Evaluating Lexicon Incorporation for Depression Symptom Estimation
This work addresses depression assessment for mental health applications, but it is incremental as it builds on existing lexicon and transformer methods.
The paper tackled depression symptom estimation by incorporating sentiment, emotion, and domain-specific lexicons into a transformer-based model, achieving new state-of-the-art results for depression level estimation in patient-therapist interviews.
This paper explores the impact of incorporating sentiment, emotion, and domain-specific lexicons into a transformer-based model for depression symptom estimation. Lexicon information is added by marking the words in the input transcripts of patient-therapist conversations as well as in social media posts. Overall results show that the introduction of external knowledge within pre-trained language models can be beneficial for prediction performance, while different lexicons show distinct behaviours depending on the targeted task. Additionally, new state-of-the-art results are obtained for the estimation of depression level over patient-therapist interviews.