Understanding Interpersonal Conflict Types and their Impact on Perception Classification

TL;DR

This paper introduces a new dataset and classification method for understanding interpersonal conflict types and their influence on perception, revealing how relationship context affects conflict content and social norm judgments.

Contribution

It presents a novel annotation scheme, a new dataset, and a classifier for predicting perception of actions in conflict situations, with analysis of conflict aspects and participant relationships.

Findings

Conflict content varies based on participant relationships.

Generated conflict clusters are validated by humans.

The classifier effectively predicts perceptions of right or wrong.

Abstract

Studies on interpersonal conflict have a long history and contain many suggestions for conflict typology. We use this as the basis of a novel annotation scheme and release a new dataset of situations and conflict aspect annotations. We then build a classifier to predict whether someone will perceive the actions of one individual as right or wrong in a given situation. Our analyses include conflict aspects, but also generated clusters, which are human validated, and show differences in conflict content based on the relationship of participants to the author. Our findings have important implications for understanding conflict and social norms.