Financial Sentiment Analysis

Towards Temporal-Aware Multi-Modal Retrieval Augmented Generation in Finance ArXiv ID: 2503.05185 “View on arXiv” Authors: Unknown Abstract Finance decision-making often relies on in-depth data analysis across various data sources, including financial tables, news articles, stock prices, etc. In this work, we introduce FinTMMBench, the first comprehensive benchmark for evaluating temporal-aware multi-modal Retrieval-Augmented Generation (RAG) systems in finance. Built from heterologous data of NASDAQ 100 companies, FinTMMBench offers three significant advantages. 1) Multi-modal Corpus: It encompasses a hybrid of financial tables, news articles, daily stock prices, and visual technical charts as the corpus. 2) Temporal-aware Questions: Each question requires the retrieval and interpretation of its relevant data over a specific time period, including daily, weekly, monthly, quarterly, and annual periods. 3) Diverse Financial Analysis Tasks: The questions involve 10 different financial analysis tasks designed by domain experts, including information extraction, trend analysis, sentiment analysis and event detection, etc. We further propose a novel TMMHybridRAG method, which first leverages LLMs to convert data from other modalities (e.g., tabular, visual and time-series data) into textual format and then incorporates temporal information in each node when constructing graphs and dense indexes. Its effectiveness has been validated in extensive experiments, but notable gaps remain, highlighting the challenges presented by our FinTMMBench. ...

Large language models in finance : what is financial sentiment? ArXiv ID: 2503.03612 “View on arXiv” Authors: Unknown Abstract Financial sentiment has become a crucial yet complex concept in finance, increasingly used in market forecasting and investment strategies. Despite its growing importance, there remains a need to define and understand what financial sentiment truly represents and how it can be effectively measured. We explore the nature of financial sentiment and investigate how large language models (LLMs) contribute to its estimation. We trace the evolution of sentiment measurement in finance, from market-based and lexicon-based methods to advanced natural language processing techniques. The emergence of LLMs has significantly enhanced sentiment analysis, providing deeper contextual understanding and greater accuracy in extracting sentiment from financial text. We examine how BERT-based models, such as RoBERTa and FinBERT, are optimized for structured sentiment classification, while GPT-based models, including GPT-4, OPT, and LLaMA, excel in financial text generation and real-time sentiment interpretation. A comparative analysis of bidirectional and autoregressive transformer architectures highlights their respective roles in investor sentiment analysis, algorithmic trading, and financial decision-making. By exploring what financial sentiment is and how it is estimated within LLMs, we provide insights into the growing role of AI-driven sentiment analysis in finance. ...

Market-Derived Financial Sentiment Analysis: Context-Aware Language Models for Crypto Forecasting ArXiv ID: 2502.14897 “View on arXiv” Authors: Unknown Abstract Financial Sentiment Analysis (FSA) traditionally relies on human-annotated sentiment labels to infer investor sentiment and forecast market movements. However, inferring the potential market impact of words based on their human-perceived intentions is inherently challenging. We hypothesize that the historical market reactions to words, offer a more reliable indicator of their potential impact on markets than subjective sentiment interpretations by human annotators. To test this hypothesis, a market-derived labeling approach is proposed to assign tweet labels based on ensuing short-term price trends, enabling the language model to capture the relationship between textual signals and market dynamics directly. A domain-specific language model was fine-tuned on these labels, achieving up to an 11% improvement in short-term trend prediction accuracy over traditional sentiment-based benchmarks. Moreover, by incorporating market and temporal context through prompt-tuning, the proposed context-aware language model demonstrated an accuracy of 89.6% on a curated dataset of 227 impactful Bitcoin-related news events with significant market impacts. Aggregating daily tweet predictions into trading signals, our method outperformed traditional fusion models (which combine sentiment-based and price-based predictions). It challenged the assumption that sentiment-based signals are inferior to price-based predictions in forecasting market movements. Backtesting these signals across three distinct market regimes yielded robust Sharpe ratios of up to 5.07 in trending markets and 3.73 in neutral markets. Our findings demonstrate that language models can serve as effective short-term market predictors. This paradigm shift underscores the untapped capabilities of language models in financial decision-making and opens new avenues for market prediction applications. ...

