Explainable AI for News Classification

Abstract

Abstract: The proliferation of news content across digital platforms necessitates robust and interpretable machine learning models to classify news into predefined categories effectively. This study investigates the integration of Explainable AI (XAI) techniques within the context of traditional machine learning models, including Naive Bayes, Logistic Regression, and Support Vector Machines (SVM), to achieve interpretable and accurate news classification. Utilizing the News Category Dataset, we preprocess the data to focus on the top 15 categories while addressing class imbalance challenges. Models are trained using Term Frequency-Inverse Document Frequency (TF-IDF) vectorization, achieving an acceptable classification accuracy of 67% across all models despite the complexity introduced by the high number of classes. To elucidate the decision-making processes of these models, we employ feature importance visualizations derived from model coefficients and feature log probabilities, complemented by local interpretability techniques such as LIME (Local Interpretable Model-agnostic Explanations). These methodologies enable granular insights into word-level contributions to predictions for each news category. Comparative heatmaps across models reveal significant consistencies and divergences in feature reliance, highlighting nuanced decision-making patterns. The integration of explainability into news classification provides critical interpretive capabilities, offering transparency and mitigating the risks associated with algorithmic opacity. The findings demonstrate how XAI enhances stakeholder trust by aligning model predictions with human interpretability, particularly in ethically sensitive domains. This work emphasizes the role of XAI in fostering responsible AI deployment and paves the way for future advancements, including deep learning integration and multilingual news classification with inherent interpretability frameworks