Twitter Sentiment Analysis
International Journal of Innovative Science and Research Technology · 22.06.2026 · 813
DOI: 10.38124/ijisrt/26jun364 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Innovative Science and Research Technology, online erschienen am 22.06.2026. Verfasst von Himani H. Patel und 3 weiteren Autor:innen. Die Arbeit nennt 15 Literaturangaben.
Abstract (Originalsprache)
The concept of sentiment analysis of social media texts poses a vital role in better understanding public opinions, behavior patterns of consumers, and societal trends. Twitter, being a microblogging website, poses a tremendous challenge to the social media world due to its highly noisy and informal nature of tweets. This paper emphasizes a highly efficient and scalable sentiment analysis system using the Sentiment140 dataset. The dataset comprises 1.6 million tweets that are automatically labeled using emoticons. The system uses lightweight text processing steps followed by converting tweets into a numerical representation by means of Term Frequency-Inverse Document Frequency (TF-IDF) with unigrams, bigrams, and sublinear scaling. Three powerful yet classic machine learning classifiers—Multinomial Naive Bayes and Logistic Regression (tuned using GridSearchCV) and Linear SVM—are combined using a hard voting classifier. This paper proves that the combination of classifiers yields better accuracy and performance. An experimental study using a train-test splitting ratio of 75:25 demonstrates that the combination classifier exhibits higher accuracy, precision, recall, and F1-measure. The system has been found computationally efficient. Error analysis indicates that slang usage, sarcasm, and the use of emojis constitute major challenges. The results confirm that classical linear models, when trained on large-scale data and combined effectively, provide a strong, scalable baseline for Twitter sentiment analysis suitable for real-time deployment. Future work includes incorporating emoji-aware features and contextual embeddings to handle linguistic nuance.
Zitieren
APA
Patel, H. H., Mahalle, O., Shetty, A., & Hugar, S. (2026). Twitter Sentiment Analysis. International Journal of Innovative Science and Research Technology, 813. https://doi.org/10.38124/ijisrt/26jun364
Vancouver
Patel HH, Mahalle O, Shetty A, Hugar S. Twitter Sentiment Analysis. International Journal of Innovative Science and Research Technology. 2026:813. doi:10.38124/ijisrt/26jun364
BibTeX
@article{Patel2026,
author = {Patel, Himani H. and Mahalle, Om and Shetty, Anish and Hugar, Sachin},
title = {Twitter Sentiment Analysis},
journal = {International Journal of Innovative Science and Research Technology},
year = {2026},
pages = {813},
doi = {10.38124/ijisrt/26jun364}
}
EUVIMED