Impact of Stopword Variation on Qur'anic Text Classification using Support Vector Machine and Backpropagation

Abstrak

This study aims to analyze the impact of varying stopword sets on the performance of Qur'anic text classification models in Indonesian translations, using two machine learning algorithms: Support Vector Machine (SVM) and Backpropagation Neural Network (BPNN). The research involved six stopword variants: Sastrawi, Damian Doyle, Fadillah Z. Tala, Natural Language Toolkit (NLTK) Indonesian, Yudi Wibisono, and a combination of all these lists. The preprocessing steps included cleaning, case folding, tokenization, stopword removal, and stemming, followed by TF-IDF (Term Frequency-Inverse Document Frequency) text representation. Feature selection was performed using the Chi-Square method to select the top 1,000 features. The evaluation results showed that SVM consistently outperformed BPNN across all metrics, including accuracy, precision, recall, and F1-score. The Sastrawi stopword variant delivered the best performance with an F1-score of 0.6697, followed by Fadillah Z. Tala and Damian Doyle. In contrast, BPNN showed lower performance, with the highest F1-score of 0.4607 achieved using the NLTK stopword variant. These findings highlight that selecting relevant, contextually appropriate stopwords is critical to classification Effectiveness. SVMs proved more reliable at handling high-dimensional text data while preserving the semantic meaning of Qur'anic verses.

Identifier

• OpenAlex: https://openalex.org/W7167058908
• DOI: https://doi.org/10.35970/jinita.v8i1.3069