# Identifying depression-related topics in smartphone-collected free-response speech recordings using an automatic speech recognition system and a deep learning topic model

arXiv: https://arxiv.org/abs/2308.11773 · HTML: https://mlsanity.com/paper/2308.11773/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 101 references that are in the map.
- First posted on arXiv 22 Aug 2023.

## Builds on (most cited first, 7 of 7)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022)
- [The PRIORI Emotion Dataset: Linking Mood to Emotion Detected In-the-Wild](https://mlsanity.com/paper/1806.10658/) (2018)
- [Remote smartphone-based speech collection: acceptance and barriers in individuals with major depressive disorder](https://mlsanity.com/paper/2104.08600/) (2021)
- [Predicting Depressive Symptom Severity through Individuals' Nearby Bluetooth Devices Count Data Collected by Mobile Phones: A Preliminary Longitudinal Study](https://mlsanity.com/paper/2104.12407/) (2021)
- [Characterizing Financial Market Coverage using Artificial Intelligence](https://mlsanity.com/paper/2302.03694/) (2023)
- [Towards robust paralinguistic assessment for real-world mobile health (mHealth) monitoring: an initial study of reverberation effects on speech](https://mlsanity.com/paper/2305.12514/) (2023)

## Built on by (most cited first, 2 of 2)

- [Large-scale digital phenotyping: identifying depression and anxiety indicators in a general UK population with over 10,000 participants](https://mlsanity.com/paper/2409.16339/) (2024)
- [Multilingual Lexical Feature Analysis of Spoken Language for Predicting Major Depression Symptom Severity](https://mlsanity.com/paper/2511.07011/) (2025)

## Abstract (arXiv)

Language use has been shown to correlate with depression, but large-scale validation is needed. Traditional methods like clinic studies are expensive. So, natural language processing has been employed on social media to predict depression, but limitations remain-lack of validated labels, biased user samples, and no context. Our study identified 29 topics in 3919 smartphone-collected speech recordings from 265 participants using the Whisper tool and BERTopic model. Six topics with a median PHQ-8 greater than or equal to 10 were regarded as risk topics for depression: No Expectations, Sleep, Mental Therapy, Haircut, Studying, and Coursework. To elucidate the topic emergence and associations with depression, we compared behavioral (from wearables) and linguistic characteristics across identified topics. The correlation between topic shifts and changes in depression severity over time was also investigated, indicating the importance of longitudinally monitoring language use. We also tested the BERTopic model on a similar smaller dataset (356 speech recordings from 57 participants), obtaining some consistent results. In summary, our findings demonstrate specific speech topics may indicate depression severity. The presented data-driven workflow provides a practical approach to collecting and analyzing large-scale speech data from real-world settings for digital health research.