Natural Language Processing of Auditory Perceptual Experiences: A Content-Analytic Approach

Abstract

ABSTRACT Much research in auditory cognition focuses on quantitative outcome variables that do not fully capture individual differences in how people perceive and remember auditory information. To better account for qualitative aspects of auditory experience, we use topic modeling to analyze 779 written responses to three questions regarding: 1) how people judged similarity between sounds; 2) how people remembered and recognized previously heard sounds; and 3) how people formed impressions of the sounds they heard. Cross-validation showed that 20 topics characterized the similarity responses, 16 characterized the recognition judgments, and 30 characterized people’s impressions. Principal components analysis of the topic distributions identified latent themes within each set of topics and produced component scores on those themes for every respondent. Similarity strategies clustered into three themes: Featural Separation, Impression Formation, and Listening Effort. Recognition strategies clustered into five themes: Featural Irregularity, Contrast, Holistic Processing, Timbral Impressions, and Featural Change. Impressions clustered into two themes: Mechanical Sounds, and Electronic Sounds. Results are analogous to the output of a traditional content analysis – but were produced in a fraction of the time using a replicable methodology that can scale to large datasets. Our work represents a new method for triangulating quantitative, qualitative, and computational methods in auditory research.