A Twitter discourse analysis of negative feelings and stigma related to NAFLD, NASH and obesity

Abstract

Background People with non‐alcoholic fatty liver disease (NAFLD) and non‐alcoholic steatohepatitis (NASH) are stigmatized, partly since ‘non‐alcoholic’ is in the name, but also because of obesity, which is a common condition in this group. Stigma is pervasive in social media and can contribute to poorer health outcomes. We examine how stigma and negative feelings concerning NAFLD/NASH and obesity manifest on Twitter. Methods Using a self‐developed search terms index, we collected NAFLD/NASH tweets from May to October 2019 (Phase I). Because stigmatizing NAFLD/NASH tweets were limited, Phase II focused on obesity (November‐December 2019). Via sentiment analysis, >5000 tweets were annotated as positive, neutral or negative and used to train machine learning–based Natural Language Processing software, applied to 193 747 randomly sampled tweets. All tweets collected were analysed. Results In Phase I, 16 835 tweets for NAFLD and 2376 for NASH were retrieved. Of the annotated NAFLD/NASH tweets, 97/1130 (8.6%) and 63/535 (11.8%), respectively, related to obesity and 13/1130 (1.2%) and 5/535 (0.9%), to stigma; they primarily focused on scientific discourse and unverified information. Of the 193 747 non‐annotated obesity tweets (Phase II), the algorithm classified 40.0% as related to obesity, of which 85.2% were negative, 1.0% positive and 13.7% neutral. Conclusions NAFLD/NASH tweets mostly indicated an unmet information need and showed no clear signs of stigma. However, the negative content of obesity tweets was recurrent. As obesity‐related stigma is associated with reduced care engagement and lifestyle modification, the main NAFLD/NASH treatment, stigma‐reducing interventions in social media should be included in the liver health agenda.

Nonalcoholic fatty liver disease on Twitter: a sentiment analysis

“…Keywords: Nonalcoholic fatty liver disease, NAFLD, Twitter, sentiment analysis Dear Editor, Sentiment analysis is a methodology for analyzing a piece of text in order to investigate sentiments hidden within it (in terms of positive [+1], negative [-1], or neutral [0]) [1] . In health care, the use of sentiment analysis can help in better understanding how individuals talk and feel regarding a specific health topic [2] .…”

“…In the social media era, the use of sentiment analysis is quite useful since social media platforms are specific and natural environments where individuals can share and try to find information such as those on health [2] . To date, there are scarce data [3] regarding the use of sentiment analysis related to nonalcoholic fatty liver disease (NAFLD), which is the most common chronic liver disease worldwide, affecting nearly 30% of adults in general population and up to 70% of individuals with type 2 diabetes [4] .…”

“…Briefly, API is a software intermediary that allows two applications to talk to each other. The standard API of Twitter provides a subset of the current tweets and their metadata [2] . However, it has several limitations [2] .…”

“…The standard API of Twitter provides a subset of the current tweets and their metadata [2] . However, it has several limitations [2] . For instance, the data obtained for every tweet are quite limited, the tweets obtained are a sample of the total tweets, and the number of requests per minute is limited as well [2] .…”

“…However, it has several limitations [2] . For instance, the data obtained for every tweet are quite limited, the tweets obtained are a sample of the total tweets, and the number of requests per minute is limited as well [2] . For each tweet we retrieved the text of the tweet, including any emojis.…”