Sarcasm Detection in a Disaster Context
Not on the map. Why?
Abstract (arXiv)
During natural disasters, people often use social media platforms such as Twitter to ask for help, to provide information about the disaster situation, or to express contempt about the unfolding event or public policies and guidelines. This contempt is in some cases expressed as sarcasm or irony. Understanding this form of speech in a disaster-centric context is essential to improving natural language understanding of disaster-related tweets. In this paper, we introduce HurricaneSARC, a dataset of 15,000 tweets annotated for intended sarcasm, and provide a comprehensive investigation of sarcasm detection using pre-trained language models. Our best model is able to obtain as much as 0.70 F1 on our dataset. We also demonstrate that the performance on HurricaneSARC can be improved by leveraging intermediate task transfer learning. We release our data and code at https://github.com/tsosea2/HurricaneSarc.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 24 of its 60 references that are in the map. First posted on arXiv 16 Aug 2023.
Builds on
24 of 60 references.
References · 24
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
- 2020Don't Stop Pretraining: Adapt Language Models to Domains and Taskscited by 1,565
- 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
- 2014Convolutional Neural Networks for Sentence Classificationcited by 1,127
- 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
- 2020GoEmotions: A Dataset of Fine-Grained Emotionscited by 486
- 2018Tune: A Research Platform for Distributed Model Selection and Trainingcited by 395
- 2020BERTweet: A pre-trained language model for English Tweetscited by 346
- 2013Crowdsourcing a Word-Emotion Association Lexiconcited by 196
- 2020Intermediate-Task Transfer Learning with Pretrained Models for Natural Language Understanding: When and Why Does It Work?cited by 127
- 2017A Large Self-Annotated Corpus for Sarcasmcited by 64
12 more
- 2017Creating and Characterizing a Diverse Corpus of Sarcasm in Dialoguecited by 43
- 2019iSarcasm: A Dataset of Intended Sarcasmcited by 41
- 2016A Deeper Look into Sarcastic Tweets Using Deep Convolutional Neural Networkscited by 33
- 2016Modelling Context with User Embeddings for Sarcasm Detection in Social Mediacited by 26
- 2018CASCADE: Contextual Sarcasm Detection in Online Discussion Forumscited by 26
- 2020Uncertainty-aware Self-training for Text Classification with Few Labelscited by 20
- 2019Sentiment and Sarcasm Classification with Multitask Learningcited by 19
- 2016Are Word Embedding-based Features Useful for Sarcasm Detection?cited by 14
- 2017Really? Well. Apparently Bootstrapping Improves the Performance of Sarcasm and Nastiness Classifiers for Online Dialoguecited by 14
- 2019Keyphrase Extraction from Disaster-related Tweetscited by 12
- 2018Footwear Size Recommendation Systemcited by 10
- 2019One Embedding To Do Them Allcited by 10
Built on by
Citing papers per year: 2025: 1.
1 paper.