PT - JOURNAL ARTICLE AU - Di-Jia Su AU - John M. Mulvey AU - H. Vincent Poor TI - Improving Portfolio Performance via Natural Language Processing Methods AID - 10.3905/jfds.2022.1.088 DP - 2022 Mar 22 TA - The Journal of Financial Data Science PG - jfds.2022.1.088 4099 - https://pm-research.com/content/early/2022/03/22/jfds.2022.1.088.short 4100 - https://pm-research.com/content/early/2022/03/22/jfds.2022.1.088.full AB - Recent natural language processing (NLP) breakthroughs have proven effective for addressing many language-directed tasks, such as completing sentences and addressing search queries. This technology has been successfully implemented by tech firms including Google and others. An important element consists of language embeddings linked to pre-training systems. This article describes NLP concepts and their application to portfolio models via a modern version of sentiment analysis. The authors demonstrate the advantages of employing information from Twitter along with the NLP for constructing a portfolio of stocks, especially during unusual events such as the COVID-19 pandemic.