Sentimental Analysis of Movie Tweet Reviews Using Machine Learning Algorithms - 57th Hawaii International Conference on System Sciences

Aug 4, 2026

Upload by Oliver

Sentiment analysis enables extracting public opinion and emotional polarity from microblog platforms, especially for movie tweet reviews. This study proposes a robust system architecture that integrates multiple machine learning algorithms, including Multinomial Naive Bayes, SVM, KNN, Bernoulli’s Naive Bayes, and Random Forest, trained on annotated Twitter data. Tweets are filtered to exclude non-opinionated content and are then labeled as positive, negative, or neutral. Text preprocessing covers tokenization, stemming, and stop-word removal to generate numerical features. Experiments evaluate accuracy, precision, recall, and F1-score with cross-validation to improve reliability and robustness.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages12

Reading Time30 min

AccessFree to download

Abstract

1. Introduction

Proceedings of the 57th Hawaii International Conference on System Sciences | 2024 Sentimental Analysis of Movie Tweet Reviews Using Machine Learning Algorithms Hemanth Kumar Kari Texas A&M University-Commerce [hemanthkumarkari@gmail.com](hemanthkumarkari@gmail.com) Abstract Sentiment analysis stands as a prominent tool within microblogging platforms, gaining substantial traction as a means to discern public opinion and sentiment across various topics, including movie tweet reviews. In response to this demand, the study introduces a robust system architecture that incorporates an array of algorithms, ranging from Multinomial Naive Bayes and Support Vector Machine (SVM) to K-Nearest Neighbors (KNN), Bernoulli’s Naive Bayes, and Random Forest. This architecture is meticulously trained using annotated Twitter data, methodically excluding non-opinionated content while precisely identifying sentiment. Thorough experimentation underscores the effectiveness of our methodology. To accomplish this, we curate an extensive data set of movie-related tweets, each carefully labeled with sentiments spanning positive, negative, or neutral tones. The methodological framework involves intricate text preprocessing steps, encompassing tokenization, stemming, and the removal of extraneous stop words. This facilitates the extraction of essential features and the conversion of raw text into numerical representations suitable for machine learning. Our sentiment classification modeling employs a diverse ensemble of machine learning algorithms, including Naive Bayes, Support Vector Machines, and Recurrent Neural Networks. The assessment involves a range of metrics such as accuracy, precision, recall, and F1-score, supported by rigorous techniques like cross-validation to enhance the dependability and robustness of results. Our unique contribution lies in the strategic deployment of algorithms and a resilient system architecture adept at surmounting the challenges inherent to microblogs. We emphasize the utmost importance of preprocessing in augmenting the precision of sentiment classification. This research substantiates the system’s aptitude in extracting valuable insights for informed decision-making through the scrutiny of microblog sentiments. Keywords: sentiment analysis, microblogging, machine learning, system architecture, experimental results, feature selection, accuracy metrics, and Confusion Matrix 1. Introduction In the era of digitization, the surge in social media platforms has catalyzed a transformative wave, enabling individuals to voice their perspectives on a broad spectrum of subjects, including movies (Johnson, R., Zhang, T. 2015) . However, within this expansive realm of online discourse, microblogs emerge as a dynamic landscape that demands a unique approach to sentiment analysis. This journey embarks on the intricate path of unraveling sentiment analysis intricacies within the realm of microblogs, where the casual and fluid nature of communication introduces layers of complexity. Microblogs present a unique challenge to traditional sentiment analysis methodologies, given their informal nature and prevalence of linguistic nuances. This necessitates an innovative approach that transcends mere algorithmic comparisons. Our endeavor strives to delve into this complexity and establish an intricate understanding of sentiment within microblogging platforms. Amid the continuous stream of movie-related tweets, a critical demand arises to efficiently distill meaningful insights from this data influx (Johnson, R.,& Zhang, T. (2015)) . This imperative has spurred my exploration into the realm of sentiment analysis, where the prowess of machine learning algorithms becomes a guiding light. However, our research aims URI: [https://hdl.handle.net/10125/107012](https://hdl.handle.net/10125/107012)[ ](https://hdl.handle.net/10125/107012)[978-0-9981331-7-1](978-0-9981331-7-1) (CC BY-NC-ND 4 .0) Page 5225 to transcend th

FAQs

What problem does the research address?

The research addresses sentiment analysis for movie-related microblog tweets, aiming to infer public opinion from informal, nuanced text streams.

Which machine learning algorithms are used in the proposed system?

The system integrates Multinomial Naive Bayes, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Bernoulli’s Naive Bayes, and Random Forest.

How is tweet text prepared before sentiment classification?

The methodology includes tokenization, stemming, and stop-word removal, enabling conversion of raw text into numerical feature representations for machine learning models.

Aug 4, 2026

Upload by Oliver