Understanding IMF decision-making with sentiment analysis

Abstract

With the advances in information technologies, the amount of available data on web sources where people express their opinions increases continually. Sentiment analysis is one of the effective tools for decision-makers to gain insights from massive heaps of data. The field of International Organizations, which produces big data in the form of large documents, has significant potential to benefit from sentiment analysis in decision-making. In this paper, we evaluate the effectiveness of different sentiment analysis tools in classifying the sentiments of the International Monetary Fund's (IMF) Executive Board members regarding the design of IMF programs. We introduce a novel dataset, Executive Board meeting minutes of the IMF, in which the sentences are labelled as positive, neutral, or negative. The experimental results demonstrate that sentiment classification with state-of-the-art language models yields high performance on this dataset when trained with domain-specific data.