Psychologically Motivated Text Mining
This work addresses the need for more psychologically grounded text mining techniques to improve social trend analysis and behavior prediction, representing an incremental advance by integrating psychological insights into existing NLP methods.
The authors tackled the problem of identifying metaphorical framing in text to predict human behavior, presenting a method that learns such patterns from large text collections and validating it across three languages with psychological assessments.
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.