Search Articles

View query in Help articles search

Search Results (1 to 10 of 11 Results)

Download search results: CSV END BibTex RIS


Results and Methodological Implications of the Digital Epidemiology of Prescription Drug References Among Twitter Users: Latent Dirichlet Allocation (LDA) Analyses

Results and Methodological Implications of the Digital Epidemiology of Prescription Drug References Among Twitter Users: Latent Dirichlet Allocation (LDA) Analyses

For more information on topic modeling in health science, including proposed applications and functions, see studies by Valdez et al [13] and Valdez and Goodson [25]. Coherence score cross-validation refers to an iterative analysis to identify the optimal number of topics for a given corpus. Coherence score cross-validation was completed by programming a computer to iteratively run an LDA topic model for an increasing k number of topics.

Maria A Parker, Danny Valdez, Varun K Rao, Katherine S Eddens, Jon Agley

J Med Internet Res 2023;25:e48405

Misinformation and Public Health Messaging in the Early Stages of the Mpox Outbreak: Mapping the Twitter Narrative With Deep Learning

Misinformation and Public Health Messaging in the Early Stages of the Mpox Outbreak: Mapping the Twitter Narrative With Deep Learning

Valdez and Patterson [31] propose that computationally driven analyses can complement and verify traditional quantitative or qualitative research findings. Therefore, this study aims to investigate longitudinal mpox-related narratives on social media using deep-learning techniques. The mpox outbreak marks the first public health emergency and response following a once-in-a-generation global pandemic.

Andy Edinger, Danny Valdez, Eric Walsh-Buhi, Jennifer S Trueblood, Lorenzo Lorenzo-Luaces, Lauren A Rutter, Johan Bollen

J Med Internet Res 2023;25:e43841

Difficulty Regulating Social Media Content of Age-Restricted Products: Comparing JUUL’s Official Twitter Timeline and Social Media Content About JUUL

Difficulty Regulating Social Media Content of Age-Restricted Products: Comparing JUUL’s Official Twitter Timeline and Social Media Content About JUUL

Valdez et al [15] have provided examples of exploratory topic models in practice. The second step uses an iterative topic model analysis that meta-analytically generates models with an increasing number of topics per corpus (ie, 1 topic, 2 topics…20 topics) [16]. This analysis generates a coherence score for each iteration, such that higher scores are equated with better model fit and interpretability.

Danny Valdez, Jennifer B Unger

JMIR Infodemiology 2021;1(1):e29011