Home // eLmL 2019, The Eleventh International Conference on Mobile, Hybrid, and On-line Learning // View article


Analysing Textual Content of Educational Web Pages for Discovering Features Useful for Classification Purposes

Authors:
Vladimir Estivill-Castro
Matteo Lombardi
Alessandro Marani

Keywords: Learning Objects, Internet based systems, Navigational aspects for on-line learning, Recommender Systems.

Abstract:
Studies in Information Retrieval and Technology Enhanced Learning have not been able yet to propose reliable support to students and teachers when seeking educational resources on the Web. The driving force of web-search has been to match the topic of a query with the topic of documents. This paper involves Natural Language Learning approaches for an in-depth analysis of the common traits among educational web-pages. We analyzed the textual content of resources coming from educational websites and a survey among instructors. We computed more than 100 attributes and tested their significance for classification against web-pages from non-educational sources. Our analysis selected a set of 53 attributes. The results of a classification task prove that our traits allow for highly accurate filtering of resources with educational purposes. Moreover, the reliability of the proposed methodology is statistically verified.

Pages: 30 to 35

Copyright: Copyright (c) IARIA, 2019

Publication date: February 24, 2019

Published in: conference

ISSN: 2308-4367

ISBN: 978-1-61208-689-7

Location: Athens, Greece

Dates: from February 24, 2019 to February 28, 2019