RAG-IT: Retrieval-Augmented Instruction Tuning for Automated Financial Analysis – A Case Study for the Semiconductor Sector ArXiv ID: 2412.08179 “View on arXiv” Authors: Unknown Abstract Financial analysis relies heavily on the interpretation of earnings reports to assess company performance and guide decision-making. Traditional methods for generating such analyzes require significant financial expertise and are often time-consuming. With the rapid advancement of Large Language Models (LLMs), domain-specific adaptations have emerged for financial tasks such as sentiment analysis and entity recognition. This paper introduces RAG-IT (Retrieval-Augmented Instruction Tuning), a novel framework designed to automate the generation of earnings report analysis through an LLM fine-tuned specifically for the financial domain. Our approach integrates retrieval augmentation with instruction-based fine-tuning to enhance factual accuracy, contextual relevance, and domain adaptability. We construct a sector-specific financial instruction dataset derived from semiconductor industry documents to guide the LLM adaptation to specialized financial reasoning. Using NVIDIA, AMD, and Broadcom as representative companies, our case study demonstrates that RAG-IT substantially improves a general-purpose open-source LLM and achieves performance comparable to commercial systems like GPT-3.5 on financial report generation tasks. This research highlights the potential of retrieval-augmented instruction tuning to streamline and elevate financial analysis automation, advancing the broader field of intelligent financial reporting. ...

Combining Financial Data and News Articles for Stock Price Movement Prediction Using Large Language Models ArXiv ID: 2411.01368 “View on arXiv” Authors: Unknown Abstract Predicting financial markets and stock price movements requires analyzing a company’s performance, historic price movements, industry-specific events alongside the influence of human factors such as social media and press coverage. We assume that financial reports (such as income statements, balance sheets, and cash flow statements), historical price data, and recent news articles can collectively represent aforementioned factors. We combine financial data in tabular format with textual news articles and employ pre-trained Large Language Models (LLMs) to predict market movements. Recent research in LLMs has demonstrated that they are able to perform both tabular and text classification tasks, making them our primary model to classify the multi-modal data. We utilize retrieval augmentation techniques to retrieve and attach relevant chunks of news articles to financial metrics related to a company and prompt the LLMs in zero, two, and four-shot settings. Our dataset contains news articles collected from different sources, historic stock price, and financial report data for 20 companies with the highest trading volume across different industries in the stock market. We utilized recently released language models for our LLM-based classifier, including GPT- 3 and 4, and LLaMA- 2 and 3 models. We introduce an LLM-based classifier capable of performing classification tasks using combination of tabular (structured) and textual (unstructured) data. By using this model, we predicted the movement of a given stock’s price in our dataset with a weighted F1-score of 58.5% and 59.1% and Matthews Correlation Coefficient of 0.175 for both 3-month and 6-month periods. ...

Evaluating Company-specific Biases in Financial Sentiment Analysis using Large Language Models ArXiv ID: 2411.00420 “View on arXiv” Authors: Unknown Abstract This study aims to evaluate the sentiment of financial texts using large language models~(LLMs) and to empirically determine whether LLMs exhibit company-specific biases in sentiment analysis. Specifically, we examine the impact of general knowledge about firms on the sentiment measurement of texts by LLMs. Firstly, we compare the sentiment scores of financial texts by LLMs when the company name is explicitly included in the prompt versus when it is not. We define and quantify company-specific bias as the difference between these scores. Next, we construct an economic model to theoretically evaluate the impact of sentiment bias on investor behavior. This model helps us understand how biased LLM investments, when widespread, can distort stock prices. This implies the potential impact on stock prices if investments driven by biased LLMs become dominant in the future. Finally, we conduct an empirical analysis using Japanese financial text data to examine the relationship between firm-specific sentiment bias, corporate characteristics, and stock performance. ...

MANA-Net: Mitigating Aggregated Sentiment Homogenization with News Weighting for Enhanced Market Prediction ArXiv ID: 2409.05698 “View on arXiv” Authors: Unknown Abstract It is widely acknowledged that extracting market sentiments from news data benefits market predictions. However, existing methods of using financial sentiments remain simplistic, relying on equal-weight and static aggregation to manage sentiments from multiple news items. This leads to a critical issue termed ``Aggregated Sentiment Homogenization’’, which has been explored through our analysis of a large financial news dataset from industry practice. This phenomenon occurs when aggregating numerous sentiments, causing representations to converge towards the mean values of sentiment distributions and thereby smoothing out unique and important information. Consequently, the aggregated sentiment representations lose much predictive value of news data. To address this problem, we introduce the Market Attention-weighted News Aggregation Network (MANA-Net), a novel method that leverages a dynamic market-news attention mechanism to aggregate news sentiments for market prediction. MANA-Net learns the relevance of news sentiments to price changes and assigns varying weights to individual news items. By integrating the news aggregation step into the networks for market prediction, MANA-Net allows for trainable sentiment representations that are optimized directly for prediction. We evaluate MANA-Net using the S&P 500 and NASDAQ 100 indices, along with financial news spanning from 2003 to 2018. Experimental results demonstrate that MANA-Net outperforms various recent market prediction methods, enhancing Profit & Loss by 1.1% and the daily Sharpe ratio by 0.252. ...

