This is project made for Newsmatics hackathon 2025.
The goal of the project is to analyze using aspect based sentiment analysis models and visualize the sentiment of a commercial product in the news mainly in US. User can see how did the occurrence of their product in news, how it changed by time, filter by different types of media or publishing houses and see the average article in the selected time bracket (day/week/month).
Scripts for analyzing the news are in data_analysis/ with some datasets for showcase and frontend for visualization of the data is in my-app.