ArticlePDF Available

Comparing Online Community Structure of Patients of Chronic Diseases

Authors:
Hanuma Teja Maddali
Hanuma Teja Maddali
Hanuma Teja Maddali
  • This person is not on ResearchGate, or hasn't claimed this research yet.
Peter Gloor at Massachusetts Institute of Technology
Peter Gloor
Peter Margolis at Cincinnati Children's Hospital Medical Center
Peter Margolis
Download full-text PDF
Read full-text
Download citation

Abstract

In this paper we compare the social network structure of people talking about Crohn's disease, Cystic Fibrosis, and Type 1 diabetes on Facebook and Twitter. We find that the Crohn's community's contributors are most emotional on Facebook and Twitter and most negative on Twitter, while the T1D community's communication network structure is most cohesive.
Content uploaded by Peter Margolis
Author content
All content in this area was uploaded by Peter Margolis on Jul 23, 2015
Content may be subject to copyright.
PROCEEDINGS COINs15
COMPARING ONLINE COMMUNITY STRUCTURE OF PATIENTS OF CHRONIC
DISEASES
Hanuma Teja Maddali, Peter A. Gloor, Peter A. Margolis
MIT CCI, Cincinnati Children’s Medical Center
Cambridge USA, Cincinnati USA
hmaddali@mit.edu, pgloor@mit.edu, Peter.Margolis@cchmc.org
ABSTRACT
In this paper we compare the social network structure
of people talking about Crohn’s disease, Cystic
Fibrosis, and Type 1 diabetes on Facebook and
Twitter. We find that the Crohn’s community’s
contributors are most emotional on Facebook and
Twitter and most negative on Twitter, while the T1D
community’s communication network structure is
most cohesive.
INTRODUCTION
Social media has become a major means of
communication for patients of chronic diseases; to
stay in touch with each other, find support and learn
about novel treatments to better cope with their
illness. In particular, Facebook has become a major
channel for community activation and peer group
support. In earlier work we found that while patients
of Crohn’s disease actively participated on Facebook
discussions by posting comments, they were
surprisingly unconnected by not “friending” each
other on Facebook (Gloor et al. 2010). In this project
we build on this earlier work by extending the focus
comparing Facebook pages on different chronic
illnesses, and also looking at how patients and other
stakeholders talk about the same chronic diseases on
Twitter.
In this first analysis we focus on Facebook groups
and Tweets about “Crohn’s”, “T1D” and “Cystic
Fibrosis”. The Condor 3.1 toolkit was used for
network and content analysis.
ANALYZING FACEBOOK PAGES
Facebook pages are an excellent source of
ethnographic information since they are public and
accessible through an API. Because they are usually
the official pages of organizations, they are more
likely to be moderated compared to Facebook groups,
thus also containing less spam. We found 517
Facebook pages about cystic fibrosis, 275 groups
about type 1 diabetes, and 587 groups about Crohn’s
disease.
Table 1 lists the key statistics of the top 4 Facebook
pages for each of the three chronic diseases. Crohns
is the most active, as it has gathered close to 10,000
messages in just seven months.
Chronic
Disease Facebook Page Name Number of Likes Actors Message
s
Data time
range
Cystic
Fibrosis
Cystic Fibrosis Foundation 188194
4302 5669
Sep 23, 2011
to
Nov 28, 2014
Cystic Fibrosis Trust 64527
CysticFibrosis.com 17567
Cystic Fibrosis Canada 9080
Type 1
Diabetes
Type 1 Diabetes 37643
3906 9217
Jan 18, 2010
to
Nov 28, 2014
Cure Type 1 Diabetes 8636
I hate Diabetes (type 1) 6422
Type 1 Diabetes Awareness 4960
Crohns
Crohn’s and Colitis UK 90989
6143 9836
May 1, 2014
to
Nov 28, 2014
CCFA - Crohn's & Colitis Foundation of
America 89481
Crohn's & Colitis Awareness 30265
Living with Crohn's Disease: Healthline 17451
Table 1: Statistics of top 4 Facebook pages for
each of Crohn’s, T1D and cystic fibrosis
It appears that the official patient organizations of
Cystic Fibrosis and Crohn’s are doing a better job
activating patients on Facebook compared to T1D, as
they are collecting between 90,000 and 190,000 likes,
while the T1D top pages are “unofficial” pages with
much lower numbers of likes.
