Detecting Stress in Textual Data
Nowadays, stress has become a growing problem for society due to its high impact on individuals but also on health care systems and companies. In order to overcome this problem, early detection of stress is a key factor. PHowever, there is still a lack of well-validated methods that provide good results in different datasets. In a recent study, researchers proposed a method to detect stress in textual data by combining lexicon-based features with distributional representations to enhance classification performance.
To help organize features for stress detection in text, they proposed a lexicon-based feature framework that exploits affective, syntactic, social, and topic-related features. The study evaluated the proposed approach using multiple public English datasets, implementing it with three machine learning models that were evaluated in terms of performance through several experiments. The results showed that the combination of FastText embeddings with a selection of lexicon-based features was the best-performing model, achieving F-scores above 80%.
Overall, this study provides a promising method for early detection of stress in textual data, which could help individuals, health care systems, and companies to tackle this growing problem. The proposed lexicon-based feature framework and distributional representations can be used as a baseline for other researchers, and the combination of FastText embeddings with a selection of lexicon-based features can be applied to different datasets to achieve high performance. The results of this study highlight the potential of text analysis in detecting stress and open up avenues for further research.
A text classification approach to detect psychological stress combining a lexicon-based feature framework with distributional representations