Final Report: Taming Twitter: Using Social Media Networks to Identify Deviant Behavior

Abstract

We propose a statistical analysis and data collection framework to identify actors in social media networks who are likely to engage in non-normative or deviant behaviors (specifically, driving under the influence of alcohol or use of marijuana) or have a non-normative attribute (specifically, being obese). We focus on Twitter users reports of behaviors, via the text of their Tweets, and information about their (online) Twitter social network.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 07, 2016
Accession Number
AD1200942

Entities

People

  • Ali Shojaie
  • Hedwig Lee
  • Tyler H. McCormick

Organizations

  • University of Washington

Tags

Communities of Interest

  • Human Systems
  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Abstracts
  • Birds
  • Communities
  • Community Relations
  • Drug Users
  • Dynamics
  • Governments
  • Machine Learning
  • Media
  • Social Media
  • Social Networking Services
  • Social Networks
  • Social Sciences
  • Standards
  • Statistical Analysis
  • Statistics
  • Students
  • Time Intervals

Fields of Study

  • Computer science

Readers

  • Agent-Based Social Robotics and Mobile-Assisted Learning in Virtual Environments.
  • Team-Based Human-Centered Cognitive Task Decision Making and Information Performance.