Article: Analysis of English sentiment semantic evolution based on BERT and dynamic word embeddings Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.37 pp.75 - 90 Abstract: To address the challenge of accurately capturing the evolutionary trends of English sentiment semantics in large-scale time-series text data, this study proposes a sentiment semantic evolution analysis method by fusing BERT and dynamic word embeddings. First, the overall framework of the fusion model is constructed, including the data pre-processing layer, feature extraction layer, fusion layer, and application layer. Second, based on the theory of semantic change, the sentiment semantic evolution analysis index system is determined, covering temporal stability, contextual similarity, and sentiment polarity variation. Key features of sentiment semantics are extracted from time-slice corpora. Application results on a historical English corpus show that the model's semantic evolution prediction accuracy reaches 89.72%, and the time efficiency is improved by 15.3% compared with single models, demonstrating excellent performance in capturing temporal dynamics and semantic accuracy. Inderscience Publishers - linking academia, business and industry through research

Title: Analysis of English sentiment semantic evolution based on BERT and dynamic word embeddings

Authors: Yueqin Liu

Addresses: Xi'an Kedagaoxin University, Xi'an, 710109, China

Abstract: To address the challenge of accurately capturing the evolutionary trends of English sentiment semantics in large-scale time-series text data, this study proposes a sentiment semantic evolution analysis method by fusing BERT and dynamic word embeddings. First, the overall framework of the fusion model is constructed, including the data pre-processing layer, feature extraction layer, fusion layer, and application layer. Second, based on the theory of semantic change, the sentiment semantic evolution analysis index system is determined, covering temporal stability, contextual similarity, and sentiment polarity variation. Key features of sentiment semantics are extracted from time-slice corpora. Application results on a historical English corpus show that the model's semantic evolution prediction accuracy reaches 89.72%, and the time efficiency is improved by 15.3% compared with single models, demonstrating excellent performance in capturing temporal dynamics and semantic accuracy.

Keywords: English sentiment semantics; semantic evolution; BERT; dynamic word embeddings; feature fusion.

DOI: 10.1504/IJICT.2025.149179

International Journal of Information and Communication Technology, 2025 Vol.26 No.37, pp.75 - 90

Received: 19 Jul 2025
Accepted: 02 Sep 2025
Published online: 16 Oct 2025 *

Title: Analysis of English sentiment semantic evolution based on BERT and dynamic word embeddings

Keep up-to-date