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.
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.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the Tenth Italian Conference on Computational Linguistics (CLiC-it 2024): Pisa, Italy, December 4-6, 2024. |
| Editors | Felice Dell'Orletta, Alessandro Lenci, Simonetta Montemagni, Rachele Sprugnoli |
| Publisher | CEUR-WS.org |
| Number of pages | 8 |
| Publication status | E-pub ahead of print - 4 Dec 2024 |
Publication series
| Name | CEUR Workshop Proceedings |
|---|---|
| Publisher | CEUR-WS.org |
| ISSN (Electronic) | 1613-0073 |