Researchers have developed a novel method for classifying natural language texts by utilizing weighted structured patterns like N-grams and their hierarchical relationships. This approach aims to automate the detection of specific cognitive distortions, contributing to psychological care. The developed artificial intelligence model is designed to be interpretable, robust, and transparent, showing significant improvements in F1 scores over existing literature on two public datasets. The associated code and models are made available for community use. AI
IMPACT This research could lead to more accessible and automated tools for mental health support by improving AI's ability to understand and classify nuanced psychological states in text.
RANK_REASON The cluster contains an academic paper detailing a new method for text classification and its application to psychological care, including performance metrics and code availability. [lever_c_demoted from research: ic=1 ai=1.0]
- Anton Kolonin
- artificial intelligence
- arXiv
- cognitive distortion
- F1 scores
- Hugging Face
- natural language texts
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
