Men Are from Mars, Women Are from Venus: Evaluation and Modelling of Verbal Associations

TL;DR

This paper analyzes human word associations, examining how response types relate to respondent demographics, and introduces a personalized model that incorporates demographic factors to improve natural language processing tasks.

Contribution

It provides a quantitative analysis of word association types and proposes a novel personalized association model considering demographic variables.

Findings

Correlation between response types and gender/occupation

Differences in syntagmatic and paradigmatic associations

Enhanced NLP models with demographic data

Abstract

We present a quantitative analysis of human word association pairs and study the types of relations presented in the associations. We put our main focus on the correlation between response types and respondent characteristics such as occupation and gender by contrasting syntagmatic and paradigmatic associations. Finally, we propose a personalised distributed word association model and show the importance of incorporating demographic factors into the models commonly used in natural language processing.