Article: Data-centric analytics for ideological sentiment monitoring: fusion of features with optimised attention mechanisms Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.35 pp.18 - 39 Abstract: To address sentiment inaccuracies in civic education contexts, this study proposes a data-driven analytics framework integrating domain-adaptive feature engineering with hierarchical modelling. We construct Chinese social media corpora (Weibo/WeChat) through keyword-filtered crawling and interaction-weighted prioritisation, reducing noise by 42%. A hybrid feature space combines TF-IDF lexical patterns, syntactic POS distributions, Word2Vec/BERT embeddings, and HowNet-derived sentiment features. The core classification employs a Bi-LSTM model with attention mechanisms, dynamically weighting sentiment-bearing terms while compensating for category imbalance via class-weighted cross-entropy loss. Crucially, ideological semantics are mapped through logistic regression classifiers trained on annotated civic categories. Experimental results demonstrate: 1) attention weights effectively localise civic sentiment triggers; 2) domain feature fusion improves classification robustness; 3) semantic mapping achieves 89.2% accuracy in civic topic identification. This methodology enables real-time Kafka-based opinion monitoring while preserving interpretability for educational governance. Inderscience Publishers - linking academia, business and industry through research

Title: Data-centric analytics for ideological sentiment monitoring: fusion of features with optimised attention mechanisms

Authors: Wencong Wu; Juan Wang

Addresses: School of Marxism, Beijing Wuzi University, Beijing, 101126, China ' School of Marxism, Beijing University of Chinese Medicine, Beijing, 100029, China

Abstract: To address sentiment inaccuracies in civic education contexts, this study proposes a data-driven analytics framework integrating domain-adaptive feature engineering with hierarchical modelling. We construct Chinese social media corpora (Weibo/WeChat) through keyword-filtered crawling and interaction-weighted prioritisation, reducing noise by 42%. A hybrid feature space combines TF-IDF lexical patterns, syntactic POS distributions, Word2Vec/BERT embeddings, and HowNet-derived sentiment features. The core classification employs a Bi-LSTM model with attention mechanisms, dynamically weighting sentiment-bearing terms while compensating for category imbalance via class-weighted cross-entropy loss. Crucially, ideological semantics are mapped through logistic regression classifiers trained on annotated civic categories. Experimental results demonstrate: 1) attention weights effectively localise civic sentiment triggers; 2) domain feature fusion improves classification robustness; 3) semantic mapping achieves 89.2% accuracy in civic topic identification. This methodology enables real-time Kafka-based opinion monitoring while preserving interpretability for educational governance.

Keywords: sentiment analysis; TF-IDF; social media monitoring; Bi-LSTM.

DOI: 10.1504/IJICT.2025.149046

International Journal of Information and Communication Technology, 2025 Vol.26 No.35, pp.18 - 39

Received: 02 Jul 2025
Accepted: 16 Aug 2025
Published online: 10 Oct 2025 *

Title: Data-centric analytics for ideological sentiment monitoring: fusion of features with optimised attention mechanisms

Keep up-to-date