SENTIMENT ANALYSIS OF DYSTHYMIA FORM OF DEPRESSION USING MULTIMODAL APPROACH

To investigate the correlation between linguistic traits and dysthymia symptoms, researchers have compiled a comprehensive set of speech features, drawing on previous research findings. These features encompass various aspects of speech, including prosody, pitch, intonation, speech rate, and pauses, among others. Analysing these linguistic cues can provide valuable insights into an individual’s emotional state and mental well-being. One commonly used technique for assessing the severity of depression is the Beck Depression Inventory (BDI). This approach involves individuals answering specific questions that help gauge their level of depression. By incorporating such self-report measures into the analysis of linguistic traits, a more holistic assessment of dysthymia can be obtained. The combination of objective linguistic analysis and subjective self-assessment measures can enhance the accuracy and reliability of dysthymia detection. We have one solution to solve this issue in terms of machine learning. Machine learning is a process which learns from past experience and provide the best result when the same issue or event occurs in the future.