Keynotes

We are pleased to welcome the following invited speakers covering a range of perspectives on data science, journalism, and media:

Dafna Shahaf (Hebrew University of Jerusalem)

Title: Metro Maps of Information and Applications to Journalism

Abstract: When information is abundant, it becomes increasingly difficult to fit nuggets of knowledge into a single coherent picture. Complex stories spaghetti into branches, side stories, and intertwining narratives; search engines, our most popular navigational tools, are limited in their capacity to explore such complex stories. We propose a methodology for creating structured summaries of information, which we call metro maps. Just as cartographic maps have been relied upon for centuries to help us understand our surroundings, metro maps can help us understand the relationships between many pieces of information. We discuss extensions of the framework for analysis of news and media, personalization, and investigative journalism.

Andreas Loos (ZEIT ONLINE)

Title: ZEIT ONLINE: Data Science in the News Business

Abstract: ZEIT ONLNE is one of the largest online news platforms in Germany. The data science department at ZEIT ONLINE is part of the newsroom and deals with a broad spectrum of problems, ranging from journalistic projects to the analysis of readers’ traffic patterns. Andreas will present some of the data science projects, algorithms and software that he worked on over the last two years.

Maria Mestre (Factmata)

Title: Misinformation and Bias Detection in News Content

Abstract: Factmata applies state-of-the-art natural language processing techniques to detect misinformation and bias in news content. We have also collected a unique dataset of annotations by journalists around political bias that we are using to train new and improved machine learning models. Our talk at the workshop will be around the two key areas of research of the company. Firstly we'll talk about the data collection and key insights of the dataset annotated by journalists. We'll then talk about the ways we're using this data to improve the artificial intelligence models that detect biased content.