Search Articles

View query in Help articles search

Search Results (1 to 4 of 4 Results)

Download search results: CSV END BibTex RIS


Influence of User Profile Attributes on e-Cigarette–Related Searches on YouTube: Machine Learning Clustering and Classification

Influence of User Profile Attributes on e-Cigarette–Related Searches on YouTube: Machine Learning Clustering and Classification

Please refer to Kong et al [19] for more information on how these themes were determined and labeled. We used GCN, which is a supervised machine learning method, to classify data (ie, titles and descriptions) by theme to better understand the unique clusters identified through k-means clustering. In GCN, word frequency and word co-occurrence information are used to build the word-to-word and word-to-video edges (ie, as common videos between pairs), respectively.

Dhiraj Murthy, Juhan Lee, Hassan Dashtian, Grace Kong

JMIR Infodemiology 2023;3:e42218