# The relationship between linguistic expression and symptoms of depression, anxiety, and suicidal thoughts: A longitudinal study of blog content

arXiv: https://arxiv.org/abs/1811.02750 · HTML: https://mlsanity.com/paper/1811.02750/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2018.

## Built on by (most cited first, 5 of 5)

- [LLMCARE: early detection of cognitive impairment via transformer models enhanced by LLM-generated synthetic data](https://mlsanity.com/paper/2508.10027/) (2025)
- [Speech as a Multimodal Digital Phenotype for Multi-Task LLM-based Mental Health Prediction](https://mlsanity.com/paper/2505.23822/) (2025)
- [PSI-Bench: Interpretable and Clinically Meaningful Evaluation of Depression Patient Simulators](https://mlsanity.com/paper/2604.25840/) (2026)
- [INESC-ID @ eRisk 2025: Exploring Fine-Tuned, Similarity-Based, and Prompt-Based Approaches to Depression Symptom Identification](https://mlsanity.com/paper/2506.02924/) (2025)
- [When are We Worried? Temporal Trends of Anxiety and What They Reveal about Us](https://mlsanity.com/paper/2602.10400/) (2026)

## Abstract (arXiv)

Due to its popularity and availability, social media data may present a new way to identify individuals who are experiencing mental illness. By analysing blog content, this study aimed to investigate the associations between linguistic features and symptoms of depression, generalised anxiety, and suicidal ideation. This study utilised a longitudinal study design. Individuals who blogged were invited to participate in a study in which they completed fortnightly mental health questionnaires including the PHQ9 and GAD7 for a period of 36 weeks. Linguistic features were extracted from blog data using the LIWC tool. Bivariate and multivariate analyses were performed to investigate the correlations between the linguistic features and mental health scores between subjects. We then used the multivariate regression model to predict longitudinal changes in mood within subjects. A total of 153 participants consented to taking part, with 38 participants completing the required number of questionnaires and blog posts during the study period. Between-subject analysis revealed that several linguistic features, including tentativeness and non-fluencies, were significantly associated with depression and anxiety symptoms, but not suicidal thoughts. Within-subject analysis showed no robust correlations between linguistic features and changes in mental health score. This study provides further support for the relationship between linguistic features within social media data and symptoms of depression and anxiety. The lack of robust within-subject correlations indicate that the relationship observed at the group level may not generalise to individual changes over time.