Inproceedings3790
Who's Behind That Website? Classifying Websites by the Degree of Commercial Intent
Who's Behind That Website? Classifying Websites by the Degree of Commercial Intent
Published: 2020
Buchtitel: Proceedings of the 20th International Conference on Web Engineering (ICWE’20)
Verlag: Springer
Referierte Veröffentlichung
BibTeX
Kurzfassung
Web hosting companies strive to provide customised customer services and want to know the commercial intent of a website. Whether a website is run by an individual person, a company, a non-profit organisation, or a public institution constitutes a great challenge in website classification as website content might be sparse. In this paper, we present a novel approach for determining the commercial intent of websites by using both supervised and unsupervised machine learning algorithms. Based on a large real-world data set, we evaluate our model with respect to its effectiveness and efficiency and observe the best performance with a multilayer perceptron.
Download: Media:Website-Classification_ICWE2020.pdf
Information Retrieval, Text Mining, Natürliche Sprachverarbeitung, Knowledge Discovery