Twitter-MusicPD: melody of minds - navigating user-level data on multiple mental health disorders and music preferences
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
Social media platforms have become integral spaces for individuals to express emotions, seek advice, and disclose mental health conditions. While existing research primarily focuses on analyzing textual content for predicting mental disorders, music listening, as a fundamental aspect of human experience, has gained attention for its potential to influence psychological well-being. This paper introduces the Twitter-Music-Psychological Disorder (Twitter-MusicPD) dataset, which includes data from 5767 music-listening Twitter users, covering both individuals with six self-reported psychological disorders and non-disordered users, along with a matched control group of 38,086 non-music-listening Twitter users across six disordered and non-disordered groups. The dataset spans from August 2007 to May 2022, comprising 8,976,628 English tweets reported as embeddings and the content of 78,413 music tracks shared by users. Detailed information on music tracks, including sources, titles, artists and associated lyrics, is provided, along with sentiments and emotions related to the music. Twitter-MusicPD serves as a comprehensive resource for investigating the relationships between Twitter engagement, music choices, and psychological well-being, offering insights into how tweeting behaviors and music preferences evolve over time. Our data is available at: https://github.com/szamani20/Twitter-MusicPD_Melody-of-Minds .
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.003 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.003 | 0.003 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it