Info
We work on some of the most complex and interesting challenges in emotional communication. Our world-class research and engineering teams have made scientific breakthroughs, published papers in peer reviewed journals, written books on content analysis, revolutionized information architecture, and built cutting edge software systems.
Our approach to communication content analysis takes a multi-disciplinary approach to affective computing and natural language understanding. We utilize the latest findings in computer science, neuroscience, communication, psychology and engineering.
Theoretically, we follow a transactional model of communication. V.E.R.N. identifies and quantifies encoded signals from senders based on our new model, which we built into this software.
Dr. Brendan Watson is our director of research, and he can be found here.
V.E.R.N.’S ACCURACY
We strive to be as transparent as possible with the use of our software. As V.E.R.N. is used, and more frames of reference are understood, the accuracy will increase due to our patented refinement learning process. These results reflect internal testing, and as such are not a claim to individual results nor a guarantee of success. However we test the systems regularly, strive to improve, and provide results wherever possible.
Here are the results of our latest internal testing:
Sadness
Anger
Love/Joy
81%
Our internal testing uses thousands of randomly selected sentences from a variety of sources including: Famous works of literature, news, social media, political commentary, advertising, popular culture, and customer service interactions.
We test against computerized and human coding protocols, including outside analysts to set agreement.
- Theory and foundations
- Unsupervised learning and generative models
- Neuroscience
- Machine learning
- Computer Science
- Communication
Articles in Support of Methodology
- Applications of sentiment analysis and machine learning techniques in disease outbreak prediction
- Sentiment Analysis in Health and Well-Being: Systematic Review
- Sentiment analysis in medical settings: New opportunities and challenges
- The Benefits and Caveats of Personality-Adaptive Conversational Agents in Mental Health Care
- Harnessing machine learning to enhance Emotional Intelligence in healthcare
- Collaborative care with a virtual lens: enabling patients and providers to overcome the mental health crisis
- Measuring Service Encounter Satisfaction with Customer Service Chatbots
- Patients with comorbid behavioral health conditions have longer inpatient stays
Don’t forget to read our blog for more information on the science, methodology, and application of VERN AI.