From ADHD to SAD: Analyzing the Language of Mental Health on Twitter through Self-Reported Diagnoses

Coppersmith, Glen; Dredze, Mark; Harman, Craig; Hollingshead, Kristy

doi:10.3115/v1/w15-1201

Cited by 274 publications

(284 citation statements)

References 36 publications

Supporting

Mentioning

272

Contrasting

Unclassified

Order By: Relevance

“…We use the entire Twitter history of each user as input to the model, and split it into character 1-to-5-grams, which have been shown to capture more information than words for many Twitter text classification tasks (Mcnamee and Mayfield, 2004;Coppersmith et al, 2015a). We compute the relative frequency of the 5,000 most frequent n-gram features for n ∈ {1, 2, 3, 4, 5} in our data, and then feed this as input to all models.…”

Section: Datamentioning

confidence: 99%

“…We are the first to apply MTL to predict mental health conditions from user content on Twitter -a notoriously difficult task (Coppersmith et al, 2015a;Coppersmith et al, 2015b). 2.…”

Section: Our Contributionsmentioning

confidence: 99%

“…We train our models on a union of multiple Twitter user datasets: 1) users identified as having anxiety, bipolar disorder, depression, panic disorder, eating disorder, PTSD, or schizophrenia (Coppersmith et al, 2015a), 2) those who had attempted suicide (Coppersmith et al, 2015c), and 3) those identified as having either depression or PTSD from the 2015 Computational Linguistics and Clinical Psychology Workshop shared task (Coppersmith et al, 2015b), along with neurotypical gendermatched controls (Twitter users not identified as having a mental condition). Users were identified as having one of these conditions if they stated explicitly they were diagnosed with this condition on Twitter (verified by a human annotator).…”

Section: Datamentioning

confidence: 99%

See 2 more Smart Citations

Multitask Learning for Mental Health Conditions with Limited Social Media Data

Benton¹,

Mitchell²,

Hovy³

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

150

135

View full text Add to dashboard Cite

Language contains information about the author's demographic attributes as well as their mental state, and has been successfully leveraged in NLP to predict either one alone. However, demographic attributes and mental states also interact with each other, and we are the first to demonstrate how to use them jointly to improve the prediction of mental health conditions across the board. We model the different conditions as tasks in a multitask learning (MTL) framework, and establish for the first time the potential of deep learning in the prediction of mental health from online user-generated text. The framework we propose significantly improves over all baselines and single-task models for predicting mental health conditions, with particularly significant gains for conditions with limited data. In addition, our best MTL model can predict the presence of conditions (neuroatypicality) more generally, further reducing the error of the strong feed-forward baseline.

show abstract

Section: Datamentioning

confidence: 99%

“…We are the first to apply MTL to predict mental health conditions from user content on Twitter -a notoriously difficult task (Coppersmith et al, 2015a;Coppersmith et al, 2015b). 2.…”

Section: Our Contributionsmentioning

confidence: 99%

Section: Datamentioning

confidence: 99%

See 1 more Smart Citation

Multitask Learning for Mental Health Conditions with Limited Social Media Data

Benton¹,

Mitchell²,

Hovy³

2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

150

135

View full text Add to dashboard Cite

show abstract

“…The 2015 CLPsych Shared Task consisted of three user-level binary classification tasks: PTSD vs. control, depression vs. control, and PTSD vs. depression. The first two have been addressed in a number of settings (Coppersmith et al, 2015;Coppersmith et al, 2014b;Coppersmith et al, 2014a;Resnik et al, 2013;De Choudhury et al, 2013;Rosenquist et al, 2010;Ramirez-Esparza et al, 2008), while the third task is novel. Organizing this shared task brought together many teams to consider the same problem, which had the benefit of establishing a solid foundational understanding, common standards, and a shared deep understanding of both task and data.…”

Section: Introductionmentioning

confidence: 99%

CLPsych 2015 Shared Task: Depression and PTSD on Twitter

Coppersmith¹,

Dredze

Harman

et al. 2015

Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Realit

Self Cite

245

199

View full text Add to dashboard Cite

This paper presents a summary of the Computational Linguistics and Clinical Psychology (CLPsych) 2015 shared and unshared tasks. These tasks aimed to provide apples-to-apples comparisons of various approaches to modeling language relevant to mental health from social media. The data used for these tasks is from Twitter users who state a diagnosis of depression or post traumatic stress disorder (PTSD) and demographically-matched community controls. The unshared task was a hackathon held at Johns Hopkins University in November 2014 to explore the data, and the shared task was conducted remotely, with each participating team submitted scores for a held-back test set of users. The shared task consisted of three binary classification experiments: (1) depression versus control, (2) PTSD versus control, and (3) depression versus PTSD. Classifiers were compared primarily via their average precision, though a number of other metrics are used along with this to allow a more nuanced interpretation of the performance measures.

show abstract

“…Inferring demographic attributes has thus been a frequent area of research Pennacchiotti and Popescu, 2011;Volkova, 2015;Rao and Yarowsky, 2010;Mislove et al, 2011), enabling large-scale analysis of demographically identified social media posts. Demographic inference has been used in many Twitter analyses, including studies of mental health (Coppersmith et al, 2015), exercise (Dos Reis and Culotta, 2015), language (Eisenstein et al, 2011; and personality (Schwartz et al, 2013).…”

Section: Introductionmentioning

confidence: 99%