Text Similarity Using Word Embeddings to Classify Misinformation
This addresses the inefficiency of duplicate fact-checking in collaborative misinformation detection, but it is incremental as it applies existing word embedding methods to a specific domain.
The paper tackles the problem of identifying similar content to avoid redundant fact-checking in collaborative teams, using word embeddings to classify misinformation and suggesting previously verified articles.
Fake news is a growing problem in the last years, especially during elections. It's hard work to identify what is true and what is false among all the user generated content that circulates every day. Technology can help with that work and optimize the fact-checking process. In this work, we address the challenge of finding similar content in order to be able to suggest to a fact-checker articles that could have been verified before and thus avoid that the same information is verified more than once. This is especially important in collaborative approaches to fact-checking where members of large teams will not know what content others have already fact-checked.