Detecting Levels of Depression in Text Based on Metrics
This work addresses depression monitoring for mental health applications, but it is incremental as it highlights limitations rather than achieving strong results.
The paper tackled the problem of detecting depression levels from text using the Distress Analysis Interview Corpus, but found that measuring depression through text alone is complex and limited due to unaccounted factors.
Depression is one of the most common and a major concern for society. Proper monitoring using devices that can aid in its detection could be helpful to prevent it all together. The Distress Analysis Interview Corpus (DAIC) is used to build a metric-based depression detection. We have designed a metric to describe the level of depression using negative sentences and classify the participant accordingly. The score generated from the algorithm is then levelled up to denote the intensity of depression. The results show that measuring depression is very complex to using text alone as other factors are not taken into consideration. Further, In the paper, the limitations of measuring depression using text are described, and future suggestions are made.