Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI
PLOS One · 26.06.2025 · 20 (6) · e0326602
DOI: 10.1371/journal.pone.0326602 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 26.06.2025. Verfasst von Jinghua Wu und 2 weiteren Autor:innen. Beteiligte Einrichtung: College of Information Engineering, Sichuan Agricultural University, Sichuan Ya'an, China. Hauptthemen laut MEDLINE: Agriculture. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research on Mechanisms and Path of Agricultural Digitization.
Abstract (Originalsprache)
The absence of a sentiment lexicon tailored to agricultural product reviews presents significant challenges for accurate sentiment analysis in this domain. Existing general-purpose lexicons, such as NTUSD, HOWNET, and BosonNLP, fail to capture the unique linguistic features of agricultural reviews, leading to suboptimal classification performance. To address this gap, this study constructs the BSTS sentiment lexicon, using a dataset of 19,843 preprocessed reviews from JD.com. Positive and negative seed words were extracted through BERT-based Term Frequency (TF) analysis, and the SO-PMI algorithm was applied to calculate sentiment scores for candidate words. By determining an optimal threshold, a balanced and effective lexicon was developed. Experimental results demonstrate that the BSTS lexicon outperforms existing lexicons in sentiment classification, achieving precision, recall, and F1 scores of 85.21%, 91.92%, and 88.44%, respectively. Furthermore, additional experiments on Taobao’s agricultural product reviews confirmed the lexicon’s robustness, with performance metrics of 93.28% precision and 87.34% F1 score, highlighting its effectiveness across different e-commerce platforms. The BSTS lexicon significantly improves sentiment classification in the agricultural domain, offering a reliable and domain-specific tool for sentiment analysis in agricultural product reviews.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- College of Information Engineering, Sichuan Agricultural University, Sichuan Ya'an, China.
ORCID-Profile: Jinghua Wu
Förderung
- Research on Mechanisms and Path of Agricultural Digitization
Zitieren
APA
Wu, J., Qiu, P., & Jia, X. (2025). Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI. PLOS One, 20(6), e0326602. https://doi.org/10.1371/journal.pone.0326602
Vancouver
Wu J, Qiu P, Jia X. Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI. PLOS One. 2025;20(6):e0326602. doi:10.1371/journal.pone.0326602
BibTeX
@article{Wu2025,
author = {Wu, Jinghua and Qiu, Peng and Jia, Xun},
title = {Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI},
journal = {PLOS One},
year = {2025},
volume = {20},
number = {6},
pages = {e0326602},
doi = {10.1371/journal.pone.0326602}
}
EUVIMED