Social media is regarded as a means to increase customer engagement, and the use of social media to induce customer engagement is expanding as a major marketing trend of companies in recent years. According to the speech act theory, it is highly likely that not only the content is trying to convey, but also the communication method affects customer engagement. In this context, this study classified the combinations of various linguistic styles contained in the Twitter messages of global brands into classes, and analyzed the relationship between these classes and customer engagement. For empirical analysis, 17,621 tweet messages from six representative global brands were collected. And after analyzing linguistic characteristics using LIWC 2015, an automated text analysis program, we classified the linguistic style combinations of global brand tweet messages through the Latent Class Analysis method. Using Zero-Inflated Negative Binomial regression analysis, the relationship between the class and customer engagement classified through linguistic style combination was analyzed. As results, the linguistic style combinations of global brand tweet messages were divided into 4 classes, and it was found that there was a difference in customer engagement performance according to each class.