Dataharvest 2024 - the European Investigative Journalism Conference

This workshop is suitable for those who want to automate the work of extracting information from an array of texts. You will learn how to use the OpenAI API to extract named entities (names, city names, streets, numbers, emails, etc.). We will also compare the results of OpenAI with free Python libraries for processing human language. Participants in this session will get acquainted with the capabilities of OpenAL and Python libraries for extracting named entities. In the future, this will simplify and speed up your work with text data. The participants of the master class must have at least basic Python programming skills. They should also be interested in exploring the possibilities of extracting named entities from texts. If you are bringing your own computers to the session, you should have Python installed (from 3.8 version), Jupyter Notebook installed, and a registered account on Open AI platform https://platform.openai.com/