https://www.thesesjournal.com/index.php/1 <p data-start="64" data-end="394"><strong data-start="64" data-end="106">Spectrum of Engineering Sciences (SES)</strong> is a refereed international research platform committed to advancing high-quality scholarly work. It is an open-access, online journal that follows a rigorous editorial (blind) and double-blind peer-review process. SES is published monthly and operates on a continuous publication model.</p> <p data-start="396" data-end="759">The journal primarily focuses on publishing original research and review articles in <strong data-start="481" data-end="501">Computer Science</strong> and <strong data-start="506" data-end="530">Engineering Sciences</strong>. It is launched and managed by the <strong data-start="566" data-end="625">Sociology Educational Nexus Research Institute (SME-PV)</strong>. With a strong international orientation, SES aims to attract authors and readers from diverse academic and professional backgrounds.</p> <p data-start="761" data-end="1029">At SES, we believe in the value of interdisciplinary collaboration. Bringing together multiple academic disciplines allows for the integration of knowledge across fields, enabling researchers to address complex problems and develop innovative, well-grounded solutions.</p> SOCIOLOGY EDUCATIONAL NEXUS RESEARCH INSTITUTE en-US Spectrum of Engineering Sciences 3007-312X https://www.thesesjournal.com/index.php/1/article/view/3644 <p><em>Unfortunately, fake news has also become an issue in the digital era as it can be damaging to people, organisations and even countries. In this study, a holistic machine learning method to detect fake news using natural language processing (NLP) techniques is presented. The classifiers that are tested are the following: Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Passive Aggressive Classifier (PAC), Support Vector Machine (SVM), Multinomial Naive Bayes (MNB). The technique consists of text preprocessing, TF-IDF vectorization, SMOTE (Synthetic Minority Over-sampling Technique) to overcome the class imbalance and Hyperparameter tuning using GridSearchCV and 5-fold cross validation.</em></p> <p><em>We conduct tests with two datasets: a small news dataset (6,335 samples) and a large dataset of mixed fake-real (44,898 samples). With SMOTE and hyperparameter tuning, Naïve Bayes is improved by 5.5% (from 86.0% to 91.5%) and Random Forest by 0.6% (from 90.4% to 91.0%). All of the models achieve a greater accuracy on the larger data set.</em></p> Sidra Malik Copyright (c) 2026 2026-07-31 2026-07-31 4 7 1 21