University of Twente Student Theses

Login
As of Friday, 8 August 2025, the current Student Theses repository is no longer available for thesis uploads. A new Student Theses repository will be available starting Friday, 15 August 2025.

Sentiment of S&P 500 companies’ earnings conference calls during COVID-19 and its effect on stock performance

Oosterink, Sybren (2025) Sentiment of S&P 500 companies’ earnings conference calls during COVID-19 and its effect on stock performance.

[img] PDF
1MB
Abstract:The COVID-19 pandemic sparked a global crisis and introduced unprecedented uncertainty into the global markets. This research investigates the dynamics of sentiment expressed in earnings conference calls of S&P 500 companies during the COVID-19 pandemic and how it relates to stock performance. The importance of textual data in investor communication during extreme conditions is explored by focusing on three areas: differences in sentiment across the 11 S&P 500 sectors, sentiment changes over time and textual sentiment as a predictor of stock returns. A sentiment score was created using the Loughran-McDonald financial dictionary, extracting sentiment data from both the presentation and Q&A sections of earnings call transcripts from 2019 to 2023. Monthly stock returns were calculated and integrated with sentiment data of the S&P 500 and its sectors. Moreover, statistical tests were performed to examine sectoral sentiment variations, differences in sentiment between time periods and a correlation between sentiment and stock performance. Results show significant sectoral differences, with financials, real estate, utilities and materials expressing more negative sentiment during the pandemic. Sentiment also dropped sharply in the early phase of the pandemic (2020), but recovered and stabilized rapidly thereafter. However, no significant correlation was found between sentiment and next month’s return. These findings suggest that while earnings call sentiment reflects patterns across sectors and time, it does not provide a reliable predictive power for returns on a monthly basis. Nevertheless, this research presents opportunities for future research, including investigation of immediate returns and the potential of detecting irrational behavior during distress.
Item Type:Essay (Bachelor)
Faculty:BMS: Behavioural, Management and Social Sciences
Subject:83 economics, 85 business administration, organizational science
Programme:International Business Administration BSc (50952)
Link to this item:https://purl.utwente.nl/essays/106840
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page