Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

FinXABSA: Explainable Finance through Aspect-Based Sentiment Analysis

Keane Ong, Wihan van der Heever, Ranjan Satapathy, Erik Cambria, Gianmarco Mengaldo

TL;DR

This methodology enables an interpretation of the statistical relationship between aspect-based sentiment scores and stock prices, which offers explainability to AI-driven financial decision-making.

Abstract

This paper presents a novel approach for explainability in financial analysis by deriving financially-explainable statistical relationships through aspect-based sentiment analysis, Pearson correlation, Granger causality & uncertainty coefficient. The proposed methodology involves constructing an aspect list from financial literature and applying aspect-based sentiment analysis on social media text to compute sentiment scores for each aspect. Pearson correlation is then applied to uncover financially explainable relationships between aspect sentiment scores and stock prices. Findings for derived relationships are made robust by applying Granger causality to determine the forecasting ability of each aspect sentiment score for stock prices. Finally, an added layer of interpretability is added by evaluating uncertainty coefficient scores between aspect sentiment scores and stock prices. This allows us to determine the aspects whose sentiment scores are most statistically significant for stock prices. Relative to other methods, our approach provides a more informative and accurate understanding of the relationship between sentiment analysis and stock prices. Specifically, this methodology enables an interpretation of the statistical relationship between aspect-based sentiment scores and stock prices, which offers explainability to AI-driven financial decision-making.

FinXABSA: Explainable Finance through Aspect-Based Sentiment Analysis

TL;DR

This methodology enables an interpretation of the statistical relationship between aspect-based sentiment scores and stock prices, which offers explainability to AI-driven financial decision-making.

Abstract

This paper presents a novel approach for explainability in financial analysis by deriving financially-explainable statistical relationships through aspect-based sentiment analysis, Pearson correlation, Granger causality & uncertainty coefficient. The proposed methodology involves constructing an aspect list from financial literature and applying aspect-based sentiment analysis on social media text to compute sentiment scores for each aspect. Pearson correlation is then applied to uncover financially explainable relationships between aspect sentiment scores and stock prices. Findings for derived relationships are made robust by applying Granger causality to determine the forecasting ability of each aspect sentiment score for stock prices. Finally, an added layer of interpretability is added by evaluating uncertainty coefficient scores between aspect sentiment scores and stock prices. This allows us to determine the aspects whose sentiment scores are most statistically significant for stock prices. Relative to other methods, our approach provides a more informative and accurate understanding of the relationship between sentiment analysis and stock prices. Specifically, this methodology enables an interpretation of the statistical relationship between aspect-based sentiment scores and stock prices, which offers explainability to AI-driven financial decision-making.
Paper Structure (24 sections, 6 equations, 18 figures, 3 tables)

This paper contains 24 sections, 6 equations, 18 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Data Collection
  4. Gathering Keywords via 'Keyword Hopping'
  5. Twitter API
  6. Stock Prices
  7. Collecting financial aspects for Sentic GCN
  8. Sentic GCN
  9. Sentiment Scores
  10. Pearson correlation
  11. Granger causality
  12. Uncertainty coefficient
  13. Implementation and Results
  14. Correlation results for sustainable energy stocks
  15. Granger causality results for sustainable energy stocks
  16. ...and 9 more sections

Figures (18)

  • Figure 1: The architecture of the proposed method for XFSA.
  • Figure 2: Sentic GCN architecture liang2022aspect
  • Figure 3: Pearson correlation for lagged positive absolute aspect sentiment scores & sustainable energy stock prices
  • Figure 4: Pearson correlation for lagged negative absolute aspect sentiment scores & sustainable energy stock prices
  • Figure 5: Pearson correlation for lagged positive normalised aspect sentiment scores & sustainable energy stock prices
  • ...and 13 more figures