Abstract Statistical methods applied to social media posts shed light on the dynamics of online dialogue. For example, users’ wording choices predict their persuasiveness [Tan et al., 2016; Danescu-NiculescuMizil et al., 2012a] and users adopt the language patterns of other dialogue participants [DanescuNiculescu-Mizil et al., 2011; 2012b]. In this paper, we estimate the causal effect of reply tones in debates on linguistic and sentiment changes in subsequent responses. The challenge for this estimation is that a reply’s tone and subsequent responses are confounded by the users’ ideologies on the debate topic and their emotions. To overcome this challenge, we learn representations of ideology using generative models of text. We study debates from 4FORUMS.COM and compare annotated tones of replying such as emotional versus factual, or reasonable versus attacking. We show that our latent confounder representation reduces bias in ATE estimation. Our results suggest that factual and asserting tones affect dialogue and provide a methodology for estimating causal effects from text