Figure 1: Combined network structure of three
patient communities of top 4 FB pages
Figure 1 shows the network created by the “walls” of
the Facebook pages, with a link between two actors if
one responded to a wall post of another actor. The
central node for each of the clusters in figure 1 is the
Facebook page. The connecting nodes between the
pages are people posting on more than one Facebook
page. As figure 1 shows, there are people posting
about more than one disease, for instance both about
Crohn’s and Cystic Fibrosis. Figure 2 lists the key
statistics.
Figure 2: Key network metrics of 3 disease groups on
Facebook
The T1D Facebook pages are the most centralized
and have the highest density. This suggests that a few
people might dominate the discussion, also acting as
bridges between the different T1D groups – this is
also visible in the graph in figure 1. The largest
Crohn’s and Cystic Fibrosis groups are operated by
official patient organizations, which might lead to
wider and less centralized communication with
people sticking to communicating on the same page.
T1D has the most negative sentiment on Facebook,
while Crohn’s is the most emotional, and Cystic
Fibrosis posts are using the most complex language.
ANALYZING TWITTER
Figure 3 illustrates the retweet network for the week
Nov. 23 to Nov. 30, 2014. Each node in the network
is a person, a connecting line means that one actor
mentioned another one in a tweet, or retweeted a
tweet by the other actor. As figure 3 shows, most
tweets are made into the void, i.e. they do not trigger
any reaction. Each of the three disease twitterers has
a connected component, which is most dense for
T1D, similar to the Facebook pages. There is also
some people acting as connectors between the
different disease groups, tweeting about two different
diseases. The most central tweeters are a mix of
individual patient activists, healthcare vendors, and
patient organizations.
As figure 4 illustrates, Crohn’s patients have the most
negative sentiment, and the highest emotionality on
Twitter. Crohn’s tweeters are the most responsive
(lowest ART), and also have the most similar
tweeting contribution pattern (lowest variance in
contribution index AWVCI) (Gloor et al. 2014).
T1D$
Cys(c$Fibrosis$
Crohn’s$
Figure 3: Twitter Network about 3 chronic diseases
!" !#$" !#%" !#&" !#'" !# (" !#)"
*+,-./,"
012324.5678"
*+,-./,"
9,431,47"
:8;3:"<=-2;6;"
>$?"
:-2@4;"
0" 0.2" 0.4" 0.6" 0.8" 1" 1.2" 1.4" 1.6" 1.8"
Average"Group"ART"[h]"
AWVCI"
Average"Group"Nudges"un@l"
responses"[h]"
Groupd"Nudges"Variance"un@l"
responses"[h]"
cys@c"fibrosis"
T1D"
crohns"
Figure 4: Key network metrics of 3 disease groups on
Twitter
CONCLUSIONS
In this early study we have shown that stakeholder’s
in Crohn’s, which as a disease might appear “out of
the blue” in the life of a patient are more emotional
and negative than patients of Cystic Fibrosis, who
have the disease since birth and are focused on
creating and maintaining a long-term survival
ecosystem.
REFERENCES
Gloor, P. Grippa, F. Borgert, A. Colletti, R. Dellal, G.
Margolis, P. Seid, M. (2011) Towards Growing a
COIN in a Medical Research Community. , Procedia
- Social and Behavioral Sciences, 26, Proceedings
COINs 2010, Savannah GA, Oct 7-9, 2010
Gloor, P. A., Almozlino, A., Inbar, O., Lo, W., &
Provost, S. (2014). Measuring Team Creativity
Through Longitudinal Social Signals. arXiv preprint
arXiv:1407.0440.
... Patients with IBD tend to be more emotional and negative than patients with other chronic conditions [49]. They usually express a negative sentiment when they talk about the disease and its symptoms but positively address the diets and drugs that help manage them [48]. ...
... Unlike previous research related to patients' sentiments on Twitter [48][49][50], we focused our research on entity sentiment rather than the sentiment of the entire tweet. By analyzing patients' sentiments toward specific keywords related to nutrition and fitness, we uncovered the sentiments of certain lifestyles that influence the disease. ...
... In the second stage of the study, tweets of patients with IBD were collected to investigate the different lifestyles they implemented to deal with their disease and assess these lifestyles' effectiveness. Unlike previous research on patients' sentiments on Twitter [48][49][50], we focused our research on entity sentiment for specific words rather than the entire tweet's sentiment. We suggested a novel approach by considering entity sentiment analysis to obtain patients' sentiments toward the different nutrition and fitness-based solutions they try. ...
