This study developed a working model to supplement telepsychology and psychotherapists to detect emotional health that impacts the mental health of subjects.
Mental illness impacts the emotions of an individual and can have serious consequences. Innovating strategies for prevention, accurate diagnosis, and intervention in this space then becomes imperative. At an extreme level, mental illness can compel a patient to take extreme steps and to pre-empt life threatening situations, predictive analytics can play a significant role.
The new age technology can help in the early detection of mental health issues through emotional analysis. Artificial Intelligence can aid in monitoring emotions in multiple ways. Chatbots or robotic companions, in real-time, can help predict an individual’s risk of depression and suicidal behavior.
A team of participants developed a working model to supplement research work that augmented telepsychology and psychotherapists for observations and interventions. They guided psychologists in the selection and timing of therapeutic tools. Important to note is that they do not claim this alone will determine the disease and its cure.
The project’s objective was to cover all the modalities for prediction (Image, Video, Audio, Text, and Bio-signals), determine fusion techniques across modalities, and uncover the temporal aspects across modalities to support real-time predictions.
The team found a strong correlation between a few emotions, such as anger, fear, and sadness. Some modalities were strongly associated with specific emotions. For example, anger, happiness, and surprise are video-dominated emotions, while sadness and fear are audio-dominated emotions. The team also observed increased accuracy in video (59%), audio (87%) and text (62%).
The managerial implications of the project were that it helped develop a systematic approach for predicting human emotions using multiple modalities. The results can help analyze emotions and act as an aid or tool for psychiatrists in telepsychology. The work in exploiting biosignals as a modality can be used to investigate clinical use cases. Multi-modality (video, audio, text) and added bio-signal modes (colour on the face) were suggested for more accurate results. The team developed a step-by-step method for model use and development such that it can aid a psychiatrist’s treatment recommendation with remote therapy.
There is immense user value in the project undertaken. In conjunction with the proposed model, a psychiatrist can identify and analyse the subject’s emotional state better and modify treatment accordingly. By knowing the subject’s emotional state better, the psychiatrist can modify their treatment and even understand how the subject is reacting to the intervention introduced. Hence, this ability to detect emotions correctly will not only be beneficial but will also bring positive changes to the realm of mental health.
With most of the world moving towards virtual interactions post-COVID pandemic, Emotion AI will play a significant role in detecting emotions in virtual conversations. It supports the psychiatrists or the healthcare professionals in providing the best treatment and continuously monitoring their well-being. The user value of this project can be achieved by helping individuals:
- Identifying signs of depression, anxiety, grief and pain.
- Creating awareness of their emotional states.
- Achieving the emotional well-being of one and all.
Other potential business use cases of this emotion detection were also identified as a part of this project. In-car driver emotion detection system- a detection system can be deployed over vehicles, which may aid the drivers in understanding their emotional state and understand if they are driving carefully. If integrated with the vehicle’s sensor systems, this can also control speeds and inform the near-and-dear ones of the situations. Emotion detection and scores during interviews: the emotion detection system can come up with temporal scores during different stages of interviews, which can help in the evaluation process, making it more quantitative and less subjective and giving a score for emotional Intelligence during different situations.
References:
1) Kumar S., Nandkumar A., Nidhi M., Nagpal S., Dhawan V., ‘Prediction of Emotional State using AI’.