Are commercial Tweets Truthful About Loosely Regulated Substance Such as CBD? (Preprint)
UNSTRUCTURED Background: This study analyzes differences in the terms and sentiments regarding CBD expressed by commercial and personal users on Twitter. It demonstrates that in the absence of official clinical trial information, data from social networks can be used by public health and medical researchers to assess public claims about loosely-regulated substances like CBD: for example, by comparing the medical conditions targeted by those selling CBD against the medical conditions patients commonly treat with CBD. Objective: The objective of this study is to provide a framework for public health and medical researchers to use to analyze the consumption and marketing of unregulated substances. Specifically we examined cannabidiol (CBD), which is a substance that is often being presented to the public as medication despite complete evidence of efficacy and safety. Methods: We collected 567,850 tweets by searching Twitter with the Tweepy Python package using the terms CBD and cannabidiol. We trained two binary text classifiers to create two corpora of 156,080 personal use and 158,014 commercial/sales. Using medical, standard, and slang dictionaries, we identified and compared the most frequently occurring medical conditions, symptoms, side effects, body parts, and other substances referenced in both corpora. Results: We found references to medically relevant terms that were unique to either personal or commercial CBD tweet classes, as well as medically relevant terms that were common in both classes. In addition, to assess popular claims about the efficacy of CBD as a medical treatment circulating on Twitter, we performed sentiment analysis via the VADER model on the personal CBD tweets. We calculated the average sentiment scores for both personal and commercial CBD tweets referencing at least one of 17 medical conditions/symptoms, and observed an overall positive sentiment in both personal and commercial CBD tweets. We observed negative sentiment conveyed in personal CBD tweets referencing autism, while noticing it was being marketed multiple times as a treatment of autism within commercial CBD tweets. Conclusion: Our proposed framework provides a tool for public health and medical researchers to analyze the consumption and marketing of unregulated substances on social networks. Our analysis showed that that most users of CBD are satisfied with it in regards to the condition it that it is being advertised for, with the exception of autism.