# Attention-Based LSTM for Psychological Stress Detection from Spoken Language Using Distant Supervision

arXiv: https://arxiv.org/abs/1805.12307 · HTML: https://mlsanity.com/paper/1805.12307/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 May 2018.

## Built on by (most cited first, 8 of 8)

- [Micromodels for Efficient, Explainable, and Reusable Systems: A Case Study on Mental Health](https://mlsanity.com/paper/2109.13770/) (2021)
- [Calibration of Transformer-based Models for Identifying Stress and Depression in Social Media](https://mlsanity.com/paper/2305.16797/) (2023)
- [WorryWords: Norms of Anxiety Association for over 44k English Words](https://mlsanity.com/paper/2411.03966/) (2024)
- [Sequence-to-Sequence Lexical Normalization with Multilingual Transformers](https://mlsanity.com/paper/2110.02869/) (2021)
- [Nora: The Well-Being Coach](https://mlsanity.com/paper/2106.00410/) (2021)
- [Autoencoders as Tools for Program Synthesis](https://mlsanity.com/paper/2108.07129/) (2021)
- [Using LLMs to Aid Annotation and Collection of Clinically-Enriched Data in Bipolar Disorder and Schizophrenia](https://mlsanity.com/paper/2406.12687/) (2024)
- [Interpreting Criminal Charge Prediction and Its Algorithmic Bias via Quantum-Inspired Complex Valued Networks](https://mlsanity.com/paper/2106.13456/) (2021)

## Abstract (arXiv)

We propose a Long Short-Term Memory (LSTM) with attention mechanism to classify psychological stress from self-conducted interview transcriptions. We apply distant supervision by automatically labeling tweets based on their hashtag content, which complements and expands the size of our corpus. This additional data is used to initialize the model parameters, and which it is fine-tuned using the interview data. This improves the model's robustness, especially by expanding the vocabulary size. The bidirectional LSTM model with attention is found to be the best model in terms of accuracy (74.1%) and f-score (74.3%). Furthermore, we show that distant supervision fine-tuning enhances the model's performance by 1.6% accuracy and 2.1% f-score. The attention mechanism helps the model to select informative words.