Identifying Patients on Twitter and Learning from Their Personal Experience: The Case of IBD (Preprint)
Article
Full-text available
  • Mar 2021
  • J MED INTERNET RES
Background Patients use social media as an alternative information source, where they share information and provide social support. Although large amounts of health-related data are posted on Twitter and other social networking platforms each day, research using social media data to understand chronic conditions and patients’ lifestyles is limited. Objective In this study, we contributed to closing this gap by providing a framework for identifying patients with inflammatory bowel disease (IBD) on Twitter and learning from their personal experiences. We enabled the analysis of patients’ tweets by building a classifier of Twitter users that distinguishes patients from other entities. This study aimed to uncover the potential of using Twitter data to promote the well-being of patients with IBD by relying on the wisdom of the crowd to identify healthy lifestyles. We sought to leverage posts describing patients’ daily activities and their influence on their well-being to characterize lifestyle-related treatments. Methods In the first stage of the study, a machine learning method combining social network analysis and natural language processing was used to automatically classify users as patients or not. We considered 3 types of features: the user’s behavior on Twitter, the content of the user’s tweets, and the social structure of the user’s network. We compared the performances of several classification algorithms within 2 classification approaches. One classified each tweet and deduced the user’s class from their tweet-level classification. The other aggregated tweet-level features to user-level features and classified the users themselves. Different classification algorithms were examined and compared using 4 measures: precision, recall, F1 score, and the area under the receiver operating characteristic curve. In the second stage, a classifier from the first stage was used to collect patients' tweets describing the different lifestyles patients adopt to deal with their disease. Using IBM Watson Service for entity sentiment analysis, we calculated the average sentiment of 420 lifestyle-related words that patients with IBD use when describing their daily routine. Results Both classification approaches showed promising results. Although the precision rates were slightly higher for the tweet-level approach, the recall and area under the receiver operating characteristic curve of the user-level approach were significantly better. Sentiment analysis of tweets written by patients with IBD identified frequently mentioned lifestyles and their influence on patients’ well-being. The findings reinforced what is known about suitable nutrition for IBD as several foods known to cause inflammation were pointed out in negative sentiment, whereas relaxing activities and anti-inflammatory foods surfaced in a positive context. Conclusions This study suggests a pipeline for identifying patients with IBD on Twitter and collecting their tweets to analyze the experimental knowledge they share. These methods can be adapted to other diseases and enhance medical research on chronic conditions.
View
... Whilst there are descriptive accounts of online communities of people living with chronic disease, little is known of the properties of these communities and how they function and evolve over time [26,27]. Given that social media and adjacent technologies are a complex and fast-changing phenomenon, there is a need for continuous research on the dimensions of affordances, affective forces and agency provided in different online platforms and the complex ways participants are engaging with each other in these sites and contributing to health information or disease-management practice. ...
A call for better understanding of social media in surveillance and management of noncommunicable diseases
Article
Full-text available
  • Dec 2021
  • Health Res Pol Syst
Using social media for health purposes has attracted much attention over the past decade. Given the challenges of population ageing and changes in national health profile and disease patterns following the epidemiologic transition, researchers and policy-makers should pay attention to the potential of social media in chronic disease surveillance, management and support. This commentary overviews the evidence base for this inquiry and outlines the key challenges to research laying ahead. The authors provide concrete suggestions and recommendations for developing a research agenda to guide future investigation and action on this topic.
View
... However, most empirical findings show that hospitals mainly communicate only unidirectional with these groups (Vanzetta et al. 2014). Cases on how hospitals could use feedback from social media channels are already known from network analyses in medical research (e.g., Gloor et al. 2016). Such analyses can also provide useful insights relevant for other internal stakeholders in hospitals. ...
Collaborative Innovation Networks: Latest Insights from Social Innovation, Education, and Emerging Technologies Research
Book
  • Jul 2019
Collaborative innovation networks are cyberteams of motivated individuals, and are self-organizing emergent social systems with the potential to promote health, happiness and individual growth in real-world work settings. This book describes how to identify and nurture collaborative innovation networks in order to shape the future working environment and pave the way for health and happiness, and how to develop future technologies to promote economic development, social innovation and entrepreneurship. The expert contributions and case studies presented also offer insights into how large corporations can creatively generate solutions to real-world problems by means of self-organizing mechanisms, while simultaneously promoting the well-being of individual workers. The book also discusses how such networks can benefit startups, offering new self-organizing forms of leadership in which all stakeholders are encouraged to collaborate in the development of new products.
