Sentiment Analysis of Economic Text: A Lexicon-based Approach


The goal of this paper is to propose a dictionary specifically designed for textual applications in economics. We construct the dictionary with two important characteristics: i) to have a wide coverage of terms typically used in documents discussing economic and financial concepts, and ii) to provide a human-annotated sentiment score in the range [-1,1]. The sentiment score is a useful feature when the interest is to weight words by their sentiment content as opposed to categorizing terms in positive and negative. We use the dictionary to construct a measure of economic pessimism and show that it captures the business cycle and correlates with measures of economic and financial uncertainty.

working paper SSRN 4106936