Twitter in Circulating Transportation Information: A Case Study on Two Cities

Twitter.com, an online social network with nearly 320 million active users and over 500 million tweets per day, has become one of the most popular micro-blogging platforms in the recent years. The users can share their instant thoughts or information on a wide range of topics or interests through 140 characters short messages known as ‘tweets’. Corporations, news agencies, transportation authorities, local governments, airlines and various other agencies use Twitter to share real-time public service information. However, meaningful extraction of information from the large amount of data on Twitter is a great challenge. The prospect of social media for cooperation between citizens and governmental authorities is an evolving issue in theory and practice. This paper examines the promising aspects of using Twitter by the governmental transportation authorities. Based on a dataset of nearly nine thousand official tweets from transportation authorities in two Louisiana major cities, the researchers explored information retrieval aspects of posted official tweets. One year growth of the followers of these official Twitter handles is nearly 48%, which indicates that information distributed through these handles are useful for the followers. The historical tweet frequency indicates the wider use of the official tweets during natural disasters and emergencies. Moreover, this research performed topic modeling on the generated tweets and conducted sentiment analyses on few countermeasures. The results showed mixed sentiments towards these countermeasures. Authorities need to examine negative sentiments more profoundly to improve performance. This research contributes in developing Twitter mining framework, transportation specific senti-lexicon and sentiment score algorithm.

• Supplemental Notes:
  • This paper was sponsored by TRB committee AND20 Standing Committee on User Information Systems.
• Corporate Authors:

  Transportation Research Board

  500 Fifth Street, NW
  Washington, DC  United States  20001
• Authors:
  • Das, Subasish
  • Sun, Xiaoduan
  • Dutta, Anandi
  • Zupancich, Michelle
• Conference:
  • Transportation Research Board 96th Annual Meeting
  • Location: Washington DC, United States
  • Date: 2017-1-8 to 2017-1-12
• Date: 2017

Language

• English

Media Info

• Media Type: Digital/other
• Features: Figures; References; Tables;
• Pagination: 16p
• Monograph Title: TRB 96th Annual Meeting Compendium of Papers

Subject/Index Terms

• TRT Terms: Data collection; Data mining; Information dissemination; Social media; Transportation departments
• Identifier Terms: Twitter
• Geographic Terms: Baton Rouge (Louisiana); New Orleans (Louisiana)
• Subject Areas: Data and Information Technology; Highways; Society;

Filing Info

• Accession Number: 01627721
• Record Type: Publication
• Report/Paper Numbers: 17-03840
• Files: TRIS, TRB, ATRI
• Created Date: Feb 27 2017 5:12PM