English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Models that accurately detect depression from text are important tools foraddressing the post-pandemic mental health crisis. BERT-based classifiers'promising performance and the off-the-shelf availability make them greatcandidates for this task. However, these models are known to suffer fromperformance inconsistencies and poor generalization. In this paper, weintroduce the DECK (DEpression ChecKlist), depression-specific modelbehavioural tests that allow better interpretability and improvegeneralizability of BERT classifiers in depression domain. We create 23 teststo evaluate BERT, RoBERTa and ALBERT depression classifiers on three datasets,two Twitter-based and one clinical interview-based. Our evaluation shows thatthese models: 1) are robust to certain gender-sensitive variations in text; 2)rely on the important depressive language marker of the increased use of firstperson pronouns; 3) fail to detect some other depression symptoms like suicidalideation. We also demonstrate that DECK tests can be used to incorporatesymptom-specific information in the training data and consistently improvegeneralizability of all three BERT models, with an out-of-distribution F1-scoreincrease of up to 53.93%.

DECK: Behavioral Tests to Improve Interpretability and Generalizability of BERT Models Detecting Depression from Text