INTRODUCING THE CONCEPT OF DECISIONAL DNA–BASED WEB CONTENT MINING

With very fast expansion of the Internet, several problems and challenges are created by the persistent growth of the amount of information in Web content. These challenges are related mainly to the difficulty of extracting potentially useful information and knowledge from Internet pages. To support Web content knowledge capture we propose a concept that integrates a novel decisional DNA knowledge structure with the traditional Web crawler technologies. Decisional DNA as a knowledge representation platform can be used to deal with noisy and incomplete data and can help to learn from experience and make precise decisions and predictions in vague and fuzzy environments. We illustrate our proposed concept with a set of experiments to prove its initial efficiency and effectiveness.