Title: Understanding where Wikipedia needs citations through data science.
In this talk, we will discuss how data science can help understanding the space of verifiability in Wikipedia, from both the editors' and the readers' perspective. First, we will see statistics about scholarly publications cited in Wikipedia articles, broken down by topic, accessibility and language. We will then look at the most common reasons why citations are required in Wikipedia articles, and see how algorithmic models can determine if a statement requires a citation. Finally, we will learn how Wikipedia readers interact with citations, showing preliminary results on a large-scale dataset collected from English Wikipedia.
Miriam Redi is a Research Scientist at the Wikimedia Foundation and Visiting Research Fellow at King's College London. Formerly, she worked as a Research Scientist at Yahoo Labs in Barcelona and Nokia Bell Labs in Cambridge. She received her PhD from EURECOM, Sophia Antipolis. She conducts research in social multimedia computing, working on fair, interpretable, multimodal machine learning solutions to improve knowledge equity.