arbiter
JournalsAccount

Emotion Analysis and Topic Modelling of Supply Chain Discussion during the COVID-19 Pandemic

Suhong Li et al.

American Business Review2025https://doi.org/10.37625/abr.28.1.203-222article
ABDC B
Weight
0.50

Abstract

This study aims to investigate the supply chain discussion during the COVID-19 pandemic using the supply chain tweets collected between March 2020 and May 2022 globally. The findings reveal an evolving sentiment trajectory: while the users’ sentiment remained neutral in 2020 and 2021, a negative sentiment surged starting in January 2022. Moreover, an emotion analysis indicates a mix of sadness and optimism among Twitter users, with anger gradually intensifying from June 2021 onward. Furthermore, topic modeling reveals distinct themes discussed each year. In 2020, major topics centered around the government’s response to COVID-19, food and medical supply chain crises. By 2021, discussions shifted to inflation/gas prices, government handling of supply chain crisis, and vaccination/recovery efforts. The first half of 2022 witnessed dominant discussions on the war in Ukraine, inflation and human rights, the US election and border crossing issues. The implications of these findings were discussed at the end.

Open via your library →

Cite this paper

https://doi.org/https://doi.org/10.37625/abr.28.1.203-222

Or copy a formatted citation

@article{suhong2025,
  title        = {{Emotion Analysis and Topic Modelling of Supply Chain Discussion during the COVID-19 Pandemic}},
  author       = {Suhong Li et al.},
  journal      = {American Business Review},
  year         = {2025},
  doi          = {https://doi.org/https://doi.org/10.37625/abr.28.1.203-222},
}

Paste directly into BibTeX, Zotero, or your reference manager.

Flag this paper

Emotion Analysis and Topic Modelling of Supply Chain Discussion during the COVID-19 Pandemic

Flags are reviewed by the Arbiter methodology team within 5 business days.

Evidence weight

0.50

Balanced mode · F 0.40 / M 0.15 / V 0.05 / R 0.40

F · citation impact0.50 × 0.4 = 0.20
M · momentum0.50 × 0.15 = 0.07
V · venue signal0.50 × 0.05 = 0.03
R · text relevance †0.50 × 0.4 = 0.20

† Text relevance is estimated at 0.50 on the detail page — for your query’s actual relevance score, open this paper from a search result.