Written Goodbyes: How Genre and Sociolinguistic Factors Influence the Content and Style of Suicide Notes

Abstract

The study analyses a novel corpus of 76 freely available English authentic suicide notes (SNs) (letters and social media posts), spanning from 1902 to 2023. By using NLP and corpus linguistics tool, this research aims at decoding patterns of content and style in SNs. In particular, we explore variation in linguistic features in SNs across sociolinguistic factors (age, gender, addressee, time period) and between text type - referred to as genre - (letters vs. online posts). To this end, we use topic models, subjectivity analysis, and sentiment and emotion analysis. Results highlight how both discourse and emotion expression, show differences depending on genre, gender, age group and time period. We suggest a more nuanced approach to personalized prevention and intervention strategies based on insights from computer-assisted linguistic analysis.