Scholarlink

This research delves into the fusion of Generative Pre-Trained Models (GPT) and Discriminative Pre-Trained Language Models in Financial domain for sentiment analysis. Sentiment analysis is very important pillars for understanding user’s opinions in text based data. The synergy of Large Language models’ discriminative power, aims to fine-tune sentiment classification accuracy and nuance. This research explores how Large and Traditional Language models, trained on large corpus, capture context and semantic relationships for sentiment interpretation. This study captures insights into leveraging both generative and discriminative pre-trained Language models to develop sentiment systems, fostering a comprehensive understanding of sentiments in diverse contexts. Employing machine learning, NLP and deep learning models for sentiment analysis assesses language, context, and linguistic cues for accurate sentiment classification. In today’s corporate landscape, developing optimal Generative models for financial news sentiment analysis is crucial for informed decision-making and effective strategy formulation. As technology advances, sentiment analysis will remain integral to understanding public sentiment and shaping strategies across diverse industries.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Leveraging Generative Pre-trained Models and Discriminative Pre-trained Language Models for Sentiment Analysis

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Dhruba Jyoti Bhowmik,
  • Satyajeet Azad,
  • Purnima Kohli,
  • Himanshi Saini,
  • Raj Kumar,
  • Sumant Azad,
  • Amit Singh Bisht

摘要

This research delves into the fusion of Generative Pre-Trained Models (GPT) and Discriminative Pre-Trained Language Models in Financial domain for sentiment analysis. Sentiment analysis is very important pillars for understanding user’s opinions in text based data. The synergy of Large Language models’ discriminative power, aims to fine-tune sentiment classification accuracy and nuance. This research explores how Large and Traditional Language models, trained on large corpus, capture context and semantic relationships for sentiment interpretation. This study captures insights into leveraging both generative and discriminative pre-trained Language models to develop sentiment systems, fostering a comprehensive understanding of sentiments in diverse contexts. Employing machine learning, NLP and deep learning models for sentiment analysis assesses language, context, and linguistic cues for accurate sentiment classification. In today’s corporate landscape, developing optimal Generative models for financial news sentiment analysis is crucial for informed decision-making and effective strategy formulation. As technology advances, sentiment analysis will remain integral to understanding public sentiment and shaping strategies across diverse industries.