Emotional Intensity analysis in Bipolar subjects
This work contributes to quantitative psychiatry by enabling automated identification of altered mental states in Bipolar subjects, though it appears incremental as it builds on previous studies.
The study tackled the problem of classifying Bipolar and control subjects by analyzing speech using an Emotion Intensity Index based on the Dictionary of Affect, achieving over 75% labeling performance with classical classification techniques.
The massive availability of digital repositories of human thought opens radical novel way of studying the human mind. Natural language processing tools and computational models have evolved such that many mental conditions are predicted by analysing speech. Transcription of interviews and discourses are analyzed using syntactic, grammatical or sentiment analysis to infer the mental state. Here we set to investigate if classification of Bipolar and control subjects is possible. We develop the Emotion Intensity Index based on the Dictionary of Affect, and find that subjects categories are distinguishable. Using classical classification techniques we get more than 75\% of labeling performance. These results sumed to previous studies show that current automated speech analysis is capable of identifying altered mental states towards a quantitative psychiatry.