Back

YeZzzs Does it: Studying Sleep and Emotion using the Digital Rest-Activity Rhythms of Kanye West's Tweets

Reid, M. J.; Rojo-Wissar, D.; Mei, M.; Differing, M.; Smith, M. T.; Smith, M. G.

2025-02-14 health informatics
10.1101/2025.02.03.25321602 medRxiv
Show abstract

One of the greatest challenges faced by the field of precision medicine is the identification of biomarkers capable of detecting clinically meaningful change at the individual level, not just amongst large-scale population studies. To this end, the evermore present social mediaverse provides unparalleled access to ecologically-valid databases of digital-biomarkers, that could be leveraged with single-user precision to support mental health care by monitoring use-patterns and emotional state. Despite this potential, investigation into how social-media use can be used to study sleep-wake behaviors has been remarkably scant, in part due to a lack of established methods to detect and estimate sleep using social-media activity. We present here a new approach to using social media-based data to track both sleep and mood, with potential applications to mental health monitoring and prevention. Amongst demonstrating proof of concept, we also provide an ethical and theoretical framework of how to proceed amongst this sensitive but potentially highly fruitful field.

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.