Agricultural Text Classification Method Based on ERNIE 2.0 and Multi-Feature Dynamic Fusion

Under the rapid development of agricultural information technology, there has been an explosive growth in agricultural Q&A texts on the Internet, making the accurate classification of these texts a critical research topic in this field. However, the dispersion, complexity, and difficulty...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuliang Duan, Yuhai Liu, Zhenjia You, Zhiyao Li
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10858722/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850064259170435072
author Xuliang Duan
Yuhai Liu
Zhenjia You
Zhiyao Li
author_facet Xuliang Duan
Yuhai Liu
Zhenjia You
Zhiyao Li
author_sort Xuliang Duan
collection DOAJ
description Under the rapid development of agricultural information technology, there has been an explosive growth in agricultural Q&A texts on the Internet, making the accurate classification of these texts a critical research topic in this field. However, the dispersion, complexity, and difficulty in collecting agricultural data pose significant challenges to achieving efficient and accurate text classification. To address this, this paper proposes a text classification model based on multi-feature dynamic fusion—ERNIE 2.0_BiGRU_CapsNet_Att. The model uses the ERNIE 2.0 pre-training framework to encode the dataset to learn the dynamic semantic representations of words; it combines Bidirectional Gated Recurrent Units (Bi-GRU) and Capsule Networks to capture high-dimensional sequential and local features of the text; meanwhile, it enriches feature inputs by constructing artificial numerical feature vectors. With the introduction of an attention mechanism, the model can dynamically adjust feature weights to achieve effective multi-feature fusion. We validated the effectiveness of this fusion model on a self-constructed agricultural Q&A dataset. Experimental results, averaged over five runs, show that the proposed model achieved 95.1% precision (±0.1), 94.8% recall (±0.2), and 95.2% F1-score (±0.1), representing a 1.1% improvement in precision, a 0.6% improvement in recall, and a 0.7% improvement in F1-score compared to the best-performing baseline model. These results demonstrate that the proposed model significantly outperforms traditional classification models and achieves robust performance across experiments.
format Article
id doaj-art-df297c8d4f1e49ca993c2fdf06dd59f5
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-df297c8d4f1e49ca993c2fdf06dd59f52025-08-20T02:49:20ZengIEEEIEEE Access2169-35362025-01-0113529595297110.1109/ACCESS.2025.353727710858722Agricultural Text Classification Method Based on ERNIE 2.0 and Multi-Feature Dynamic FusionXuliang Duan0https://orcid.org/0000-0001-7559-346XYuhai Liu1https://orcid.org/0009-0004-3663-3835Zhenjia You2https://orcid.org/0009-0007-4275-5240Zhiyao Li3https://orcid.org/0009-0001-6749-4960School of Information Engineering, Sichuan Agricultural University, Yaan, Sichuan, ChinaSchool of Information Engineering, Sichuan Agricultural University, Yaan, Sichuan, ChinaKey Laboratory of Agricultural Information Engineering in Sichuan Province, Yaan, Sichuan, ChinaKey Laboratory of Agricultural Information Engineering in Sichuan Province, Yaan, Sichuan, ChinaUnder the rapid development of agricultural information technology, there has been an explosive growth in agricultural Q&A texts on the Internet, making the accurate classification of these texts a critical research topic in this field. However, the dispersion, complexity, and difficulty in collecting agricultural data pose significant challenges to achieving efficient and accurate text classification. To address this, this paper proposes a text classification model based on multi-feature dynamic fusion—ERNIE 2.0_BiGRU_CapsNet_Att. The model uses the ERNIE 2.0 pre-training framework to encode the dataset to learn the dynamic semantic representations of words; it combines Bidirectional Gated Recurrent Units (Bi-GRU) and Capsule Networks to capture high-dimensional sequential and local features of the text; meanwhile, it enriches feature inputs by constructing artificial numerical feature vectors. With the introduction of an attention mechanism, the model can dynamically adjust feature weights to achieve effective multi-feature fusion. We validated the effectiveness of this fusion model on a self-constructed agricultural Q&A dataset. Experimental results, averaged over five runs, show that the proposed model achieved 95.1% precision (±0.1), 94.8% recall (±0.2), and 95.2% F1-score (±0.1), representing a 1.1% improvement in precision, a 0.6% improvement in recall, and a 0.7% improvement in F1-score compared to the best-performing baseline model. These results demonstrate that the proposed model significantly outperforms traditional classification models and achieves robust performance across experiments.https://ieeexplore.ieee.org/document/10858722/Agricultural information technologyfusion modelcontextual featurelocal feature
spellingShingle Xuliang Duan
Yuhai Liu
Zhenjia You
Zhiyao Li
Agricultural Text Classification Method Based on ERNIE 2.0 and Multi-Feature Dynamic Fusion
IEEE Access
Agricultural information technology
fusion model
contextual feature
local feature
title Agricultural Text Classification Method Based on ERNIE 2.0 and Multi-Feature Dynamic Fusion
title_full Agricultural Text Classification Method Based on ERNIE 2.0 and Multi-Feature Dynamic Fusion
title_fullStr Agricultural Text Classification Method Based on ERNIE 2.0 and Multi-Feature Dynamic Fusion
title_full_unstemmed Agricultural Text Classification Method Based on ERNIE 2.0 and Multi-Feature Dynamic Fusion
title_short Agricultural Text Classification Method Based on ERNIE 2.0 and Multi-Feature Dynamic Fusion
title_sort agricultural text classification method based on ernie 2 0 and multi feature dynamic fusion
topic Agricultural information technology
fusion model
contextual feature
local feature
url https://ieeexplore.ieee.org/document/10858722/
work_keys_str_mv AT xuliangduan agriculturaltextclassificationmethodbasedonernie20andmultifeaturedynamicfusion
AT yuhailiu agriculturaltextclassificationmethodbasedonernie20andmultifeaturedynamicfusion
AT zhenjiayou agriculturaltextclassificationmethodbasedonernie20andmultifeaturedynamicfusion
AT zhiyaoli agriculturaltextclassificationmethodbasedonernie20andmultifeaturedynamicfusion