News

Basis Technology Chief Scientist Presents Published Work on Using NLP to Help Diagnose Mental Health Disorders

Kfir Bar delivers keynote session during Future of Text Analytics conference

SOMERVILLE, Mass. — May 31, 2022 — Kfir Bar, Ph.D., and Chief Scientist at Basis Technology, presented “Adaptable NLP: A Case Study in Mental Health” during the recent Future of Text Analytics virtual summit. The presentation was based on the published work of Bar and colleagues as part of the proceedings of the Sixth Workshop on Computational Linguistics and Clinical Psychology.

In their work, Bar et. al., focused on schizophrenia and the adaptability of natural language processing (NLP) software to detect the distinguishing characteristics of associated disordered speech. Their goal was to automatically and reliably detect disorganized speech patterns to help clinicians make better diagnoses and pursue appropriate treatment options. 

In his presentation, Bar described the particular speech patterns, such as derailment and incoherence, that are strong indicators of thought disorders like schizophrenia. In the group’s study of Hebrew-speaking mental health patients and a control group, scores were assigned to the degree of speech derailment and coherence. Using these measures, the researchers were able to build a classification system for detecting schizophrenia through recorded interviews that achieved 81.5% accuracy. 

The text analysis system used in this case was the Ben-Gurion University Morphological Tagger, a context-sensitive morphological analyzer for Modern Hebrew. However, the methodology could be applied to models trained to detect these patterns in other languages. 

According to Bar, “We were very encouraged by results that showed a strong degree of accuracy for predicting a schizophrenia diagnosis through text analysis. It certainly holds promise as another diagnostic tool for mental health clinicians.”  

About Basis Technology

Analyzing text — the hardest part of big data — is critical to verifying identity, understanding customers, anticipating world events, and uncovering crime. While unknown to end users, AI-powered text analytics platform Rosette is used by Refinitiv, Société Générale, Luminoso, Recorded Future, Medallia, and agencies across the U.S. intelligence community, to solve their toughest human language problems. For over 20 years, Basis Technology has been at the forefront of natural language processing applied to financial compliance, enterprise search, social listening, e-commerce, and e-discovery. 

Our cyber forensics team pioneers better, faster, and cheaper techniques to extract digital evidence, keeping government and law enforcement ahead of exponential growth of data volumes. KonaSearch automates workflows through its deep search across every field, object, and attachment in Salesforce and other data sources. For more information  visit www.basistech.com  or email info@basistech.com.