This study evaluates the performance of conventional machine learning classifiers for sentiment analysis of ChatGPT-related tweets. While deep learning approaches have demonstrated advanced capabilities, their substantial computational requirements present practical limitations. Using a dataset of 219,294 tweets from November 2022 to April 2023, we assess four classifiers (Logistic Regression, Support Vector Machines, Random Forest, and Naive Bayes) with two feature extraction techniques (Bag of Words and TF-IDF) across balanced and imbalanced datasets. Results indicate that Linear SVM with TF-IDF vectorization achieves the highest accuracy (84.02%) and macro F1-score (80.81%) without balancing techniques. Random Forest with Bag of Words and balancing techniques shows competitive performance (80.08% macro F1-score), while Naive Bayes consistently underperforms across configurations. n-gram analysis reveals predominantly positive public sentiment toward ChatGPT, focusing on capabilities and utility, while negative sentiments center on performance limitations and broader AI implications. This research provides empirical insights into sentiment analysis methodologies for emerging AI technologies and demonstrates the continued effectiveness of conventional machine learning approaches in resource-constrained environments.
P. Addo, Samuel Kofi Akpatsa, E. Mensah et al.· Journal of Technology Educat...· 0 citations
Credit risk assessment is pivotal to the sustainability of micro-lending institutions, particularly in emerging economies such as Ghana, where conventional evaluation methods remain predominantly manual and subjective. Traditional approaches, which rely on face-to-face interviews, personal judgments, and simple background checks, are vulnerable to human biases, inconsistencies, and inefficiencies that contribute to elevated default rates and broader financial instability. This study investigates the application of machine learning (ML) techniques, specifically Random Forest (RF), Extra Tree Classifier (ETC), and a probability-averaged Ensemble Classifier, to enhance credit risk assessment in Ghanaian micro-lending institutions. Using a quantitative experimental research design, the study analysed 32,581 loan records drawn from Tepa Man Microfinance Institution. Data preprocessing included missing-value imputation, one-hot encoding, and class balancing via random oversampling, applied exclusively to the training set. Model performance was evaluated through 10-fold stratified cross-validation using accuracy, precision, recall, F1-score, AUC-ROC, Cohen's Kappa, and Matthews Correlation Coefficient (MCC). Hyperparameters were set to scikit-learn defaults (n_estimators = 100, random_state = 42) to ensure reproducibility. The Random Forest and Extra Tree Classifiers each achieved a mean accuracy of 99.33% and an AUC-ROC of 0.9997, results that are consistent with the high-quality, real-world dataset and are critically interpreted in the context of potential overfitting risks. Feature importance analysis identified the loan-to-income ratio and interest rate as the dominant predictors of default. The Ensemble Method, which averages class probabilities across both base models, achieved 84.25% accuracy and an AUC of 0.9231, demonstrating stronger generalization than the individual classifiers. The study concludes that integrating ML models can substantially improve the accuracy, consistency, and reliability of credit risk evaluations, thereby reducing default rates and supporting financial inclusion in Ghana's microfinance sector.
P. Addo, Samuel Kofi Akpatsa, Emmanuel Mensah et al.· Journal of Applied Social Sc...· 0 citations