Unscrambling Codes: From Hieroglyphs to Market News

This paper reviews some of the steps that paved the way for the development of sentiment analysis (or opinion mining), a technique apparently used by Jim Simons’ Medallion fund for scoring an ‘impossible’ performance: a 66% annual average rate of return in the 31 years between 1988 and 2018. Sentiment analysis is a powerful tool that uses natural language processing (NLP), or computational linguistics, to determine whether a text about a company is positive, negative or neutral and, in a final analysis, to discover stock price patterns. Humans have always used symbols to communicate, plainly or secretively. Here we review some of the methods used in the past centuries, including Egyptians’ hieroglyphs, Julius Caesar’s cipher, Fibonacci’s abbreviations, Leonardo da Vinci’s Mirror Writing, Mary Stuart’s code. The intention is to describe some passages of the long journey made by human beings to arrive at the current sophisticated IT tools for sentiment analysis.