Machine learning classifiers to predict the quality of semantic web queries

Abstract

In this research, a classification framework to automatically identify well and poorly designed SPARQL queries is proposed. Evaluating SPARQL queries becomes a difficult challenging issue because of the query design and the volume of data to be handled. The proposed context applies various machine learning algorithms including decision trees, k nearest neighbours, support vector machine, and naive Bayes. In addition, two different feature extraction techniques called TFIDF measure and count vectorizer are measured to identify the key features. The experimental results show that the four machine learning classifiers applied are able to classify the SPARQL queries into three categories like well, accepted, and poorly designed queries. It also provides hopeful results with respect to recall, precision, and F1-score. In datasets used for experimentation, it was found that the decision trees classifier outperforms well compared to other classifiers by achieving 92% in terms of F1-measure. Also, the count vectorizer performs well in measuring the TFIDF property to predict the poorly designed queries.