Manuscript received June 11, 2026; accepted July 11, 2026; published July 30, 2026
Abstract—By comparing and analysing the performance of several machine learning algorithms on fine-grained sentiment classification problems to examine their suitability and shortcomings for use as models in sentiment analysis. Sentiment analysis remains a prominent research area in Natural Language Processing (NLP). However, systematic comparisons of whether these methods demonstrate superiority in fine-grained classification settings have yet to be conducted. Based on the GoEmotions dataset that includes 28 sentiment classes as our experiment’s reference for evaluating four kinds of models: logistic regression, BiLSTM, BERT, and the large-scale language model Claude (claude-haiku-4-5). The experiments employ TF-IDF feature extraction, sequence encoding, pre-training with fine-tuning, and zero-shot and few-shot prompting strategies. Based on this experiment, the model’s generalisation capabilities improve as architectural depth increases. The accuracy of logistic regression was only 55.11%; BERT obtained the highest F1 score and performed the best overall, and bidirectional pre-trained representations were most valuable among other methods. However, large language models perform significantly worse on the 28-class classification task in zero-shot settings, suggesting that they are better suited for generative and open-ended emotional interaction than for standardized classification benchmarks.
Keywords—sentiment analysis, fine-grained emotion classification, BERT, BiLSTM, GoEmotions dataset
Cite: Shangjiafeng Guo, "Comparative Analysis of Language Models for Sentiment Classification," International Journal of Engineering and Technology, vol. 18, no. 3, pp. 102-105, 2026.
Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (
CC BY 4.0). 
