation Component
8.4. Analysis and Results
8.4.1. Detected Events
8.4.1.1. Validation of Detected Events
8.4.1.2. Spatial Analysis
8.4.1.3. Spatio-Temporal Analysis
8.4.2. Evaluation: Tweet Filtering Classifiers
8.4.3. Evaluation: Event Classifiers
8.5. Conclusion
References
9. Cyberphysical Data Analytics Platforms
9.1. Introduction
9.2. Smart Territory Platforms and the Edge Computing Approach
9.2.1. Smart City Vertical Markets and Tools
9.3. Deepint.net: A Platform for Smart Territories
9.3.1. Platform Architecture
9.4. Case Study
9.4.1. Pareto Optimal Location Algorithm
9.4.2. Implementation with Deepint.net
9.5. Conclusion
References
10. Crowd Detection Platforms
10.1. Introduction
10.2. Smart Cities
10.2.1. Smart Cities as a Platform: Verticals and Domains of Smart Cities
10.3. A Platform for Smart Cities
10.4. A Case Study: Melbourne
10.4.1. Input Data
10.4.2. Crowd Detection Method
10.4.3. Face Recognition Unit
10.4.4. Regression Unit
10.4.5. Using Deepint.net to Construct a Solution
10.5. Results
10.5.1. Limitations
10.6. Conclusion
References
11. City-as-a-Platform
11.1. Introduction
11.2. Methodology
11.3. Results
11.3.1. Knowledge-based Urban Development and Smart Cities
11.3.2. Smart Urban Governance
11.3.3. Digital E-government Platforms
11.4. City-as-a-Platform
11.4.1. The Evolution of City-as-a-Platform
11.4.2. Opportunities and Challenges for the Development Based on Collective Knowledge in City-as-a-Platform
11.5. Conclusion
References
12. City as a Sensor for Platform Urbanism
12.1. Introduction
12.2. Methodology
12.3. Results
12.4. Discussion
12.5. Conclusion
Appendix
References
Afterword
Index