Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI.
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,...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2025-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://doi.org/10.1371/journal.pone.0326602 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1839647601743364096 |
|---|---|
| author | Jinghua Wu Peng Qiu Xun Jia |
| author_facet | Jinghua Wu Peng Qiu Xun Jia |
| author_sort | Jinghua Wu |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-4b78d7f151c74c94b4e4c1f429a99af7 |
| institution | Matheson Library |
| issn | 1932-6203 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-4b78d7f151c74c94b4e4c1f429a99af72025-06-30T05:31:45ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01206e032660210.1371/journal.pone.0326602Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI.Jinghua WuPeng QiuXun JiaThe 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.https://doi.org/10.1371/journal.pone.0326602 |
| spellingShingle | Jinghua Wu Peng Qiu Xun Jia Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI. PLoS ONE |
| title | Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI. |
| title_full | Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI. |
| title_fullStr | Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI. |
| title_full_unstemmed | Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI. |
| title_short | Constructing a domain-specific sentiment lexicon for agricultural product reviews using BERT and SO-PMI. |
| title_sort | constructing a domain specific sentiment lexicon for agricultural product reviews using bert and so pmi |
| url | https://doi.org/10.1371/journal.pone.0326602 |
| work_keys_str_mv | AT jinghuawu constructingadomainspecificsentimentlexiconforagriculturalproductreviewsusingbertandsopmi AT pengqiu constructingadomainspecificsentimentlexiconforagriculturalproductreviewsusingbertandsopmi AT xunjia constructingadomainspecificsentimentlexiconforagriculturalproductreviewsusingbertandsopmi |