Fact Check: Analyzing Financial Events from Multilingual News Sources

TL;DR

FactCheck in finance is a web-based tool that aggregates multilingual financial news, extracts events with unsupervised clustering, and assesses article credibility using a transformer-based fact-checker, aiding analysts in understanding complex financial data.

Contribution

This paper introduces FactCheck, a novel system combining multilingual news aggregation, unsupervised event extraction, and transformer-based credibility assessment for financial news analysis.

Findings

FactCheck outperforms baseline models in M&A event fact-checking.

Unsupervised clustering effectively extracts financial events from multilingual sources.

The system provides a comprehensive view of financial news for analysts.

Abstract

The explosion in the sheer magnitude and complexity of financial news data in recent years makes it increasingly challenging for investment analysts to extract valuable insights and perform analysis. We propose FactCheck in finance, a web-based news aggregator with deep learning models, to provide analysts with a holistic view of important financial events from multilingual news sources and extract events using an unsupervised clustering method. A web interface is provided to examine the credibility of news articles using a transformer-based fact-checker. The performance of the fact checker is evaluated using a dataset related to merger and acquisition (M\&A) events and is shown to outperform several strong baselines.