TY  - JOUR
AU  - Homan, Christopher Michael
AU  - Schrading, J Nicolas
AU  - Ptucha, Raymond W
AU  - Cerulli, Catherine
AU  - Ovesdotter Alm, Cecilia
PY  - 2020
DA  - 2020/11/19
TI  - Quantitative Methods for Analyzing Intimate Partner Violence in Microblogs: Observational Study
JO  - J Med Internet Res
SP  - e15347
VL  - 22
IS  - 11
KW  - intimate partner violence
KW  - social media
KW  - natural language processing
AB  - Background: Social media is a rich, virtually untapped source of data on the dynamics of intimate partner violence, one that is both global in scale and intimate in detail. Objective: The aim of this study is to use machine learning and other computational methods to analyze social media data for the reasons victims give for staying in or leaving abusive relationships. Methods: Human annotation, part-of-speech tagging, and machine learning predictive models, including support vector machines, were used on a Twitter data set of 8767 #WhyIStayed and #WhyILeft tweets each. Results: Our methods explored whether we can analyze micronarratives that include details about victims, abusers, and other stakeholders, the actions that constitute abuse, and how the stakeholders respond. Conclusions: Our findings are consistent across various machine learning methods, which correspond to observations in the clinical literature, and affirm the relevance of natural language processing and machine learning for exploring issues of societal importance in social media. 
SN  - 1438-8871
UR  - http://www.jmir.org/2020/11/e15347/
UR  - https://doi.org/10.2196/15347
UR  - http://www.ncbi.nlm.nih.gov/pubmed/33211021
DO  - 10.2196/15347
ID  - info:doi/10.2196/15347
ER  -