APPLICATION OF MACHINE LEARNING TO TEXT CLASSIFICATION - LAUTECH Journal of Engineering and Technology 18(1) 2024

Aug 3, 2026

Upload by Ezra

The information superhighway enables organizations to disseminate information, but processing massive customer data manually is inefficient. This study applies Python-based data collection and machine learning models, using Random Forest and Naïve Bayes, to perform text classification on collected datasets. Text outputs are categorized into positive, negative, slightly negative, slightly positive, or neutral classes. Results indicate Random Forest outperforms Naïve Bayes, achieving 76.5% accuracy versus 70.01%. The approach supports organizational insight into customer perceptions.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Abstract

Introduction

Related Work on Machine Learning for Text Analysis

Methods and Models Discussed in Prior Studies

Proposed Approach (Python + Machine Learning)

Classification Results and Accuracy Comparison

LAUTECH Journal of Engineering and Technology 18 (1) 2024: 47-56 APPLICATION OF MACHINE LEARNING TO TEXT CLASSIFICATION 1*Ozoh P., 2Rasheed S., 3Akanbi C., 4Olayiwola M., 5Ibrahim M., 6Kolawole M., 7Olubusayo O., 8Adigun A. 1,2,3,5,8Department of ICT, Osun State University, Nigeria 4,6Department of Mathematical Sciences, Osun State University, Nigeria, 7Department of Physics, Osun State University, Nigeria Corresponding Author, [email: p](email: patrick.ozoh@uniosun.edu.ng:)[atrick.ozoh@uniosun.edu.ng](email: patrick.ozoh@uniosun.edu.ng:)[:](email: patrick.ozoh@uniosun.edu.ng:) [olayiwola.oyedunsi@uniosun.edu.ng](olayiwola.oyedunsi@uniosun.edu.ng) ABSTRACT The information superhighway provides important principles for giving out information to various consultations. Organizations depend on knowing customer observations about products and services. Data can be enormous to process physically. This study investigates a technique applying Python programming to collect datasets instinctively. The use of machine learning models evolves by applying Random Forest and Naïve Bayes algorithms. These techniques are applied to the data collected for text classification purposes. This process distributes data into; positive, negative, slightly negative, slightly positive, or neutral. The results from the study show the Random Forest classifier is more efficient than the Naïve Bayes algorithm, resulting in an accuracy rate of 76.5% about Naïve Bayes (70.01%). This technique enables organizations to receive insights into customer ways of thinking. Keywords: Text classification, Internet community, Random Forest (RF), Insight, Data scraping. INTRODUCTION The application of machine learning models to analyze articles was discussed by Rejeb et al.(2024) . The study shows that the ChatGPT is an important tool for students and educators. The study indicates ChatGPT's crucial function in improving students' writing duties and enhancing an interactive learning community. The study finds theoretical and practical concerns for applying ChatGPT in educational institutions. Choe et al.(2024) investigate conducting measurable learning by introducing SAMA, which integrates classification algorithms and models. When the SAMA algorithm is compared with large-scale learning benchmarks, SAMA produces a reduction in storage capacity. Also, SAMA-based data optimization produces harmonious enhancements in text classification accuracy. Abubakr et al.(2024) present a relative analysis between two models for a multi-class classification. The result from the study indicates the proposed application of the deep learning technique yielded an accuracy of 94.95%, compared to 85.71% for the previous technique. Mupaikwa (2024) proposed in digital libraries. The technique utilized the KNearest neighbor, Bayesian networks, fuzzy logic, support vector machines, clustering, and classification algorithms. The paper proposed the training of librarians, curriculum reviews, and research on Pythondependent technology for libraries. Büyükkeçeci & Okur (2024) discuss the feature selection technique for selecting features relevant to machine learning functions. This study focused on feature selection and feature selection stability. This technique minimizes dataset size. This plays a role in improving the performance of machine learning models. Valtonen et al. (2024) proposed a standard research database of unstructured text and encountered the representativeness difference between collections of preprocessing and UMLbased algorithms that confront research undertakings and transparency. The study requires for contextual representations to focus on issues and offer recommendations for addressing contextual suitability of the UML in research settings. A review of past research works on text mining was done by Shamshiri et al. (2024) . The paper investigates the aim of conducting several research works having special functions. The findings from this paper wi

FAQs

What machine learning algorithms are used for text classification in the study?

The study applies Random Forest and Naïve Bayes to the collected text datasets to classify sentiment into multiple categories.

How are the text classification outputs categorized?

The process assigns texts to positive, negative, slightly negative, slightly positive, or neutral classes.

Which classifier performed better and what accuracy was reported?

Random Forest performed more efficiently, reaching 76.5% accuracy, compared with 70.01% for Naïve Bayes.

Aug 3, 2026

Upload by Ezra