Sentiment classification optimization based on improved Senti-BERT and BiLSTM-Attention

Jie Zhang, Jianbang Liu, Zhaosheng Xu · 2026

Read Sentiment classification optimization based on improved Senti-BERT and BiLSTM-Attention by Jie Zhang, Jianbang Liu, Zhaosheng Xu (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0358103.txt.

Description

Jie Zhang, Jianbang Liu, and Zhaosheng Xu improved machines that read emotion in text, published in PLOS ONE in 2026. Sentiment classification decides whether a text glows with praise or grumbles with complaint, and businesses pay for accuracy. The team optimized a hybrid model joining an improved Senti-BERT with a BiLSTM network and an attention step.

Zhang's architecture squeezes more accuracy from the models behind review analysis and social listening. Small gains matter at scale, where millions of posts are sorted daily. The hybrid design pairs the strengths of two model families rather than betting on one. For researchers, the paper offers a tested recipe; for users of sentiment tools, it promises fewer glaring misreads of sarcasm and mixed reviews.

Catalog record

CREATORJie Zhang, Jianbang Liu, Zhaosheng Xu
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE61857
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0358103

Browse the full library · About the Tower of Babel