Summer school

Next, we will see how to analyse a text using Natural Language Processing (NLP) methods and create a full NLP pipeline (cleaning, stop words, Part-of-Speech tagging, Named Entity Recognition, Stemming/Lemmatization) relevant to a given research project. We will apply this to the press conferences made by the European Central Bank to show how it is possible to give structure to unstructured data. The next session will be dedicated to sentiment analysis and will present the different methods (dictionary approach and machine learning) with an application on a database of media articles. The fourth session will be devoted to machine learning using text as data with an application on StockTwits data (asset pricing). In the last session, we will introduce methods of textual analysis on unsupervised data (topic modelling and transformers). We will perform an application of a Latent Dirichlet Allocation on a large corpus of Glassdoor reviews.

For the different sessions, we will first present both the related theories and methods – in a language accessible to non-mathematicians – and their latest applications in the economic and financial literature. We will then study and share with the participants all scripts and codes to realize different tasks in Python. We will also offer participants the opportunity to present their research and/or projects, and if possible, we will assist them with their projects – both on the data collection side and on the data analysis side.