We propose an effective model based on BERT to classify tweets as medical and non-medical. We experimentally validate the proposed model on more than 14k tweets, reaching accuracy levels of 0.93.

Twitter goes to the doctor: Detecting medical tweets using machine learning and BERT

Roitero K.;Della Mea V.;Mizzaro S.;Serra G.
2020-01-01

Abstract

We propose an effective model based on BERT to classify tweets as medical and non-medical. We experimentally validate the proposed model on more than 14k tweets, reaching accuracy levels of 0.93.
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11390/1189151
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 7
  • ???jsp.display-item.citation.isi??? ND
social impact