How to apply zero‐shot learning to text data in substance use research: An overview and tutorial with media data
Addiction · 2024-05 · 119 (5) · 951-959
DOI: 10.1111/add.16427 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift Addiction, online erschienen am 11.01.2024. Verfasst von Benjamin Riordan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Alcohol Policy Research, La Trobe University, Melbourne, Australia. Hauptthemen laut MEDLINE: Social Media, Substance-Related Disorders. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: La Trobe University SPPH internal grant, Australian Research Council Discovery Early Career Researcher Award.
Abstract (Originalsprache)
A vast amount of media‐related text data is generated daily in the form of social media posts, news stories or academic articles. These text data provide opportunities for researchers to analyse and understand how substance‐related issues are being discussed. The main methods to analyse large text data (content analyses or specifically trained deep‐learning models) require substantial manual annotation and resources. A machine‐learning approach called ‘zero‐shot learning’ may be quicker, more flexible and require fewer resources. Zero‐shot learning uses models trained on large, unlabelled (or weakly labelled) data sets to classify previously unseen data into categories on which the model has not been specifically trained. This means that a pre‐existing zero‐shot learning model can be used to analyse media‐related text data without the need for task‐specific annotation or model training. This approach may be particularly important for analysing data that is time critical. This article describes the relatively new concept of zero‐shot learning and how it can be applied to text data in substance use research, including a brief practical tutorial.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Centre for Alcohol Policy Research, La Trobe University, Melbourne, Australia.
- Computer Science and Information Technology, La Trobe University, Melbourne, Australia.
ORCID-Profile: Benjamin Riordan, Abraham Albert Bonela, Emmanuel Kuntsche
Förderung
- La Trobe University SPPH internal grant
- Australian Research Council Discovery Early Career Researcher Award
Zitieren
APA
Riordan, B., Bonela, A. A., He, Z., Nibali, A., Anderson-Luxford, D., & Kuntsche, E. (2024). How to apply zero‐shot learning to text data in substance use research: An overview and tutorial with media data. Addiction, 119(5), 951-959. https://doi.org/10.1111/add.16427
Vancouver
Riordan B, Bonela AA, He Z, Nibali A, Anderson-Luxford D, Kuntsche E. How to apply zero‐shot learning to text data in substance use research: An overview and tutorial with media data. Addiction. 2024;119(5):951-959. doi:10.1111/add.16427
BibTeX
@article{Riordan2024,
author = {Riordan, Benjamin and Bonela, Abraham Albert and He, Zhen and Nibali, Aiden and Anderson-Luxford, Dan and Kuntsche, Emmanuel},
title = {How to apply zero‐shot learning to text data in substance use research: An overview and tutorial with media data},
journal = {Addiction},
year = {2024},
volume = {119},
number = {5},
pages = {951--959},
doi = {10.1111/add.16427}
}
EUVIMED