From Traditional Machine Learning to Transformers: Sentiment Analysis on Social Media Data
SPU - Journal of Science, Technology and Management Research · 01.07.2026 · 26-34
DOI: 10.63766/spujstmr.26.000070 ↗Kurz gefasst
Fachartikel in der Zeitschrift SPU - Journal of Science, Technology and Management Research, online erschienen am 01.07.2026. Verfasst von Patel Charmi D und 3 weiteren Autor:innen.
Abstract (Originalsprache)
It is notoriously hard to analyze sentiment in social media. It is written in a disorganized manner, using slang, and is extremely dependent on implicit context. Classical baselines, including TF-IDF with Linear Support Vector Machines (SVM), however, give a good starting point. Nevertheless, such approaches do not capture the underlying semantic meaning as they deal with words individually. This paper compares traditional machine learning models with RoBERTa, transformer architecture with the ability to capture the entire sentence context. Social media detain the real world are sloppy, with too fine emotion tags and grossly skewed classes. In order to solve these problems, we designed a semantics-aware label consolidation algorithm based on Sentence Transformers. We then balanced our training data by using SMOTE in the continuous embedding space. Experiments with a multi-platform dataset with diverse data show that RoBERTa is significantly better than all classical baselines in terms of accuracy, precision, recall, and F1-score. More to the point, the transformer is able to deal with sarcasm and negation, which bag-of-words models often fail to do. This paper points to the need of contemporary sentiment analysis to include context-sensitive embedding and specific preprocessing to be able to read online communication correctly
Zitieren
APA
D, P. C., M, M. J., Gaurang, P., & Amit, P. (2026). From Traditional Machine Learning to Transformers: Sentiment Analysis on Social Media Data. SPU - Journal of Science, Technology and Management Research, 26-34. https://doi.org/10.63766/spujstmr.26.000070
Vancouver
D PC, M MJ, Gaurang P, Amit P. From Traditional Machine Learning to Transformers: Sentiment Analysis on Social Media Data. SPU - Journal of Science, Technology and Management Research. 2026:26-34. doi:10.63766/spujstmr.26.000070
BibTeX
@article{D2026,
author = {D, Patel Charmi and M, Mevada Jayesh and Gaurang, Patel and Amit, Patel},
title = {From Traditional Machine Learning to Transformers: Sentiment Analysis on Social Media Data},
journal = {SPU - Journal of Science, Technology and Management Research},
year = {2026},
pages = {26--34},
doi = {10.63766/spujstmr.26.000070}
}
EUVIMED