CLOct 19, 2023

FinEntity: Entity-level Sentiment Classification for Financial Texts

arXiv:2310.12406v1135 citationsh-index: 12Has Code
Originality Synthesis-oriented
AI Analysis

This work addresses the problem of accurately assessing sentiment toward specific financial entities for researchers and practitioners in finance, but it is incremental as it primarily introduces a new dataset rather than a novel method.

The authors tackled the lack of a publicly available dataset for entity-level sentiment analysis in financial texts by introducing FinEntity, a dataset that annotates financial entity spans and their sentiment in financial news, and they benchmarked pre-trained models like BERT and ChatGPT on this task, achieving competitive results with BERT-based models showing up to 85% accuracy.

In the financial domain, conducting entity-level sentiment analysis is crucial for accurately assessing the sentiment directed toward a specific financial entity. To our knowledge, no publicly available dataset currently exists for this purpose. In this work, we introduce an entity-level sentiment classification dataset, called \textbf{FinEntity}, that annotates financial entity spans and their sentiment (positive, neutral, and negative) in financial news. We document the dataset construction process in the paper. Additionally, we benchmark several pre-trained models (BERT, FinBERT, etc.) and ChatGPT on entity-level sentiment classification. In a case study, we demonstrate the practical utility of using FinEntity in monitoring cryptocurrency markets. The data and code of FinEntity is available at \url{https://github.com/yixuantt/FinEntity}

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes