Machine Learning Classifiers for Twitter Surveillance of Vaping: Comparative Machine Learning Study.
Shyam VisweswaranJason B ColditzPatrick O'HalloranNa-Rae HanSanya B TanejaJoel WellingKar-Hai ChuJaime E SidaniBrian A PrimackPublished in: Journal of medical Internet research (2020)
We derived and evaluated traditional machine learning and deep learning classifiers to identify vaping-related relevant, commercial, and provape tweets. Overall, deep learning classifiers such as LSTM-CNN had superior performance and had the added advantage of requiring no preprocessing. The performance of these classifiers supports the development of a vaping surveillance system.