Article: Aspect-level sentiment classification with emotional keywords attention network Journal: International Journal of Computational Intelligence Studies (IJCISTUDIES) 2026 Vol.13 No.5 pp.1 - 13 Abstract: Aspect-level sentiment classification (ASC) aims to uncover the sentiment polarity expressed towards specific entities in market analysis. Despite its popularity, two fundamental obstacles persist: 1) manual annotation is notoriously labour-intensive, resulting in data-scarce regimes where models struggle to acquire sufficient knowledge; 2) accurate sentiment inference demands rich prior semantic knowledge that is difficult to acquire even when large corpora are available. To address these challenges, we first automatically identify emotion-bearing keywords for each aspect and summarise their distributional properties. We then introduce a convolutional neural network enhanced with an attention mechanism that explicitly highlights these keywords through an emotion-keyword mask, thereby guiding the model to focus on sentiment-relevant context. Extensive experiments on standard SemEval benchmarks show that the proposed mask consistently improves performance and that our overall approach achieves competitive results against recent strong baselines. Inderscience Publishers - linking academia, business and industry through research

Title: Aspect-level sentiment classification with emotional keywords attention network

Authors: Zhifeng Yuan; Jin Yuan

Addresses: Puyang Vocational and Technical College, Economic and Technological Development Zone, No. 249, West Huanghe Road, Puyang City, Henan Province, China ' Lenovo, Software Park, Houchangcun Road, Haidian District, Beijing, China

Abstract: Aspect-level sentiment classification (ASC) aims to uncover the sentiment polarity expressed towards specific entities in market analysis. Despite its popularity, two fundamental obstacles persist: 1) manual annotation is notoriously labour-intensive, resulting in data-scarce regimes where models struggle to acquire sufficient knowledge; 2) accurate sentiment inference demands rich prior semantic knowledge that is difficult to acquire even when large corpora are available. To address these challenges, we first automatically identify emotion-bearing keywords for each aspect and summarise their distributional properties. We then introduce a convolutional neural network enhanced with an attention mechanism that explicitly highlights these keywords through an emotion-keyword mask, thereby guiding the model to focus on sentiment-relevant context. Extensive experiments on standard SemEval benchmarks show that the proposed mask consistently improves performance and that our overall approach achieves competitive results against recent strong baselines.

Keywords: attention network; sentiment classification; natural language processing.

DOI: 10.1504/IJCISTUDIES.2026.152417

International Journal of Computational Intelligence Studies, 2026 Vol.13 No.5, pp.1 - 13

Accepted: 22 Nov 2025
Published online: 18 Mar 2026 *

Title: Aspect-level sentiment classification with emotional keywords attention network

Keep up-to-date