@article{2026ijdsa,
 abstract = {Sentiment analysis is vital for understanding market dynamics and formulating informed investing strategies, especially in volatile financial conditions. This study advances target-based financial sentiment analysis (TBFSA) by rigorously evaluating the efficacy of Large Language Models (LLMs) in zero-shot and few-shot learning contexts. We compare cutting-edge generative LLMs, such as ChatGPT-4o, ChatGPT-4, ChatGPT-o1, DeepSeek-R1, Llama-3-8B, Gemma-2-9B, and Gemma-2-27B, with conventional lexicon-based tools (VADER and TextBlob) and discriminative transformer-based models (FinBERT, FinBERT-Tone, DistilFinRoBERTa, and Deberta-v3-base-absa-v1.1). Our analysis utilizes a newly curated dataset of 1,162 manually annotated Bloomberg news articles, designed explicitly for TBFSA (due to copyright constraints, only URLs are publicly released, with full news content accessible through a Bloomberg Terminal). The findings indicate that LLMs, particularly DeepSeek-R1 and ChatGPT variants (especially ChatGPT-o1), outperform lexicon-based approaches and discriminative transformer-based models across all evaluation metrics, without requiring additional training or task-specific fine-tuning. In addition, these models achieve the highest directional accuracy and statistically significant correlations with contemporaneous short-term market returns within the studied sample, demonstrating their ability to capture sentiment signals that are aligned with observed market movements. The study establishes generative LLMs as a scalable and cost-effective method for target-level sentiment analysis, relieving the need for expensive, rigorous fine-tuning. The research provides valuable insights, enabling institutions to use unstructured textual data effectively for sentiment monitoring, market analysis, and risk assessment.},
 author = {Iftikhar Muhammad and Marco Rospocher and Timotej Knez and Slavko {\v Z}itnik},
 bdsk-url-1 = {https://doi.org/10.1007/s41060-026-01201-x},
 date = {2026/07/02},
 date-added = {2026-07-02 21:46:19 +0200},
 date-modified = {2026-07-02 21:47:12 +0200},
 doi = {10.1007/s41060-026-01201-x},
 isbn = {2364-4168},
 journal = {International Journal of Data Science and Analytics},
 number = {1},
 pages = {217},
 title = {Benchmarking large language models for target-based financial sentiment and stock return},
 url = {https://doi.org/10.1007/s41060-026-01201-x},
 volume = {22},
 year = {2026}
}