View
... Interests have also grown towards the analysis of the social mechanism and dynamics inside these patients communities. For example in [15] the authors compare Facebook pages on different chronic illnesses, and also looking at how patients and other stakeholders talk about the same chronic diseases on Twitter, while in [20] an evolutionary metaheuristics approach has been used in order to identify communities or subsets of user in a Facebook group of patients. ...
A combined approach for the analysis of support groups on Facebook - the case of patients of hidradenitis suppurativa
Article
Full-text available
Hidradenitis Suppurativa (HS), also known as Acne Inversa, is a chronic, underdiagnosed, often debilitating and painful disease that affects the folds of the skin. It has a considerable negative impact on the quality of life and on the emotional well-being. In this paper we discuss some results obtained by applying automatic Emotion Detection and Social Network Analysis techniques on the Facebook group of the Italian patients’ association (Inversa Onlus). In particular, we analyze the patients’ emotional states, as expressed by the posts and comments published from 2009 to 2017, and how these emotions are influenced by different social network factors, such as interactions and friendships in the group, during the observed years.
View
What Are IBD Patients Talking About on Twitter?
Chapter
  • Jan 2021
In recent years, social networking sites and online communities have served as alternate information sources for patients, who use social media to share health and treatment information, learn from each other’s experiences, and provide social support. This research aimed to investigate what patients with Inflammatory Bowel Disease (IBD) are talking about on Twitter and to learn from the experimental knowledge of living with the disease they share online. We collected tweets of 337 IBD patients who openly tweeted about their disease on Twitter and used the Natural Language Understanding (NLU) module by IBM Cloud to apply category classification and keywords extraction to their tweets. To evaluate the results, we suggested a method for sampling the general population of Twitter users and forming a control group. We found statistically significant differences between the thematic segmentations of the patients and those of random Twitter users. We identified keywords that patients frequently use in the contexts of health, fitness, or nutrition, and obtained their sentiment. The results of the research suggest that the personal information shared by IBD patients on Twitter can be used to understand better the disease and how it affects patients’ lives. By leveraging posts describing patients’ daily activities and how they influence their wellbeing, we can derive complementary knowledge about the disease that is based on the wisdom of the crowd.
View
Measuring Team Creativity Through Longitudinal Social Signals
Article
Full-text available
  • Jul 2014
Research into human dynamical systems has long sought to identify robust signals for human behavior. We have discovered a series of social network-based indicators that are reliable predictors of team creativity and collaborative innovation. We extract these signals from electronic records of interpersonal interactions, including e-mail, and face-to-face interaction measured via sociometric badges. The first of these signals is Rotating Leadership, measuring the degree to which, over time, actors in a team vary in how central they are to team's communication network's structure. The second is Rotating Contribution, which measures the degree to which, over time, actors in a team vary in the ratio of communications they distribute versus receive. The third is Prompt Response Time, which measures, over time, the responsiveness of actors to one another's communications. Finally, we demonstrate the predictive utility of these signals in a variety of contexts, showing them to be robust to various methods of evaluating innovation.
View
Towards Growing a COIN in a
  • Nov 2010
  • P Margolis
  • M Seid
Margolis, P. Seid, M. (2011) Towards Growing a COIN in a Medical Research Community., Procedia -Social and Behavioral Sciences, 26, Proceedings COINs 2010, Savannah GA, Oct 7-9, 2010
Towards Growing a COIN in a
  • Oct 2010
  • P Gloor
  • F Grippa
  • A Borgert
  • R Colletti
  • G Dellal
  • P Margolis
  • M Seid
Gloor, P. Grippa, F. Borgert, A. Colletti, R. Dellal, G. Margolis, P. Seid, M. (2011) Towards Growing a COIN in a Medical Research Community., Procedia -Social and Behavioral Sciences, 26, Proceedings COINs 2010, Savannah GA, Oct 7-9, 2010
  • Jan 2014
  • P A Gloor
  • A Almozlino
  • O Inbar
  • W Lo
  • S Provost
Gloor, P. A., Almozlino, A., Inbar, O., Lo, W., & Provost, S. (2014). Measuring Team Creativity Through Longitudinal Social Signals. arXiv preprint arXiv:1407.0440.