CatMemo at the FinLLM Challenge Task: Fine-Tuning Large Language Models using Data Fusion in Financial Applications ArXiv ID: 2407.01953 “View on arXiv” Authors: Unknown Abstract The integration of Large Language Models (LLMs) into financial analysis has garnered significant attention in the NLP community. This paper presents our solution to IJCAI-2024 FinLLM challenge, investigating the capabilities of LLMs within three critical areas of financial tasks: financial classification, financial text summarization, and single stock trading. We adopted Llama3-8B and Mistral-7B as base models, fine-tuning them through Parameter Efficient Fine-Tuning (PEFT) and Low-Rank Adaptation (LoRA) approaches. To enhance model performance, we combine datasets from task 1 and task 2 for data fusion. Our approach aims to tackle these diverse tasks in a comprehensive and integrated manner, showcasing LLMs’ capacity to address diverse and complex financial tasks with improved accuracy and decision-making capabilities. ...

FNSPID: A Comprehensive Financial News Dataset in Time Series ArXiv ID: 2402.06698 “View on arXiv” Authors: Unknown Abstract Financial market predictions utilize historical data to anticipate future stock prices and market trends. Traditionally, these predictions have focused on the statistical analysis of quantitative factors, such as stock prices, trading volumes, inflation rates, and changes in industrial production. Recent advancements in large language models motivate the integrated financial analysis of both sentiment data, particularly market news, and numerical factors. Nonetheless, this methodology frequently encounters constraints due to the paucity of extensive datasets that amalgamate both quantitative and qualitative sentiment analyses. To address this challenge, we introduce a large-scale financial dataset, namely, Financial News and Stock Price Integration Dataset (FNSPID). It comprises 29.7 million stock prices and 15.7 million time-aligned financial news records for 4,775 S&P500 companies, covering the period from 1999 to 2023, sourced from 4 stock market news websites. We demonstrate that FNSPID excels existing stock market datasets in scale and diversity while uniquely incorporating sentiment information. Through financial analysis experiments on FNSPID, we propose: (1) the dataset’s size and quality significantly boost market prediction accuracy; (2) adding sentiment scores modestly enhances performance on the transformer-based model; (3) a reproducible procedure that can update the dataset. Completed work, code, documentation, and examples are available at github.com/Zdong104/FNSPID. FNSPID offers unprecedented opportunities for the financial research community to advance predictive modeling and analysis. ...

BioFinBERT: Finetuning Large Language Models (LLMs) to Analyze Sentiment of Press Releases and Financial Text Around Inflection Points of Biotech Stocks ArXiv ID: 2401.11011 “View on arXiv” Authors: Unknown Abstract Large language models (LLMs) are deep learning algorithms being used to perform natural language processing tasks in various fields, from social sciences to finance and biomedical sciences. Developing and training a new LLM can be very computationally expensive, so it is becoming a common practice to take existing LLMs and finetune them with carefully curated datasets for desired applications in different fields. Here, we present BioFinBERT, a finetuned LLM to perform financial sentiment analysis of public text associated with stocks of companies in the biotechnology sector. The stocks of biotech companies developing highly innovative and risky therapeutic drugs tend to respond very positively or negatively upon a successful or failed clinical readout or regulatory approval of their drug, respectively. These clinical or regulatory results are disclosed by the biotech companies via press releases, which are followed by a significant stock response in many cases. In our attempt to design a LLM capable of analyzing the sentiment of these press releases,we first finetuned BioBERT, a biomedical language representation model designed for biomedical text mining, using financial textual databases. Our finetuned model, termed BioFinBERT, was then used to perform financial sentiment analysis of various biotech-related press releases and financial text around inflection points that significantly affected the price of biotech stocks. ...