Marketers and researchers recognize the importance and impact on consumer behavior of marketer-generated content (MGC) in social media channels. In this study, the authors present a method to classify MGC using a combination of unsupervised and supervised machine learning. They gather a large data set of posts from Facebook, Instagram, and Twitter and use a time-series model (panel-data vector autoregression) to demonstrate how MGC can be used to explain average toxicity on the part of users. They contribute to the field by examining what types of MGC lead to toxic comments and how these toxic comments impact product usage. The authors find that MGC that demonstrates the quality of products and MGC that is aimed at creating a sense of belonging to a group are more likely to increase average toxicity. Furthermore, the authors find that higher average toxicity in social media communities leads to an increase in usage of the focal product. Finally, the results contribute to the literature by providing insights on the impact of MGC on product usage.