Affective Conditioning on Hierarchical Attention Networks Applied to Depression Detection from Transcribed Clinical Interviews

Danai Xezonaki, Georgios Paraskevopoulos, Alexandros Potamianos, Shrikanth Narayanan


In this work we propose a machine learning model for depression detection from transcribed clinical interviews. Depression is a mental disorder that impacts not only the subject’s mood but also the use of language. To this end we use a Hierarchical Attention Network to classify interviews of depressed subjects. We augment the attention layer of our model with a conditioning mechanism on linguistic features, extracted from affective lexica. Our analysis shows that individuals diagnosed with depression use affective language to a greater extent than not-depressed. Our experiments show that external affective information improves the performance of the proposed architecture in the General Psychotherapy Corpus and the DAIC-WoZ 2017 depression datasets, achieving state-of-the-art 71.6 and 70.3 using the test set, F1-scores respectively.


 DOI: 10.21437/Interspeech.2020-2819

Cite as: Xezonaki, D., Paraskevopoulos, G., Potamianos, A., Narayanan, S. (2020) Affective Conditioning on Hierarchical Attention Networks Applied to Depression Detection from Transcribed Clinical Interviews. Proc. Interspeech 2020, 4556-4560, DOI: 10.21437/Interspeech.2020-2819.


@inproceedings{Xezonaki2020,
  author={Danai Xezonaki and Georgios Paraskevopoulos and Alexandros Potamianos and Shrikanth Narayanan},
  title={{Affective Conditioning on Hierarchical Attention Networks Applied to Depression Detection from Transcribed Clinical Interviews}},
  year=2020,
  booktitle={Proc. Interspeech 2020},
  pages={4556--4560},
  doi={10.21437/Interspeech.2020-2819},
  url={http://dx.doi.org/10.21437/Interspeech.2020-2819}
}