Estimating Causal Effects of Tone in Online Debates

06/10/2019
by   Dhanya Sridhar, et al.
0

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.vWe 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/08/2020

Measuring Emotions in the COVID-19 Real World Worry Dataset

The COVID-19 pandemic is having a dramatic impact on societies and econo...
research
08/17/2021

Validating daily social media macroscopes of emotions

To study emotions at the macroscopic level, affective scientists have ma...
research
09/15/2017

And That's A Fact: Distinguishing Factual and Emotional Argumentation in Online Dialogue

We investigate the characteristics of factual and emotional argumentatio...
research
01/24/2023

What Drives Virtual Influencer's Impact?

In the midst of the influencer marketing boom, more and more companies a...
research
10/14/2022

Counterfactual Neural Temporal Point Process for Estimating Causal Influence of Misinformation on Social Media

Recent years have witnessed the rise of misinformation campaigns that sp...
research
10/24/2020

Causal Effects of Linguistic Properties

We consider the problem of estimating the causal effects of linguistic p...
research
05/03/2021

Explaining Outcomes of Multi-Party Dialogues using Causal Learning

Multi-party dialogues are common in enterprise social media on technical...

Please sign up or login with your details

Forgot password? Click here to reset