Can Social Ontological Knowledge Representations be Measured Using Machine Learning?

TL;DR

This paper explores how machine learning can quantify personal social ontologies by analyzing term co-occurrences in language, aiming to develop psychometric measures of individual social beliefs.

Contribution

It proposes a novel NLP pipeline to measure social ontological views through term co-occurrence analysis based on social psychology and neuroscience insights.

Findings

Identifies key social concepts for personal social ontology

Develops an NLP pipeline to analyze term usage

Suggests co-occurrence patterns reflect social beliefs

Abstract

Personal Social Ontology (PSO), it is proposed, is how an individual perceives the ontological properties of terms. For example, an absolute fatalist would arguably use terms that remove any form of agency from a person. Such fatalism has the impact of ontologically defining acts such as winning, victory and success in a manner that is contrary to how a non-fatalist would ontologically define them. While both the said fatalist and non-fatalist would agree on the dictionary definition of these terms, they would differ on specifically how they can be brought about. This difference between the two individuals can be induced from their usage of these terms, i.e., the co-occurrence of these terms with other terms. As such a quantification of this such co-occurrence offers an avenue to characterise the social ontological views of the speaker. In this paper we ask, what specific term co-occurrence should be measured in order to obtain a valid and reliable psychometric measure of a persons social ontology? We consider the social psychology and social neuroscience literature to arrive at a list of social concepts that can be considered principal features of personal social ontology, and then propose an NLP pipeline to capture the articulation of these terms in language.