Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Monday, March 11, 2019 at 4:00 PM to 4:30 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?


Currently accepted at: Journal of Medical Internet Research

Date Submitted: Oct 30, 2018
Open Peer Review Period: Nov 3, 2018 - Dec 13, 2018
Date Accepted: Apr 26, 2019
(closed for review but you can still tweet)

This paper has been accepted and is currently in production.

It will appear shortly on 10.2196/12610

The final accepted version (not copyedited yet) is in this tab.

Using Twitter to understand the human bowel disease community: an exploratory analysis of key topics

  • Martín Pérez-Pérez; 
  • Gael Pérez-Rodríguez; 
  • Florentino Fdez-Riverola; 
  • Anália Lourenço



Nowadays, the use of social media is part of daily life, with more and more people, including governments and Health organisations, using at least one platform regularly. Social media create the opportunity to interact among large groups of people that share the same interests and suffer the same afflictions. In particular, these channels promote the ability to find and share information about Health and medical conditions.


The goal of this work was to characterise the bowel disease community on Twitter by identifying and geo-locating active users, analysing the external events that motivate the posted content, as well as pin pointing biomedical and scientific topics in order to explore how patients understand, discuss, feel and react to these conditions. To do so, the following questions were answered: which are the main communities and most influential users?; where are the main content providers from?; in what way external events determine the posted content and motivate discussion?; what are the key biomedical and scientific topics under discussion?; how are the topics interrelated in conversations?; and what kind of external sources of information are being promoted?.


To answer the previous questions, a dataset of tweets about bowel disease conditions was collected from February to August, 2018. The textual content, time, location and user information of these tweets were extracted. Missing or incomplete information about the user profiles was completed using different techniques. With the help of an entity recogniser, it was possible to detect a wide number of specialized terms in tweet contents, as well as hyperlinks and hashtags. These information was used to identify and categorize the key topics under discussion. Moreover, with the identified terms and the extracted hashtags it was possible to perform a semantic analysis of the tweets and depict existing conceptual relations. Finally, the information shared among users was inspected.


A final dataset comprising 24,634 tweets from 13,517 different users was analysed. Users were characterized in distinct communities (i.e. bowel disease, nutritional, gluten and food), which are mostly geo-located in the United States. There was an interesting peak of activity during May and June, 2018, just before and after the World IBD Day. Regarding the identified conceptual terms, the most relevant categories were ‘diseases’, ‘treatments’ and ‘compounds’, and the most mentioned terms were ‘irritable bowel syndrome’, ‘diet’ and ‘cannabis’, respectively. Also, the most shared sources of information were related to awareness campaigns and scientific articles.


This work evidences that Twitter is becoming an influential space for online conversations about bowel conditions, including associated symptoms and treatments. Further qualitative and quantitative content analyses hold the potential to support decision-making among Health-related stakeholders, including the planning of new awareness campaigns.


Please cite as:

Pérez-Pérez M, Pérez-Rodríguez G, Fdez-Riverola F, Lourenço A

Using Twitter to understand the human bowel disease community: an exploratory analysis of key topics

Journal of Medical Internet Research. (forthcoming/in press)

DOI: 10.2196/12610


Note: Per the author's request, please log in to view the PDF

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.