# The Language of Dialogue Is Complex

## TL;DR

This paper introduces a machine learning model that automates the measurement of Integrative Complexity in social media texts, enabling large-scale analysis of conflict resolution and perspective-taking.

## Contribution

It presents a novel automated IC classification model that outperforms previous methods and applies it to analyze over 400,000 social media comments at scale.

## Key findings

- Model achieves state-of-the-art performance on unseen data.
- Replicates key findings from prior IC research.
- Enables large-scale social media analysis of complex language.

## Abstract

Integrative Complexity (IC) is a psychometric that measures the ability of a person to recognize multiple perspectives and connect them, thus identifying paths for conflict resolution. IC has been linked to a wide variety of political, social and personal outcomes but evaluating it is a time-consuming process requiring skilled professionals to manually score texts, a fact which accounts for the limited exploration of IC at scale on social media.We combine natural language processing and machine learning to train an IC classification model that achieves state-of-the-art performance on unseen data and more closely adheres to the established structure of the IC coding process than previous automated approaches. When applied to the content of 400k+ comments from online fora about depression and knowledge exchange, our model was capable of replicating key findings of prior work, thus providing the first example of using IC tools for large-scale social media analytics.