Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{175049,
        author = {Rahul Shivhare and Paras Goel and Shivika Tomar and Manav Gupta},
        title = {Benchmarking Machine Learning Algorithms for Twitter Sentiment Prediction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {2075-2082},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=175049},
        abstract = {With a focus on the comparison of the performance of different algorithms, this study examines sentiment analysis on Twitter data through machine learning approaches. The dataset's tweets contain four sentiment classes: positive, negative, neutral, and irrelevant. TF-IDF vectorization was part of the preprocessing steps for converting raw text into numerical features suitable for model training. Multinomial Naive Bayes, Logistic Regression, Support Vector Machine, Decision Tree, Random Forest, and Artificial Neural Network (ANN) were the six machine learning algorithms that were implemented. When these models' accuracies for classification were measured, the highest accuracy was that of the Random Forest model (97.8%), followed by that of the ANN (97.3%). Though they did a great job, basic models like Naive Bayes and Logistic Regression lagged behind the advanced approaches. The results indicate how efficiently complicated models carry out sentiment analysis operations and provide the foundation for subsequent studies on ensemble methods or another model optimization.},
        keywords = {Count Vectorizer, Multinomial Naïve Bayes, NLP Pipeline, Accuracy},
        month = {April},
        }