Reproduce “CoNewsReader: Supporting Comprehensive Understanding and Raising Critical Thoughts on Social Media News Through Comments” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Kangyu Yuan, Guanzheng Chen, Sizhe Liang, Hehai Lin, Qingyu Guo, Dingdong Liu, Xiaojuan Ma, Zhenhui Peng
CoNewsReader, an interactive tool developed by researchers from Sun Yat-sen University and The Hong Kong University of Science and Technology, leverages categorized social media comments to enhance users' comprehensive understanding and critical thinking skills when consuming news. Empirical evaluation shows it improves comprehension and critical thought quality while reducing cognitive load and increasing user engagement.
Key insights
- A structured taxonomy of social media comments, categorized by their functional value (e.g., contextualization, skepticism), can effectively support different stages of Critical News Reading.
- Large Language Models (LLMs) can be successfully employed to automate the processing, classification, summarization, and question generation from vast quantities of social media comments, reducing user cognitive load.
- Interactive features that enable guided navigation through comments and provide explicit prompts can significantly scaffold users in developing comprehensive understanding and critical thinking skills beyond just reading a news article.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.