AI-based approach to burnout identification from textual data

TL;DR

This paper presents an AI-driven NLP method using a fine-tuned RuBERT model to identify burnout signals in textual data, enabling large-scale monitoring in high-stress workplaces.

Contribution

It introduces a novel approach combining synthetic data and real user comments to fine-tune a model for burnout detection from text.

Findings

Model effectively detects burnout signals in textual data.

Synthetic data enhances model training and performance.

Applicable to large-scale monitoring in workplace environments.

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.