PL-FGSA: A Prompt Learning Framework for Fine-Grained Sentiment Analysis Based on MindSpore

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Qin, Zhenkai, He, Jiajing, Fang, Qiao
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910957109772288
author Qin, Zhenkai
He, Jiajing
Fang, Qiao
author_facet Qin, Zhenkai
He, Jiajing
Fang, Qiao
contents Fine-grained sentiment analysis (FGSA) aims to identify sentiment polarity toward specific aspects within a text, enabling more precise opinion mining in domains such as product reviews and social media. However, traditional FGSA approaches often require task-specific architectures and extensive annotated data, limiting their generalization and scalability. To address these challenges, we propose PL-FGSA, a unified prompt learning-based framework implemented using the MindSpore platform, which integrates prompt design with a lightweight TextCNN backbone. Our method reformulates FGSA as a multi-task prompt-augmented generation problem, jointly tackling aspect extraction, sentiment classification, and causal explanation in a unified paradigm. By leveraging prompt-based guidance, PL-FGSA enhances interpretability and achieves strong performance under both full-data and low-resource conditions. Experiments on three benchmark datasets-SST-2, SemEval-2014 Task 4, and MAMS-demonstrate that our model consistently outperforms traditional fine-tuning methods and achieves F1-scores of 0.922, 0.694, and 0.597, respectively. These results validate the effectiveness of prompt-based generalization and highlight the practical value of PL-FGSA for real-world sentiment analysis tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2505_14165
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PL-FGSA: A Prompt Learning Framework for Fine-Grained Sentiment Analysis Based on MindSpore
Qin, Zhenkai
He, Jiajing
Fang, Qiao
Computation and Language
Machine Learning
Fine-grained sentiment analysis (FGSA) aims to identify sentiment polarity toward specific aspects within a text, enabling more precise opinion mining in domains such as product reviews and social media. However, traditional FGSA approaches often require task-specific architectures and extensive annotated data, limiting their generalization and scalability. To address these challenges, we propose PL-FGSA, a unified prompt learning-based framework implemented using the MindSpore platform, which integrates prompt design with a lightweight TextCNN backbone. Our method reformulates FGSA as a multi-task prompt-augmented generation problem, jointly tackling aspect extraction, sentiment classification, and causal explanation in a unified paradigm. By leveraging prompt-based guidance, PL-FGSA enhances interpretability and achieves strong performance under both full-data and low-resource conditions. Experiments on three benchmark datasets-SST-2, SemEval-2014 Task 4, and MAMS-demonstrate that our model consistently outperforms traditional fine-tuning methods and achieves F1-scores of 0.922, 0.694, and 0.597, respectively. These results validate the effectiveness of prompt-based generalization and highlight the practical value of PL-FGSA for real-world sentiment analysis tasks.
title PL-FGSA: A Prompt Learning Framework for Fine-Grained Sentiment Analysis Based on MindSpore
topic Computation and Language
Machine Learning
url https://arxiv.org/abs/2505.14165