Scholarlink

This chapter examines and compares various approaches to analyzing earnings call transcripts. Earnings call transcripts provide crucial insights into company performance, but manual analysis is tedious and subjective. Utilizing natural language models offers efficient, accurate analysis, benefiting financial professionals and decision-makers. This chapter reviews various natural language models and approaches for concept extraction, specifically for earnings calls transcripts. The models explored in this survey include Latent Dirichlet Allocation (LDA), KeyBERT, BERTopic, and Large Language models (GPT-3.5, Llama 2). It underscores the value of automated analysis in data-driven financial decision-making.

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

Comparative Analysis of Different Concept Extraction Methods on Earnings Call Transcripts

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Samir Hendre,
  • Siddhesh Pande,
  • Shashank Rathi,
  • Atharva Soman,
  • Sameer Memon,
  • Aditya Kulkarni,
  • Raghavachari Madhavan,
  • Dipali Kadam

摘要

This chapter examines and compares various approaches to analyzing earnings call transcripts. Earnings call transcripts provide crucial insights into company performance, but manual analysis is tedious and subjective. Utilizing natural language models offers efficient, accurate analysis, benefiting financial professionals and decision-makers. This chapter reviews various natural language models and approaches for concept extraction, specifically for earnings calls transcripts. The models explored in this survey include Latent Dirichlet Allocation (LDA), KeyBERT, BERTopic, and Large Language models (GPT-3.5, Llama 2). It underscores the value of automated analysis in data-driven financial decision-making.