English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Efficient text classification is essential for handling the increasing volumeof academic publications. This study explores the use of pre-trained languagemodels (PLMs), including BERT, SciBERT, BioBERT, and BlueBERT, fine-tuned onthe Web of Science (WoS-46985) dataset for scientific text classification. Toenhance performance, we augment the dataset by executing seven targeted queriesin the WoS database, retrieving 1,000 articles per category aligned withWoS-46985's main classes. PLMs predict labels for this unlabeled data, and ahard-voting strategy combines predictions for improved accuracy and confidence.Fine-tuning on the expanded dataset with dynamic learning rates and earlystopping significantly boosts classification accuracy, especially inspecialized domains. Domain-specific models like SciBERT and BioBERTconsistently outperform general-purpose models such as BERT. These findingsunderscore the efficacy of dataset augmentation, inference-driven labelprediction, hard-voting, and fine-tuning techniques in creating robust andscalable solutions for automated academic text classification.

Advancing Scientific Text Classification: Fine-Tuned Models with Dataset Expansion and Hard-Voting