# Volatility Prediction using Financial Disclosures Sentiments with Word Embedding-based IR Models

## TL;DR

This paper introduces a novel approach for predicting financial market volatility by combining sentiment analysis of company disclosures with word embedding-enhanced IR models and data fusion techniques, outperforming existing methods.

## Contribution

It presents a new word embedding-based IR model for sentiment analysis of financial disclosures and explores effective fusion with market data for improved volatility prediction.

## Key findings

- Word embedding-based IR models outperform state-of-the-art methods.
- Fusion of textual and market data improves prediction accuracy.
- Sector-specific report characteristics influence volatility forecasts.

## Abstract

Volatility prediction--an essential concept in financial markets--has recently been addressed using sentiment analysis methods. We investigate the sentiment of annual disclosures of companies in stock markets to forecast volatility. We specifically explore the use of recent Information Retrieval (IR) term weighting models that are effectively extended by related terms using word embeddings. In parallel to textual information, factual market data have been widely used as the mainstream approach to forecast market risk. We therefore study different fusion methods to combine text and market data resources. Our word embedding-based approach significantly outperforms state-of-the-art methods. In addition, we investigate the characteristics of the reports of the companies in different financial sectors.