Identifying social isolation themes in NVDRS text narratives using topic modeling and text-classification methods

TL;DR

This study develops NLP-based classifiers to identify social isolation themes in NVDRS narratives, revealing significant associations with demographic factors and aiding in suicide prevention efforts.

Contribution

It introduces a novel NLP approach combining topic modeling and supervised learning to detect social isolation in death narratives, enhancing surveillance capabilities.

Findings

Classifiers achieved an average F1 score of 0.86

Identified 1,198 cases mentioning chronic social isolation

Higher odds of social isolation among men, gay individuals, and divorced persons

Abstract

Social isolation and loneliness, which have been increasing in recent years strongly contribute toward suicide rates. Although social isolation and loneliness are not currently recorded within the US National Violent Death Reporting System's (NVDRS) structured variables, natural language processing (NLP) techniques can be used to identify these constructs in law enforcement and coroner medical examiner narratives. Using topic modeling to generate lexicon development and supervised learning classifiers, we developed high-quality classifiers (average F1: .86, accuracy: .82). Evaluating over 300,000 suicides from 2002 to 2020, we identified 1,198 mentioning chronic social isolation. Decedents had higher odds of chronic social isolation classification if they were men (OR = 1.44; CI: 1.24, 1.69, p<.0001), gay (OR = 3.68; 1.97, 6.33, p<.0001), or were divorced (OR = 3.34; 2.68, 4.19, p<.0001). We found significant predictors for other social isolation topics of recent or impending divorce, child custody loss, eviction or recent move, and break-up. Our methods can improve surveillance and prevention of social isolation and loneliness in the United States.