My research is interdisciplinary, encompassing social media/computational social science, web/data science, web archiving, and (local) news.
StoryGraph provides a collection of tools that analyze the news cycle. USA generates a news similarity graph every 10 minutes by computing the similarity of news stories from 17 US news sources across the partisanship spectrum (left, center, and right). In these graphs, the nodes represent news articles, and an edge between a pair of nodes represents a high degree of similarity between the nodes (similar news stories).
Three news similarity graphs illustrating the dynamics of the news cycle. In these graphs, a single node represents a news article, a connected component (multiple connected nodes) represents a single news story reported by the connected nodes. StoryGraph uses the average degree of the connected components to quantify the level of attention stories receive. The first graph shows what is often referred to as a slow news day; low overlap across different news media organizations. The second graph shows a scenario where the attention of the media is split across multiple news stories. The third graph, which is about the release of the [Mueller Report](https://en.wikipedia.org/wiki/Mueller_report), shows a major news event; high degree of overlap/connectivity across different news media organizations.