News Kaleidoscope: Visual Investigation of Coverage Diversity in News Event Reporting

We develop a visual analytics system, NewsKaleidoscope, to investigate the how news reporting of events varies. NewsKaleidoscope combines several backend text language processing techniques with a coordinated visualization interface tailored for visualization non-expert users. To robustly evaluate NewsKaleidoscope, we conduct a trio of user studies. (1) A usability study with news novices assesses the overall system and the specific insights promoted for journalism-agnostic users. (2) A follow-up study with news experts assesses the insights promoted for journalism-savvy users. (3) Based on identified system limitations in these two studies, we amend NewsKaleidoscope design and conduct a third study to validate these improvements. Results indicate that, for both news novice and experts, NewsKaleidoscope supports an effective, task-driven workflow for analyzing the diversity of news coverage about events, though journalism expertise has a significant influence on the user insights and takeaways. Our insights while developing and evaluating NewsKaleidoscope can aid future interface designs that combine visualization with natural language processing to analyze coverage diversity in news event reporting.