In this paper, a team of US researchers mined opinions on homeopathy for COVID-19 expressed on Twitter. Their investigation was conducted with a dataset of nearly 60K tweets collected during a seven-month period ending in July 2020. The researchers first built text classifiers (linear and neural models) to mine opinions on homeopathy (positive, negative, neutral) from tweets using a dataset of 2400 hand-labeled tweets obtaining an average macro F-score of 81.5% for the positive and negative classes. The researchers applied this model to identify opinions from the full dataset.

The results show that the number of unique positive tweets is twice that of the number of unique negative tweets; but when including retweets, there are 23% more negative tweets overall indicating that negative tweets are getting more retweets and better traction on Twitter. Using a word shift graph analysis on the Twitter bios of authors of positive and negative tweets, the researchers observed that opinions on homeopathy appear to be correlated with political/religious ideologies of the authors (e.g., liberal vs nationalist, atheist vs Hindu).

The authors drew the following conclusions: to our knowledge, this is the first study to analyze public opinions on homeopathy on any social media platform. Our results surface a tricky landscape for public health agencies as they promote evidence-based therapies and preventative measures for COVID-19.

I am not clear on how to interpret this study. What does it show and why is it important? The authors state this:

… our study cannot lead to meaningful conclusions about homeopathy’s overall online landscape. We also enforced the English language constraint while analyzing the tweets which excludes the views and opinions of all the non-English speaking users, who constitute an overwhelming majority of the world’s population. However, our effort is a first step in the direction of examining the support for alternative medicines especially for homeopathy which has not been studied in the past. At least on Twitter, our findings indicate that negative opinions are gaining more traction in the context of COVID-19.

Opinions expressed on Twitter are influenced by an array of entirely different factors many of which are unpredictable or even unknown. Therefore, I am unsure what to make of these findings. Perhaps some of my readers have an idea?

6 Responses to Homeopathy for COVID: opinions expressed on Twitter

  • Textual analysis of tweets?! And then you report on their study! Showing when you get Meta enough on a subject, it becomes very thorough bullsh!t.
    Time would have been better spent actually experiencing homeopathy directly either as a treatment or in a homeopathic proving.

  • I am aware that you have been quite active on Twitter yourself. May I ask if you have considered leaving Twitter & moving to Mastodon due to the recent policy changes by Elon Musk? For me it was time to move and close my Twitter account when Musk recently twittered „My pronouns are Prosecute/Fauci”.
    Would be great if you would join, the Mastodon is far more constructive.

    • I am thinking about it

    • I know quite a few people who have moved their accounts to Mastodon, some quietly, some with a highly-vocal flounce.

      They’ve all come back.

      Twitter, for all its faults, is still a fantastic and vibrant platform. Mastodon is ridiculously clunky.

      • Well, Lenny, now you know at least one person who will not come back to Twitter – definitely not as long as it belongs to Musk.

        Are you not concerned that Musk now even started banning critical journalists (acc. to Jack Sweeney e.g. himself, Donnie O Sullivan – CNN, Ryan Mac – NYTimes, Matt Binder – Mashable, Arron Rupar, Drew Harwell – Washington Post, from his “free speech” platform, but instead spreads antiscientific conspiracies & invites right-wing trolls (sorry, I ment to say the former US president…) back on?
        I disagree that Twitter is a fantastic platform and one should keep in mind that it´s the users who generate the content – that Musk profits of.
        I disagree as well that Mastodon is “ridiculously clunky”. Until now it runs just fine. Maybe the problems that you have experienced are related to the server that you chose for your Mastodon account.
        It is of course somewhat “more quiet”, compared to Twitter, because no almighty algorithm tells you what posts you are supposed to read.
        If you spend some time with looking, you will find great content and can have civilized and productive conversations.

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Subscribe via email

Enter your email address to receive notifications of new blog posts by email.

Recent Comments

Note that comments can be edited for up to five minutes after they are first submitted but you must tick the box: “Save my name, email, and website in this browser for the next time I comment.”

The most recent comments from all posts can be seen here.