Predict Email Success Based on Text Content

Email marketing works as a top channel to generate leads for many businesses. The marketing automation platforms are part of this strategy and can improve the success of email campaigns. Many of these platforms use subject line tools to predict if an email will be opened or not, as a success metric. However, the text content is unused. Thus, this work proposes to predict the likelihood of a user clicking the Call to Action button of an email based on the content. We implement our proposal in a real-case scenario of corporate communication emails from a private university in Mexico. After building a machine learning model, the results were promising and validated our proof-of-concept. We consider the results relevant for further investigation around other ways to improve the success of an email using the text content, and this model could be reliable in most campaigns and could be used to determine which words influence the click rate metric the most.