English

AI-based approach to burnout identification from textual data

Computation and Language 2026-01-27 v1 Artificial Intelligence

Abstract

This study introduces an AI-based methodology that utilizes natural language processing (NLP) to detect burnout from textual data. The approach relies on a RuBERT model originally trained for sentiment analysis and subsequently fine-tuned for burnout detection using two data sources: synthetic sentences generated with ChatGPT and user comments collected from Russian YouTube videos about burnout. The resulting model assigns a burnout probability to input texts and can be applied to process large volumes of written communication for monitoring burnout-related language signals in high-stress work environments.

Keywords

Cite

@article{arxiv.2601.17993,
  title  = {AI-based approach to burnout identification from textual data},
  author = {Marina Zavertiaeva and Petr Parshakov and Mikhail Usanin and Aleksei Smirnov and Sofia Paklina and Anastasiia Kibardina},
  journal= {arXiv preprint arXiv:2601.17993},
  year   = {2026}
}

Comments

9 pages, 2 figures

R2 v1 2026-07-01T09:19:26.430Z