. (2023). “Integrating Economic Theory, Domain Knowledge and Social Knowledge into Hybrid Sentiment Models for Predicting Crude Oil Markets”. Cognitive Computation
Introduction and Related Work. For several decades, sentiment analysis has been considered a key indicator for assessing market mood and predicting future price changes. Problem Statement. Accurately predicting commodity markets requires an understanding of fundamental market dynamics such as the interplay between supply and demand, which are not considered in standard affective models. Method. This paper introduces two domain-specific affective models, CrudeBERT and CrudeBERT+, that adapt sentiment analysis to the crude oil market by incorporating economic theory with common knowledge of the mentioned entities and social knowledge extracted from Google Trends. Evaluation and Discussion. To evaluate the predictive capabilities of these models, comprehensive experiments were conducted using Dynamic Time Warping to identify the model that best approximates WTI crude oil futures price movements. The evaluation included news headlines and crude oil prices between January 2012 and April 2021. The results showed that CrudeBERT+ outperformed RavenPack, BERT, FinBERT, and early CrudeBERT models during the nine years evaluation period and within most of the individual years that were analyzed. Outlook and Conclusion. The success of the introduced domain-specific affective models demonstrates the potential of integrating economic theory with sentiment analysis and external knowledge sources to improve the predictive power of Financial Sentiment Analysis models. The experiments also confirm that CrudeBERT+ has the potential to provide valuable insights for decision-making in the crude oil market.
Keywords: Affective Classification, Affective Models, Embeddings, Financial Sentiment Analysis, FinBERT, Language Models