Abstract
In this paper, authors evaluate machine learning algorithms to detect the trustworthiness of a website according to HONcode criteria of conduct (detailed in paper). To derive a baseline, we evaluated a Naive Bayes algorithm, using single words as features. We compared the baseline algorithm’s performance to that of the same algorithm employing different feature types, and to the SVM algorithm. The results demonstrate that the most basic configuration (Naive Bayes, single word) could produce a 0.94 precision for “easy” HON criteria such as “Date”. Conversely, for more difficult HON criteria “Justifiability”, we obtained precision of 0.68 by adjusting the system parameters such as algorithm (SVM) and feature types (W2).
Users
Please
log in to take part in the discussion (add own reviews or comments).