This research study contributes to understanding the tone in press conferences held by the European Central Bank (ECB). The study applies the Large Language model for sentiment analysis, specifically focusing on the financial context using the finBERT model and most popular lexicon-based methods in finance, the Loughran and McDonald (LM) model. This study is the first to compare these two models in sentiment analysis for the central bank context, specifically for the ECB. Additionally, the results suggest several interesting conclusions. Firstly, the tone in the introductory part of the conferences is related to macro events such as crises, the COVID-19, and the Ukraine war, while the Q&A portion is connected to both shocks and presidential periods. Secondly, there are different communication styles observed in the speeches of the ECB's presidents. These results contribute to our understanding of the tone in the ECB's communications and encourage further research in this area.