Sentiment in Online Car Auctions Open Access

Peng, Francis (Spring 2023)

Permanent URL:


Existing literature has discussed "sentiment" as an important component of various economic settings such as asset markets or macroeconomic models, but empirical work which investigates sentiment in an auction market has not yet been done. This work investigates the effect of sentiment on the final price of online car auctions. Sentiments of messages displayed in the comments section of auction webpages are defined and quantified by a natural language processing (NLP) sentiment analysis model. It is found that sentiment score has a positive effect on the final price of an auction, but more work may need to be done in order to determine the true causal qualities of the messages which are hidden behind the sentiment.

Table of Contents

1) Introduction

2) Data

3) Methodology

3.1) Sentiment Analysis

3.1.1) Verification of Accuracy

3.2 Regression Analysis

4) Results

4.1) Robustness and Sparsity

5) Discussion

5.1) GPT

About this Honors Thesis

Rights statement
  • Permission granted by the author to include this thesis or dissertation in this repository. All rights reserved by the author. Please contact the author for information regarding the reproduction and use of this thesis or dissertation.
  • English
Research Field
Committee Chair / Thesis Advisor
Committee Members
Last modified

Primary PDF

Supplemental Files