Artifacts of Crisis: Textual Analysis of Euromaidan

Abstract

We analyze three textual data streams to characterize the change that occurred during the Ukrainian revolution of 2014. These data streams include legislative bill text, posts on Ukrainian political blogs, and Twitter data. Each stream provides a different perspective: politicians, local citizens, and global citizens. It is apparent that bill production stalled early on in the demonstrations, and that the post-revolution government quickly began voting on bills. Topic analysis of blogs and tweets revealed growing interest in Ukraine following the march on the legislature. Interest in Ukraine eventually overtook that of the conflict in the Middle East, before dying back down in the following month. Our results suggest that a stall in bill production may be an early indicator of dysfunction in the government, while spikes in Twitter activity can be seen almost immediately after the event. This effect is true for blogs as well, although for a prolonged period, implying a more detailed discourse about the event.

Publication
In SBP-BRiMS 2020
Tom Magelinski, PhD
Tom Magelinski, PhD
Senior Data Scientist - Information Extraction and Generative AI

I build AI systems that help domain experts understand vast amounts of data through state-of-the-art techniques from natural language processing, generative modeling, graph ML, and network science. I’m particularly interested researching and developing techniques to combine NLP and graph-based approaches to capture complex relationships in unstructured data.

Related