1 code implementation • LREC 2022 • Kornraphop Kawintiranon, Lisa Singh
For example, BERTweet, pre-trained RoBERTa on a large amount of Twitter data, has achieved state-of-the-art results on several Twitter NLP tasks.
1 code implementation • Machine Learning 2022 • Kornraphop Kawintiranon, Lisa Singh
The neural network model outperforms the traditional models with an F1 score of 0. 91.
Ranked #1 on Spam detection on Traditional and Context-specific Spam Twitter (using extra training data)
1 code implementation • NAACL 2021 • Kornraphop Kawintiranon, Lisa Singh
Detecting stance on Twitter is especially challenging because of the short length of each tweet, the continuous coinage of new terminology and hashtags, and the deviation of sentence structure from standard prose.
Ranked #1 on Stance Detection (US Election 2020 - Biden) on Twitter Stance Election 2020 (using extra training data)
1 code implementation • 21 May 2021 • Kornraphop Kawintiranon, Yaguang Liu
In this paper, we investigate a simple natural language processing (NLP) approach to tackle the problem.