Website Classification from Webpage Renders

Leonardo Espinosa-Leal; Anton Akusok; Amaury Lendasse; Kaj-Mikael Björk

doi:10.1007/978-3-030-58989-9_5

Website Classification from Webpage Renders

Leonardo Espinosa-Leal^*, Anton Akusok, Amaury Lendasse, Kaj-Mikael Björk

^*Corresponding author for this work

Not published at VTT

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

Abstract

In this paper, we present a fast and accurate method for the classification of web content. Our algorithm uses the visual information of the main homepage saved in an image format by means of a full body snapshot. Sliding windows of different sizes and overlaps are used to obtain a large subset of images for each render. For each sub-image, a feature vector is extracted by means of a pre-trained deep learning model. A Extreme Learning Machine (ELM) model is trained for different values of hidden neurons using the large collection of features from a curated dataset of 5979 webpages with different classes: adult, alcohol, dating, gambling, shopping, tobacco and weapons. Our results show that the ELM classifier can be trained without the manual specific object tagging of the sub-images by giving excellent results in comparison to more complex deep learning models. A random forest classifier was trained for the specific class of weapons providing an accuracy of 95% with a F1 score of 0.8.

Original language	English
Title of host publication	Proceedings of ELM2019
Editors	Jiuwen Cao, Chi Man Vong, Yoan Miche, Amaury Lendasse
Place of Publication	Cham
Publisher	Springer
Pages	41-50
ISBN (Electronic)	978-3-030-58989-9
ISBN (Print)	978-3-030-58988-2, 978-3-030-59049-9
DOIs	https://doi.org/10.1007/978-3-030-58989-9_5
Publication status	Published - 12 Sept 2020
MoE publication type	A4 Article in a conference publication
Event	2019 International Conference on Extreme Learning Machine (ELM 2019) - Yangzhou, China Duration: 14 Dec 2019 → 16 Dec 2019

Publication series

Series	Proceedings in Adaptation, Learning and Optimization
Volume	14
ISSN	2363-6084

Conference

Conference	2019 International Conference on Extreme Learning Machine (ELM 2019)
Country/Territory	China
City	Yangzhou
Period	14/12/19 → 16/12/19

Access to Document

10.1007/978-3-030-58989-9_5

Cite this

@inproceedings{32dc6c917f9e499f9f4c45f88b591132,

title = "Website Classification from Webpage Renders",

abstract = "In this paper, we present a fast and accurate method for the classification of web content. Our algorithm uses the visual information of the main homepage saved in an image format by means of a full body snapshot. Sliding windows of different sizes and overlaps are used to obtain a large subset of images for each render. For each sub-image, a feature vector is extracted by means of a pre-trained deep learning model. A Extreme Learning Machine (ELM) model is trained for different values of hidden neurons using the large collection of features from a curated dataset of 5979 webpages with different classes: adult, alcohol, dating, gambling, shopping, tobacco and weapons. Our results show that the ELM classifier can be trained without the manual specific object tagging of the sub-images by giving excellent results in comparison to more complex deep learning models. A random forest classifier was trained for the specific class of weapons providing an accuracy of 95\% with a F1 score of 0.8.",

author = "Leonardo Espinosa-Leal and Anton Akusok and Amaury Lendasse and Kaj-Mikael Bj{\"o}rk",

year = "2020",

month = sep,

day = "12",

doi = "10.1007/978-3-030-58989-9\_5",

language = "English",

isbn = "978-3-030-58988-2",

series = "Proceedings in Adaptation, Learning and Optimization",

publisher = "Springer",

pages = "41--50",

editor = "Jiuwen Cao and Vong, \{Chi Man\} and Yoan Miche and Amaury Lendasse",

booktitle = "Proceedings of ELM2019",

address = "Germany",

note = "2019 International Conference on Extreme Learning Machine (ELM 2019) ; Conference date: 14-12-2019 Through 16-12-2019",

}

Espinosa-Leal, L, Akusok, A, Lendasse, A & Björk, K-M 2020, Website Classification from Webpage Renders. in J Cao, CM Vong, Y Miche & A Lendasse (eds), Proceedings of ELM2019. Springer, Cham, Proceedings in Adaptation, Learning and Optimization, vol. 14, pp. 41-50, 2019 International Conference on Extreme Learning Machine (ELM 2019), Yangzhou, China, 14/12/19. https://doi.org/10.1007/978-3-030-58989-9_5

Website Classification from Webpage Renders. / Espinosa-Leal, Leonardo; Akusok, Anton; Lendasse, Amaury et al.
Proceedings of ELM2019. ed. / Jiuwen Cao; Chi Man Vong; Yoan Miche; Amaury Lendasse. Cham: Springer, 2020. p. 41-50 (Proceedings in Adaptation, Learning and Optimization, Vol. 14).

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Website Classification from Webpage Renders

AU - Espinosa-Leal, Leonardo

AU - Akusok, Anton

AU - Lendasse, Amaury

AU - Björk, Kaj-Mikael

PY - 2020/9/12

Y1 - 2020/9/12

N2 - In this paper, we present a fast and accurate method for the classification of web content. Our algorithm uses the visual information of the main homepage saved in an image format by means of a full body snapshot. Sliding windows of different sizes and overlaps are used to obtain a large subset of images for each render. For each sub-image, a feature vector is extracted by means of a pre-trained deep learning model. A Extreme Learning Machine (ELM) model is trained for different values of hidden neurons using the large collection of features from a curated dataset of 5979 webpages with different classes: adult, alcohol, dating, gambling, shopping, tobacco and weapons. Our results show that the ELM classifier can be trained without the manual specific object tagging of the sub-images by giving excellent results in comparison to more complex deep learning models. A random forest classifier was trained for the specific class of weapons providing an accuracy of 95% with a F1 score of 0.8.

AB - In this paper, we present a fast and accurate method for the classification of web content. Our algorithm uses the visual information of the main homepage saved in an image format by means of a full body snapshot. Sliding windows of different sizes and overlaps are used to obtain a large subset of images for each render. For each sub-image, a feature vector is extracted by means of a pre-trained deep learning model. A Extreme Learning Machine (ELM) model is trained for different values of hidden neurons using the large collection of features from a curated dataset of 5979 webpages with different classes: adult, alcohol, dating, gambling, shopping, tobacco and weapons. Our results show that the ELM classifier can be trained without the manual specific object tagging of the sub-images by giving excellent results in comparison to more complex deep learning models. A random forest classifier was trained for the specific class of weapons providing an accuracy of 95% with a F1 score of 0.8.

U2 - 10.1007/978-3-030-58989-9_5

DO - 10.1007/978-3-030-58989-9_5

M3 - Conference article in proceedings

SN - 978-3-030-58988-2

SN - 978-3-030-59049-9

T3 - Proceedings in Adaptation, Learning and Optimization

SP - 41

EP - 50

BT - Proceedings of ELM2019

A2 - Cao, Jiuwen

A2 - Vong, Chi Man

A2 - Miche, Yoan

A2 - Lendasse, Amaury

PB - Springer

CY - Cham

T2 - 2019 International Conference on Extreme Learning Machine (ELM 2019)

Y2 - 14 December 2019 through 16 December 2019

ER -

Website Classification from Webpage Renders

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this