Sriparna Saha, Associate Professor, Dept. of Computer Science and Engineering, IIT Patna (India) Shares About Developing Motivational Virtual Assistants to Help People with Mental Health Issues

CDO Magazine publishes everything outstanding that is happening in the world of data and analytics. We introduce you to remarkable data organizations and great leaders through our special lists and nominations. We work throughout the year to bring you the latest in what is breaking down barriers and setting trends in the world of data. Our lists recognize the tremendous work performed to advance the cause of data and analytics worldwide, and we showcase the thought leaders’ accomplishments in their specific lines of work.

Our Leading Data Academic Leaders List 2022 honors these great academic leaders, introducing them on a global platform where they share their insights and work, highlighting their significant successes in the previous year, the challenges they faced, and their aspirations and goals for 2022.

INTRODUCING: Sriparna Saha, Associate Professor at Department of Computer Science and Engineering, Indian Institute of Technology, Patna (India)

1.What were your most significant achievements in 2021, specifically in the last two years, and why? 

My most significant achievement in 2021 was to start developing motivational virtual assistants (VA) that can try to help people suffering from mental illnesses. We are developing a VA acting as the first point of contact for mentally distressed support seekers afflicted with some form of mental disorder. The VA’s effort is directed toward comforting and allowing support seekers to share and express their thoughts, emotions, and struggles to seek support anonymously. The VA’s response should be competent and proficient enough to provide support seekers with a natural human experience focused on imparting hope and motivation based on a positive perspective.

Research is also going on in developing some virtual diagnosis assistants for aiding doctors in the disease diagnosis process by conducting in-depth symptom investigation followed by disease inference. These diagnosis assistants are becoming more popular and effective for early diagnosis, which appears to be immensely helpful for people living in rural areas. Apart from these health-oriented chatbot designs, we are also conducting research to design some persuasive chatbots that can persuade the user to cope with the goal unavailability situation. I have been working in the field of conversational agents for the last five years, and I find this area fascinating, having several societal benefits. 

2. What challenges are you facing in the academic data field? 

The major challenge is the availability of the data. As we are working on applications of artificial intelligence/natural language processing in solving various problems of the health care domain, gathering data is quite challenging. We require gold standard data where annotations are available. But the availability of such data is limited. Moreover, to validate the results obtained by our proposed systems, we need domain experts. We are currently collaborating with medical professionals to cope with data availability issues. 

Furthermore, poor explainability and scalability appear to be the two most pressing challenges for deep learning-based, data-driven autonomous agents. Thus, we aim to build some shallow yet scalable and explainable autonomous agents that could be efficiently incorporated for health care applications such as automatic disease diagnostic assistants.

3. What traits and qualities are required to be a successful academic data leader? 

In my opinion, an in-depth understanding of data is very much necessary. A researcher should spend significant time in understanding the nature, different aspects, and quality of data. Before applying any automated technique, we should first focus on identifying hidden patterns present in the data. Collaboration with domain experts will undoubtedly be advantageous. Moreover, keeping oneself up to date with the latest tools and techniques is also an essential factor in success. As technology progresses, one should focus on new and challenging problem statements. And obviously, hard work, dedication, learning from failure, and positivity are other key traits of a successful researcher. 

4. Tell us about your priorities in 2022. What are your key targets? 

In 2022, I would like to continue our research on automated disease investigation systems. Moreover, we will also focus on multi-modal information processing. Multi-modal information is available in all spheres of life. It has been established that, rather than relying on a single modality, fusing features extracted from multiple modalities can help improve different problems related to natural language processing and information retrieval. We will continue our research in the field of multi-modal summarization, multi-modal recommendation systems, multi-modal chatbot development, multi-modal hate speech/cyberbully detection systems, multi-modal complaint detection, etc. Our focus will be to investigate in depth how to efficiently fuse different signals coming from different modalities like audio, video, text, etc.

We aim to publish our research in top-tier conferences and journals, and would like to deploy our developed systems in hospitals, LEA for run-time testing and to help improve our society. We also aim to collaborate with different industries to work on some real-time problem statements related to NLP/IR.

5. What advice would you offer aspiring academic leaders to help them prepare for the role? 

I urge aspiring academic leaders to focus on solving real-life problems with societal benefits. Society needs the support of artificial intelligence to improve the lifestyles of rural people, people in distress, patients, and many more. The United Nations’ Sustainable Development Goals (SDGs) (see https://sdgs.un.org/goals) provide a vision of the future where AI-based tools can be utilized to help improve society as a whole. We academic leaders should come forward in solving problems related to these SDGs. 

Also, I request aspiring researchers to pay close attention to the fundamentals of the field as the underlying mathematical concepts provide real-world solutions to theoretical or virtual challenges. It also strengthens your mental endurance and improves your ability to think under pressure.