Leveraging Adapter Configurations for Sentiment Classification in Financial Text Analysis
- DOI
- 10.2991/978-94-6463-787-8_51How to use a DOI?
- Keywords
- Adapter Configurations; XG-Boost; Receiver Operating Characteristic (ROC); Captum; Financial Analysis
- Abstract
This review investigates the use of connector design sin models for opinion grouping within financial text data, with a specific focus on Securities and Exchange Commission (SEC) filings and analyst reports. We evaluate several connector strategies, including LoRAConfig, UniPELTConfig, and MAMConfig, to identify optimal designs that balance performance and computational efficiency. The experiments follow a structured analysis approach, comparing various models and configurations to determine the best solution for analyzing financial reports. Our finding semphasize the importance of using Receiver Operating Characteristic (ROC) curves for comprehensive model evaluation. They reveal that traditional benchmarks, such as analyst forecasts and XG-Boost, often underperform compared to random predictions. By employing feature attribution through Captum, we provide insights into the impact of specific textual features on model predictions. Ultimately, this research highlights the potential of connector-based approaches in enhancing sentiment analysis within the financial domain, paving the way for more accurate automated financial assessments.
- Copyright
- © 2025 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Sachin Babu Antony AU - Pravallika Papineni PY - 2025 DA - 2025/07/17 TI - Leveraging Adapter Configurations for Sentiment Classification in Financial Text Analysis BT - Proceedings of the Recent Advances in Artificial Intelligence for Sustainable Development (RAISD 2025) PB - Atlantis Press SP - 671 EP - 685 SN - 1951-6851 UR - https://doi.org/10.2991/978-94-6463-787-8_51 DO - 10.2991/978-94-6463-787-8_51 ID - Antony2025 ER -