Psychologically Motivated Text Mining

TL;DR

This paper introduces a novel text mining method that learns metaphorical framing patterns from large multilingual text collections, leveraging psychological insights to improve understanding of social trends and human decision-making.

Contribution

It presents a new statistical approach to identify metaphorical framing patterns, validated across three languages, bridging psychology and NLP.

Findings

Patterns of metaphorical framing are reliably identified.

The method demonstrates psychological validity across languages.

The approach enhances social trend prediction capabilities.

Abstract

Natural language processing techniques are increasingly applied to identify social trends and predict behavior based on large text collections. Existing methods typically rely on surface lexical and syntactic information. Yet, research in psychology shows that patterns of human conceptualisation, such as metaphorical framing, are reliable predictors of human expectations and decisions. In this paper, we present a method to learn patterns of metaphorical framing from large text collections, using statistical techniques. We apply the method to data in three different languages and evaluate the identified patterns, demonstrating their psychological validity.