Document Type
Poster
Publication Date
Fall 2025
Abstract
When a company releases an earnings call, it can have a big impact on the respective stock market performance of that company. Investors of all types do their best to analyze the data and sentiment provided by the senior executive members to gauge potential future trends of the stock price. Earnings calls are especially important for companies like Nvidia that are making waves in the tech world as AI continues to grow. Previously, sentiment analyses were typically reserved for big companies who specialize in financial quantitative analysis. However, the introduction of Large Language Models (LLMs) such as Gemini, ChatGPT, and Claude provide everyday investors the ability to analyze sentiment of earnings calls without having to have advanced coding or financial knowledge. My project aims to analyze the credibility and capability of the most popular LLMs to investigate if it is possible for everyday people to perform their own sentiment analyses of earnings calls.
Recommended Citation
Hodges, Peyton, "Aspect-Based Sentiment Analysis with LLMs: Are Large Language Models able to accurately score sentiment in company earnings calls?" (2025). IPHS 200: Programming Humanity. Paper 87.
https://digital.kenyon.edu/dh_iphs_prog/87
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.