Skip to main navigation Skip to search Skip to main content

Evaluating Contextual Embeddings and their Extraction Layers for Depression Assessment

  • Stony Brook University

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations

Abstract

Recent works have demonstrated ability to assess aspects of mental health from personal discourse. At the same time, pre-trained contextual word embedding models have grown to dominate much of NLP but little is known empirically on how to best apply them for mental health assessment. Using degree of depression as a case study, we do an empirical analysis on which off-the-shelf language model, individual layers, and combinations of layers seem most promising when applied to human-level NLP tasks. Notably, we find RoBERTa most effective and, despite the standard in past work suggesting the second-to-last or concatenation of the last 4 layers, we find layer 19 (sixth-to last) is at least as good as layer 23 when using 1 layer. Further, when using multiple layers, distributing them across the second half (i.e. Layers 12+), rather than last 4, of the 24 layers yielded the most accurate results.

Original languageEnglish
Title of host publicationWASSA 2022 - 12th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop
EditorsJeremy Barnes, Orphee De Clercq, Valentin Barriere, Shabnam Tafreshi, Sawsan Alqahtani, Joao Sedoc, Roman Klinger, Alexandra Balahur
PublisherAssociation for Computational Linguistics (ACL)
Pages89-94
Number of pages6
ISBN (Electronic)9781955917520
StatePublished - 2022
Event12th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2022 - Dublin, Ireland
Duration: May 26 2022 → …

Publication series

NameWASSA 2022 - 12th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, Proceedings of the Workshop

Conference

Conference12th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, WASSA 2022
Country/TerritoryIreland
CityDublin
Period05/26/22 → …

Fingerprint

Dive into the research topics of 'Evaluating Contextual Embeddings and their Extraction Layers for Depression Assessment'. Together they form a unique fingerprint.

Cite this