Twitter Resource
Twitter data serves as a rich resource for studying various social phenomena, with research focusing on analyzing public opinion, detecting misinformation, and understanding online behavior. Current research employs a range of techniques, including transformer-based language models (like BERT and its variants), graph neural networks, and machine learning algorithms, to classify sentiment, identify bots and trolls, and detect hate speech or biased claims. These analyses provide valuable insights into public discourse, enabling improved understanding of social dynamics, the spread of misinformation, and the detection of harmful online activities, with implications for public health, political science, and social media regulation.
Papers
Vaccine Discourse on Twitter During the COVID-19 Pandemic
Gabriel Lindelöf, Talayeh Aledavood, Barbara Keller
Catch Me If You Can: Deceiving Stance Detection and Geotagging Models to Protect Privacy of Individuals on Twitter
Dilara Dogan, Bahadir Altun, Muhammed Said Zengin, Mucahid Kutlu, Tamer Elsayed
An Exploratory Study of Tweets about the SARS-CoV-2 Omicron Variant: Insights from Sentiment Analysis, Language Interpretation, Source Tracking, Type Classification, and Embedded URL Detection
Nirmalya Thakur, Chia Y. Han
A Large-Scale Dataset of Twitter Chatter about Online Learning during the Current COVID-19 Omicron Wave
Nirmalya Thakur