You are previewing Twitter: A Digital Socioscope.
O'Reilly logo
Twitter: A Digital Socioscope

Book Description

How can Twitter data be used to study individual-level human behavior and social interaction on a global scale? This book introduces readers to the methods, opportunities, and challenges of using Twitter data to analyze phenomena ranging from the number of people infected by the flu, to national elections, to tomorrow's stock prices. Each chapter, written by leading domain experts in clear and accessible language, takes the reader to the forefront of the newly emerging field of computational social science. An introductory chapter on Twitter data analysis provides an overview of key tools and skills, and gives pointers on how to get started, while the case studies demonstrate shortcomings, limitations, and pitfalls of Twitter data as well as its advantages. The book will be an excellent resource for social science students and researchers wanting to explore the use of online data.

Table of Contents

  1. Cover
  2. Half title
  3. Title page
  4. Imprints page
  5. Contents
  6. Contributors
  7. Preface
  8. Introduction
    1. Opportunities and Challenges for Online Social Research
    2. Hard Science
    3. The Social Telescope
    4. Research Applications
      1. Social Networks, Contagion, and Diffusion
      2. Collective Action and Social Movements
    5. Challenges
      1. The Privacy Paradox
      2. Measurement Issues
      3. Is the Online World a Parallel Universe?
      4. Methods, Skills, and Training
    6. Conclusion
  9. 1 Analyzing Twitter Data
    1. 1. Introduction
      1. 1.1. Twitter API Types
        1. 1.1.1. Twitter Applications
        2. 1.1.2. Open Authentication
    2. 2. Aggregating Twitter Data
      1. 2.1. Forms of Twitter Data
        1. 2.1.1. Content
        2. 2.1.2. Social Networks
        3. 2.1.3. User Profiles
        4. 2.1.4. Searching Tweets
        5. 2.1.5. Data Response Format
    3. Listing 1.1
    4. 3. Curating Twitter Data
      1. 3.1. Enriching Twitter Data
        1. 3.1.1. Tokenization and Part of Speech Tagging
      2. 3.1.2. Named Entity Recognition
      3. 3.1.3. Recovering Shortened URLS
      4. 3.1.4. Location Identification
      5. 3.2. User Profiling
      6. 3.3. Constructing Networks from Twitter Data
      7. 3.3.1. Retweet Networks
      8. 3.3.2. User Mentions Networks
      9. 3.3.3. Follow Networks
      10. 3.3.4. Content Networks
      11. 3.3.5. Data Storage and Retrieval
      12. 3.3.6. Example 1: MongoDB
    5. Listing 1.2
      1. Section
        1. 3.3.7. Example 2: Pig
    6. Listing 1.3
    7. 4. Investigating Research Problems Using Twitter Data
      1. 4.1. How Do We Assess the Quality of Data Obtained Through the Streaming APIs?
        1. 4.1.1. Finding Bias in the Streaming API
        2. 4.1.2. Finding Bias Without the Firehose
      2. 4.2. Sentiment Analysis of Tweets
      3. 4.3. Detecting Events in Twitter Data
    8. 5. Tools for Twitter Data Collection and Analysis
    9. Acknowledgments
  10. 2 Political Opinion
    1. 1. Introduction
    2. 2. Mining the Twittersphere for Public Opinion
    3. 3. Limitations of Previous Methods to Mine Twitter Political Opinion
      1. 3.1. Limitations Due to Approaching Twitter Data from a Pollster’s Perspective
      2. 3.2. Limitations Due to the Different Sources of Bias in Twitter
      3. 3.3. Limitations Due to Common Approaches to Automated Content Analysis
      4. 3.4. Limitations Due to Misinformation and Provenance of Tweets
      5. 3.5. Limitations of Common Approaches to Twitter-based Electoral Forecasting
    4. 4. Implications and Future Work
  11. 3 Socioeconomic Indicators
    1. 1. Introduction
    2. 2. Mining Twitter for Socioeconomic Indicators
      1. 2.1. Unemployment Rate
      2. 2.2. Consumer Confidence
      3. 2.3. Social Mood
      4. 2.4. Investor Sentiment
      5. 2.5. Twitter Network Features and Financial Markets
    3. 3. The Applications of Other Big Data Sources in Economic Research
      1. 3.1. Search Volume Data, Financial Market, and GDP
      2. 3.2. Phone Communication Data and Economic Development
    4. 4. Challenges and Future Research
  12. 4 Hyperlocal Happiness from Tweets
    1. 1. Introduction
    2. 2. Twitter Happiness
    3. 3. Crawling, Cleaning, and Mapping
      1. 3.1. Crawling
      2. 3.2. Cleaning
      3. 3.3. Georeferencing
    4. 4. Modeling the Use of Language
      1. 4.1. Use of Language
      2. 4.2. Sentiment
      3. 4.3. Topic Modeling
    5. 5. Case Study: Hyperlocal Happiness
      1. 5.1. Main Findings
      2. 5.2. Implications
    6. 6. Discussion
      1. 6.1. Causality
      2. 6.2. Sample Representativeness
      3. 6.3. Beyond USA or UK
    7. 7. Conclusion
  13. 5 Public Health
    1. 1. Introduction
    2. 2. Twitter – Early Warning and Preparedness
      1. 2.1. Twitter Predicts a Pandemic – a Case Study
    3. 3. Twitter – Risk Communication and Health News Dissemination
      1. 3.1. Twitter Spreads the News of the Pandemic – a Case Study
    4. 4. Twitter – Health Sentiment and Public Language
      1. 4.1. Twitter Gets You Vaccinated: A Case Study
    5. 5. Discussion
      1. 5.1. User Demographics
      2. 5.2. Location Awareness
      3. 5.3. Integration of Multiple Data Sources
      4. 5.4. Twitter – Personalized Health Information and Privacy
  14. 6 Disaster Monitoring
    1. 1. Introduction
      1. 1.1. Motivation
      2. 1.2. The Disaster Lifecycle
      3. 1.3. Managing Emergencies and Disasters
      4. 1.4. Situation Awareness
      5. 1.5. Current Systems
    2. 2. Challenges
      1. 2.1. Managing Tweet Volume
      2. 2.2. Determining Location
      3. 2.3. Trustworthy Tweets
      4. 2.4. Event Detection
      5. 2.5. Seeking Help
      6. 2.6. Community Engagement
    3. 3. Discussion
      1. 3.1. Future Opportunities
      2. 3.2. Limitations
      3. 3.3. Future Work
  15. Index