Using MT for multilingual covid-19 case load prediction
from social media texts
Popovic, MajaORCID: 0000-0001-8234-8745, Vasudevan, NedumpozhimanaORCID: 0000-0001-5161-8925, Meegan, GowerORCID: 0000-0002-8438-3998, Sneha, Rautmare, Nishtha, Jain and Kelleher, John D.ORCID: 0000-0001-6462-3248
(2023)
Using MT for multilingual covid-19 case load prediction
from social media texts.
In: 24th Annual Conference of the European Association of Machine Translation 2022 (EAMT 2023), 12-15 Jun 2023, Tampere, Finland.
ISBN 978-952-03-2947-1
In the context of an epidemiological study involving multilingual social media, this paper reports on the ability of machine translation systems to preserve content relevant for a document classification task designed to determine whether the social media text is related to covid-19. The results
indicate that machine translation does provide a feasible basis for scaling epidemiological social media surveillance to multiple languages. Moreover, a qualitative error analysis revealed that the majority of classification errors are not caused by MT errors.
24th Annual Conference of the European Association of Machine Translation 2022 (EAMT 2023), Proceedings.
.
European Association for Machine Translation (EAMT). ISBN 978-952-03-2947-1
Publisher:
European Association for Machine Translation (EAMT)