Large-scale, Language-agnostic Discourse Classification of Tweets During COVID-19
arXiv:2008.00461 · doi:10.3390/make2040032
Abstract
Quantifying the characteristics of public attention is an essential prerequisite for appropriate crisis management during severe events such as pandemics. For this purpose, we propose language-agnostic tweet representations to perform large-scale Twitter discourse classification with machine learning. Our analysis on more than 26 million COVID-19 tweets shows that large-scale surveillance of public discourse is feasible with computationally lightweight classifiers by out-of-the-box utilization of these representations.
arXiv comment14 pages, 4 figures
References in corpus (24)
- Distributed Representations of Sentences and Documents
- The COVID-19 Social Media Infodemic
- Tracking Social Media Discourse About the COVID-19 Pandemic: Development of a Public Coronavirus Twitter Data Set
- Framing COVID-19: How we conceptualize and discuss the pandemic on Twitter
- A first look at COVID-19 information and misinformation sharing on Twitter
- COVID-19 on Social Media: Analyzing Misinformation in Twitter Conversations
- Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder
- Quantifying the Carbon Emissions of Machine Learning
- Understanding the perception of COVID-19 policies by mining a multilanguage Twitter dataset
- How the world's collective attention is being paid to a pandemic: COVID-19 related n-gram time series for 24 languages on Twitter
- Causal Modeling of Twitter Activity During COVID-19
- COVID-19 Twitter Dataset with Latent Topics, Sentiments and Emotions Attributes
- Keyphrase Extraction from Disaster-related Tweets
- Cyberbullying Detection with Fairness Constraints
- Twitter discussions and emotions about COVID-19 pandemic: a machine learning approach
- What Are People Asking About COVID-19? A Question Classification Dataset
- NAIST COVID: Multilingual COVID-19 Twitter and Weibo Dataset
- In the Eyes of the Beholder: Analyzing Social Media Use of Neutral and Controversial Terms for COVID-19
- Detecting Topic and Sentiment Dynamics Due to COVID-19 Pandemic Using Social Media
- Risk Communication in Asian Countries: COVID-19 Discourse on Twitter
- Cultural Convergence: Insights into the behavior of misinformation networks on Twitter
- Towards Characterizing COVID-19 Awareness on Twitter
- Exploratory Analysis of COVID-19 Related Tweets in North America to Inform Public Health Institutes
- Deep Representation Learning for Clustering of Health Tweets
Cited by in corpus (4)
- A large-scale COVID-19 Twitter chatter dataset for open scientific research -- an international collaboration
- BERT-Deep CNN: State-of-the-Art for Sentiment Analysis of COVID-19 Tweets
- Classification Aware Neural Topic Model and its Application on a New COVID-19 Disinformation Corpus
- A Comparative Study on Transfer Learning and Distance Metrics in Semantic Clustering over the COVID-19 Tweets