Identifying and characterizing scientific authority-related misinformation discourse about hydroxychloroquine on twitter using unsupervised machine learning

This study investigates the types of misinformation spread on Twitter that evokes scientific authority or evidence when making false claims about antimalarial drug hydroxychloroquine as a treatment for COVID-19. Specifically, we examined tweets generated after former U.S. President Donald Trump retweeted using an unsupervised machine learning approach called biterm topic model is used to cluster into topics based textual similarity. The top 10 from each were content coded three categories related authority: medical endorsements hydroxychloroquine, information support hydroxychloroquine’s use, and comparison group included opposing use. Results show much higher volume featuring use supportive compared accurate updated evidence, misinformation-related propagated longer time frame, majority discourse expressed positive views drug. Metadata accounts found prominent users within more likely have media political affiliation explicitly Trump. Conversely, opposition primarily consisted doctors scientists but had far less influence in discourse. Implications these findings connections social research are discussed, well cognitive mechanisms understanding susceptibility strategies combat via online platforms.