Tutorial: Analyzing Twitter for Public Health Research (extra registration required)

Nicholas Genes* Michael Chary*
Nicholas Genes*, Icahn School of Medicine at Mount Sinai, New York, United States
Michael Chary*, Icahn School of Medicine at Mount Sinai, New York, United States
Alex F. Manini, Icahn School of Medicine at Mount Sinai, New York, United States

Track: Research
Presentation Topic: Public (e-)health, population health technologies, surveillance
Presentation Type: 4-hr Tutorial Proposal
Submission Type: Single Presentation

Building: Sheraton Maui Resort
Room: Tutorial (Kula)
Date: 2014-11-12 01:00 PM – 05:00 PM
Last modified: 2014-09-04

If you are the presenter of this abstract (or if you cite this abstract in a talk or on a poster), please show the QR code in your slide or poster (QR code contains this URL).


Background: Analysis of social media can serve as a powerful tool for research in a variety of health disciplines. Twitter, with its popularity, frequent engagement, public messaging, open API, and rich metadata, is a compelling platform for study. To date, most analyses of tweets are imprecise or opaque, using algorithms better suited to marketers instead of scholars. A sound analysis of social media rests on the successful application, in tandem, of concepts from linguistics, mathematics, and computer science.

Objectives: By the end of this 4-hour session, participants will be able to 1) understand the technical requirements for automated Twitter API queries, 2) write their own queries of Twitter content, and metadata such as user profile details or location, 3) collect and analyze the JSON search results, 4) use Python’s Natural Language Toolkit (NLTK) for basic linguistic analysis and clustering analyses, and 5) make statistically sound inferences from those analyses.

Overview: Participants should bring a laptop (preferably a MacBook) to get the full benefit of the hands-on demonstrations. The tutorial instructors will contact participants who sign up in advance, with a user-friendly guide that introduces the command line and walks users through the installation of necessary software packages and registration on GitHub. In this tutorial, users will quickly begin to collect publicly available information from Twitter’s streaming API, by modifying our prepared templates for their own research interests. They will apply their own analyses, under our guidance, and go home with a clear plan on how to collect sufficient data to produce meaningful statistical inferences on the collected data.

About the organizers: The tutorial will be led by three physician-scientists with several peer-reviewed publications regarding the analysis of social media for medical applications, as well as additional peer-reviewed and lay publications on the role of the internet and IT on healthcare. The three of us have overlapping but diverse interests across a range of Medicine 2.0 disciplines and can provide close guidance to participants with troubleshooting, research techniques, and statistical analyses.

This is a preconference event. Either register by choosing the tutorial as additional option when you register for the Medicine 2.0 Malaga conference, or register separately via Eventbrite.

Medicine 2.0® is happy to support and promote other conferences and workshops in this area. Contact us to produce, disseminate and promote your conference or workshop under this label and in this event series. In addition, we are always looking for hosts of future World Congresses. Medicine 2.0® is a registered trademark of JMIR Publications Inc., the leading academic ehealth publisher.
Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.