# Estimating Causal Effects of Tone in Online Debates

## TL;DR

This paper develops a method to estimate the causal impact of reply tones in online debates on subsequent dialogue, addressing confounding factors like ideology and emotion using generative text models.

## Contribution

It introduces a novel approach to control for confounders in causal inference from text, enabling more accurate estimation of tone effects in online discussions.

## Key findings

- Factual and asserting tones influence dialogue dynamics.
- Latent confounder representations reduce bias in causal estimates.
- Method applicable to debates on multiple online platforms.

## Abstract

Statistical methods applied to social media posts shed light on the dynamics of online dialogue. For example, users' wording choices predict their persuasiveness and users adopt the language patterns of other dialogue participants. 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 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.