The original aim was to visualize the changes in Russian news topics within time in order to get insights about how what they write corresponds to what actually happens.
During project development, we found a lot of useful techniques that are appliable to arbitrary texts. So, now we still consider news as a main object of the application, but we develop a general exploratory tool for text with end-to-end processing, from raw documents to insightful visualizations.
Concept and almost like the current prototype looks like
Who we need in the project:
1. basically anyone, who want to contribute,
2. but especially people who know how (or want to learn) to make a web-app around a data-science project.
3. people with experience in ETL pipelines.
