Skip to content
conftrace_
2020 COLING COLING 2020

FBK@SMM4H2020: RoBERTa for Detecting Medications on Twitter

Abstract

AbstractThis paper describes a classifier for tweets that mention medications or supplements, based on a pretrained transformer. We developed such a system for our participation in Subtask 1 of the Social Media Mining for Health Application workshop, which featured an extremely unbalanced dataset. The model showed promising results, with an F1 of 0.8 (task mean: 0.66).

Authors

Silvia Casola, Alberto Lavelli

Topics

Machine Learning > Core Methods > Classification

Keywords

text classification named entity recognition social media mining medication detection
Download PDF

More from COLING 2020

All COLING 2020 papers →
Towards Preemptive Detection of Depression and Anxiety in Twitter
Identifying Medication Abuse and Adverse Effects from Tweets: University of Michigan at #SMM4H 2020
How Far Can We Go with Just Out-of-the-box BERT Models?
Autobots Ensemble: Identifying and Extracting Adverse Drug Reaction from Tweets Using Transformer Based Pipelines
Transformer Models for Drug Adverse Effects Detection from Tweets
Adverse Drug Reaction Detection in Twitter Using RoBERTa and Rules