Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Unifying Economic and Language Models for Enhanced Sentiment Analysis of the Oil Market

Himmet Kaplan, Ralf-Peter Mundani, Heiko Rölke, Albert Weichselbraun, Martin Tschudy

TL;DR

The results indicate that CrudeBERT's sentiment scores align more closely with the WTI Futures curve and significantly enhance price predictions, underscoring the crucial role of integrating economic principles into LMs.

Abstract

Crude oil, a critical component of the global economy, has its prices influenced by various factors such as economic trends, political events, and natural disasters. Traditional prediction methods based on historical data have their limits in forecasting, but recent advancements in natural language processing bring new possibilities for event-based analysis. In particular, Language Models (LM) and their advancement, the Generative Pre-trained Transformer (GPT), have shown potential in classifying vast amounts of natural language. However, these LMs often have difficulty with domain-specific terminology, limiting their effectiveness in the crude oil sector. Addressing this gap, we introduce CrudeBERT, a fine-tuned LM specifically for the crude oil market. The results indicate that CrudeBERT's sentiment scores align more closely with the WTI Futures curve and significantly enhance price predictions, underscoring the crucial role of integrating economic principles into LMs.

Unifying Economic and Language Models for Enhanced Sentiment Analysis of the Oil Market

TL;DR

The results indicate that CrudeBERT's sentiment scores align more closely with the WTI Futures curve and significantly enhance price predictions, underscoring the crucial role of integrating economic principles into LMs.

Abstract

Crude oil, a critical component of the global economy, has its prices influenced by various factors such as economic trends, political events, and natural disasters. Traditional prediction methods based on historical data have their limits in forecasting, but recent advancements in natural language processing bring new possibilities for event-based analysis. In particular, Language Models (LM) and their advancement, the Generative Pre-trained Transformer (GPT), have shown potential in classifying vast amounts of natural language. However, these LMs often have difficulty with domain-specific terminology, limiting their effectiveness in the crude oil sector. Addressing this gap, we introduce CrudeBERT, a fine-tuned LM specifically for the crude oil market. The results indicate that CrudeBERT's sentiment scores align more closely with the WTI Futures curve and significantly enhance price predictions, underscoring the crucial role of integrating economic principles into LMs.

Paper Structure

This paper contains 28 sections, 5 equations, 10 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Market Efficiency and the Role of Sentiment Analysis
  4. Evolution of Sentiment Analysis in Finance
  5. The Advent of the Attention Mechanism and Transformers
  6. Language Models for Sentiment Analysis
  7. The Emergence of Large Language Models
  8. Methodology
  9. Datasets and Data Sources
  10. News Dataset
  11. Price Dataset
  12. Sentiment Classifiers
  13. RavenPack Event Sentiment Score
  14. FinBERT
  15. GPT-3.5
  16. ...and 13 more sections

Figures (10)

  • Figure 1: Components of the multi-head attention mechanism vaswani_attention_2017.
  • Figure 2: Process of generating FinBERT kaplan_conference_2023.
  • Figure 3: Illustration of an identified topic and polarity kaplan_conference_2023
  • Figure 4: Categorization of frequent recurring topics based on price theory kaplan_conference_2023.
  • Figure 5: Most recurring topics and their impact on the availability of crude oil.
  • ...and 5 more figures