Data Analyst – Sources of Distress Project
TextEntity Ner Classification
Survey data containing mental health responses were annotated with entities and labels for co-occurring psychiatric disorders. LLMs and NLP models were applied to improve detection, indicating annotation of mental health categories. The project aimed to optimize screening accuracy using machine learning and domain-specific labeling standards.
• Labeled text data to identify psychiatric conditions related to survey responses.
• Used NLP and large language models (LLMs) for enhanced annotation accuracy.
• Collaborated with domain experts to refine classification labels and annotation procedures.
• Contributed to improved clinical decision-making by providing structured, labeled datasets.
Survey data containing mental health responses were annotated with entities and labels for co-occurring psychiatric disorders. LLMs and NLP models were applied to improve detection, indicating annotation of mental health categories. The project aimed to optimize screening accuracy using machine learning and domain-specific labeling standards. • Labeled text data to identify psychiatric conditions related to survey responses. • Used NLP and large language models (LLMs) for enhanced annotation accuracy. • Collaborated with domain experts to refine classification labels and annotation procedures. • Contributed to improved clinical decision-making by providing structured, labeled datasets.
2024 - 2024