Journal of Computational Social Science, Journal Year: 2024, Volume and Issue: 8(1)

Published: Dec. 26, 2024

Abstract In financial markets, the sentiment expressed in news articles plays a pivotal role interpreting and forecasting market trends, which also holds true for task of summarization (FNS). Leveraging AI models to analyze social science data, this paper employs improve FNS effectiveness by introducing novel method that combines polarity extracted from with prompt augmentation techniques ensure generated summaries are emotionally consistent source articles. Specifically, detected sentiments embedded into prompts provide directive instructions model generate summaries. Furthermore, address problem limited large-scale datasets more tailored results, we employed prefix tuning as fine-tuning strategy. Preliminary results indicate our combined methodology outperforms approaches use only tuning. The experimental findings further validate significance analysis FNS, enhances accuracy capturing reflecting sentiment, thereby yielding valuable insights markets. This not improves relevance but ensures their content is news, offering new perspective on summarization.

Language: Английский