Text mining in computational advertising

Computational advertising uses information on web‐browsing activity and additional covariates to select advertisements for display to the user. The statistical challenge is to develop methodology that matches ads to users who are likely to purchase the advertised product. These methods not only involve text mining, but also may draw upon additional modeling related to both the user and the advertisement. This paper reviews various aspects of text mining, including n ‐grams, topic modeling, and text networks, and discusses different strategies in the context of specific business models.