# DASentimental: Detecting depression, anxiety and stress in texts via emotional recall, cognitive networks and machine learning

arXiv: https://arxiv.org/abs/2110.13710 · HTML: https://mlsanity.com/paper/2110.13710/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 71 references that are in the map.
- First posted on arXiv 26 Oct 2021.

## Builds on (most cited first, 11 of 11)

- [The COVID-19 Social Media Infodemic](https://mlsanity.com/paper/2003.05004/) (2020)
- [Multiplex lexical networks reveal patterns in early word acquisition in children](https://mlsanity.com/paper/1609.03207/) (2016)
- [#lockdown: network-enhanced emotional profiling at the times of COVID-19](https://mlsanity.com/paper/2005.04404/) (2020)
- [Text-mining forma mentis networks reconstruct public perception of the STEM gender gap in social media](https://mlsanity.com/paper/2003.08835/) (2020)
- [Revealing semantic and emotional structure of suicide notes with cognitive network science](https://mlsanity.com/paper/2007.12053/) (2020)
- [PyPlutchik: visualising and comparing emotion-annotated corpora](https://mlsanity.com/paper/2105.04295/) (2021)
- [Cognitive network science for understanding online social cognitions: A brief review](https://mlsanity.com/paper/2102.12799/) (2021)
- [Identification of Literary Movements Using Complex Networks to Represent Texts](https://mlsanity.com/paper/1302.4099/) (2013)
- [Distance entropy cartography characterises centrality in complex networks](https://mlsanity.com/paper/1802.10411/) (2018)
- [Unraveling the effects of multiscale network entanglement on disintegration of empirical systems](https://mlsanity.com/paper/2008.05368/) (2020)
- [Networked partisanship and framing: a socio-semantic network analysis of the Italian debate on migration](https://mlsanity.com/paper/2103.04653/) (2021)

## Built on by (most cited first, 6 of 6)

- [Measuring and identifying factors of individuals' trust in Large Language Models](https://mlsanity.com/paper/2502.21028/) (2025)
- [Text characterization based on recurrence networks](https://mlsanity.com/paper/2201.06665/) (2022)
- [Detecting Early and Implicit Suicidal Ideation via Longitudinal and Information Environment Signals on Social Media](https://mlsanity.com/paper/2510.14889/) (2025)
- [Towards hypergraph cognitive networks as feature-rich models of knowledge](https://mlsanity.com/paper/2304.06375/) (2023)
- [MyMentorLLM: A psychotherapy GenAI environment with multimodal voice/text patients, trainees and experts for deliberate practice](https://mlsanity.com/paper/2607.25667/) (2026)
- [Natural Language Processing Psychometrics](https://mlsanity.com/paper/2608.07316/) (2026)

## Abstract (arXiv)

Most current affect scales and sentiment analysis on written text focus on quantifying valence (sentiment) -- the most primary dimension of emotion. However, emotions are broader and more complex than valence. Distinguishing negative emotions of similar valence could be important in contexts such as mental health. This project proposes a semi-supervised machine learning model (DASentimental) to extract depression, anxiety and stress from written text. First, we trained the model to spot how sequences of recalled emotion words by N=200 individuals correlated with their responses to the Depression Anxiety Stress Scale (DASS-21). Within the framework of cognitive network science, we model every list of recalled emotions as a walk over a networked mental representation of semantic memory, with emotions connected according to free associations in people's memory. Among several tested machine learning approaches, we find that a multilayer perceptron neural network trained on word sequences and semantic network distances can achieve state-of-art, cross-validated predictions for depression (R = 0.7), anxiety (R = 0.44) and stress (R = 0.52). Though limited by sample size, this first-of-its-kind approach enables quantitative explorations of key semantic dimensions behind DAS levels. We find that semantic distances between recalled emotions and the dyad "sad-happy" are crucial features for estimating depression levels but are less important for anxiety and stress. We also find that semantic distance of recalls from "fear" can boost the prediction of anxiety but it becomes redundant when the "sad-happy" dyad is considered. Adopting DASentimental as a semi-supervised learning tool to estimate DAS in text, we apply it to a dataset of 142 suicide notes. We conclude by discussing key directions for future research enabled by artificial intelligence detecting stress, anxiety and depression.