Predicting anxiety using Google and Youtube digital traces

Anxiety is a widespread and serious mental health issue that has been exacerbated by the COVID-19 pandemic and other stressors. In this study, we explore how online behavior data from Google and YouTube can be used to infer anxiety levels in individuals. We collected and processed digital traces fro...

Full description

Saved in:
Bibliographic Details
Main Authors: Joshua Rochotte, Aniket Sanap, Vincent Silenzio, Vivek K. Singh
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Emerging Trends in Drugs, Addictions, and Health
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2667118224000047
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850256786721865728
author Joshua Rochotte
Aniket Sanap
Vincent Silenzio
Vivek K. Singh
author_facet Joshua Rochotte
Aniket Sanap
Vincent Silenzio
Vivek K. Singh
author_sort Joshua Rochotte
collection DOAJ
description Anxiety is a widespread and serious mental health issue that has been exacerbated by the COVID-19 pandemic and other stressors. In this study, we explore how online behavior data from Google and YouTube can be used to infer anxiety levels in individuals. We collected and processed digital traces from nearly 100 participants over eight weeks and applied various machine learning techniques to extract features and build predictive models. We found that combining data from multiple media modalities can yield highly accurate predictive models for anxiety as self-reported by a clinical GAD-7 scale (AUC > 0.86). We also found that the semantic categories of online engagement can affect the predictive performance of the models. This study contributes to the field of computational social science and digital mental health and demonstrates the potential of using online behavior data to monitor psychological well-being and design interventions for anxiety.
format Article
id doaj-art-4d91a0fd19f84b20a55eabbe6ef82b41
institution OA Journals
issn 2667-1182
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Emerging Trends in Drugs, Addictions, and Health
spelling doaj-art-4d91a0fd19f84b20a55eabbe6ef82b412025-08-20T01:56:34ZengElsevierEmerging Trends in Drugs, Addictions, and Health2667-11822024-12-01410014510.1016/j.etdah.2024.100145Predicting anxiety using Google and Youtube digital tracesJoshua Rochotte0Aniket Sanap1Vincent Silenzio2Vivek K. Singh3School of Communication & Information, Rutgers University, NJ, USA; Corresponding author.Department of Computer Science, Rutgers University, New Brunswick, NJ, USASchool of Public Health, Rutgers University, New Brunswick, NJ, USASchool of Communication & Information, Rutgers University, NJ, USAAnxiety is a widespread and serious mental health issue that has been exacerbated by the COVID-19 pandemic and other stressors. In this study, we explore how online behavior data from Google and YouTube can be used to infer anxiety levels in individuals. We collected and processed digital traces from nearly 100 participants over eight weeks and applied various machine learning techniques to extract features and build predictive models. We found that combining data from multiple media modalities can yield highly accurate predictive models for anxiety as self-reported by a clinical GAD-7 scale (AUC > 0.86). We also found that the semantic categories of online engagement can affect the predictive performance of the models. This study contributes to the field of computational social science and digital mental health and demonstrates the potential of using online behavior data to monitor psychological well-being and design interventions for anxiety.http://www.sciencedirect.com/science/article/pii/S2667118224000047AnxietyMachine learningGoogleYouTubeDigital traces
spellingShingle Joshua Rochotte
Aniket Sanap
Vincent Silenzio
Vivek K. Singh
Predicting anxiety using Google and Youtube digital traces
Emerging Trends in Drugs, Addictions, and Health
Anxiety
Machine learning
Google
YouTube
Digital traces
title Predicting anxiety using Google and Youtube digital traces
title_full Predicting anxiety using Google and Youtube digital traces
title_fullStr Predicting anxiety using Google and Youtube digital traces
title_full_unstemmed Predicting anxiety using Google and Youtube digital traces
title_short Predicting anxiety using Google and Youtube digital traces
title_sort predicting anxiety using google and youtube digital traces
topic Anxiety
Machine learning
Google
YouTube
Digital traces
url http://www.sciencedirect.com/science/article/pii/S2667118224000047
work_keys_str_mv AT joshuarochotte predictinganxietyusinggoogleandyoutubedigitaltraces
AT aniketsanap predictinganxietyusinggoogleandyoutubedigitaltraces
AT vincentsilenzio predictinganxietyusinggoogleandyoutubedigitaltraces
AT vivekksingh predictinganxietyusinggoogleandyoutubedigitaltraces