InfoMiner at WNUT-2020 Task 2: Transformer-based Covid-19 Informative Tweet Extraction

TL;DR

This paper presents a transformer-based approach for extracting informative Covid-19 related tweets, achieving a top-10 ranking in the WNUT-2020 Task 2 with a high F1 score.

Contribution

It introduces a transformer-based method specifically designed for identifying informative tweets in social media data related to Covid-19.

Findings

Achieved 10th place in WNUT-2020 Task 2

Scored 0.9004 F1 on test set

Demonstrated effectiveness of transformers for tweet classification

Abstract

Identifying informative tweets is an important step when building information extraction systems based on social media. WNUT-2020 Task 2 was organised to recognise informative tweets from noise tweets. In this paper, we present our approach to tackle the task objective using transformers. Overall, our approach achieves 10th place in the final rankings scoring 0.9004 F1 score for the test set.