Identifying and blocking pornographic content

Paul Watters; Wai-han Ho

doi:10.1109/ICDE.2005.227

Identifying and blocking pornographic content

Paul Watters, Wai-han Ho

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

11 Citations (Scopus)

Abstract

Content filtering on the WWW is significant social issue, since children can easily access pornography and other illegal material with ease. In this study, a descriptive and predictive model of pornographic web page characteristics was developed, to assist with recognition of pornographic pages in a content filter. Support and confidence results from simple association rules suggest that using individual terms to identify pornographic web pages is useful for description, but unreliable for prediction. However, Bayesian classification provided 99.1% accuracy in classifying test pages from both pornographic and non-pornographic corpora. The challenges for multimodal filtering are discussed. ? 2005 IEEE.

Original language	English
Title of host publication	Proceedings of the International Workshop on Managing Data for Emerging Multimedia Applications, EMMA 2005. In Conjunction with IEEE ICDE 2005
Editors	Shin'ichi Satoh, Edward Chang
Place of Publication	NJ, USA
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	113-120
Number of pages	8
ISBN (Print)	0769522858
DOIs	https://doi.org/10.1109/ICDE.2005.227
Publication status	Published - 2005
Event	The International Workshop on Managing Data for Emerging Multimedia Applications, EMMA 2005. In Conjunction with IEEE International Conference on Data Engineering, ICDE 2005 - Tokyo, Japan Duration: 9 Apr 2005 → 9 Apr 2005

Conference

Conference	The International Workshop on Managing Data for Emerging Multimedia Applications, EMMA 2005. In Conjunction with IEEE International Conference on Data Engineering, ICDE 2005
City	Tokyo, Japan
Period	9/04/05 → 9/04/05

Access to Document

10.1109/ICDE.2005.227

Cite this

@inproceedings{1b4a31cb49dd43fa9968cb4eb4dc976a,

title = "Identifying and blocking pornographic content",

abstract = "Content filtering on the WWW is significant social issue, since children can easily access pornography and other illegal material with ease. In this study, a descriptive and predictive model of pornographic web page characteristics was developed, to assist with recognition of pornographic pages in a content filter. Support and confidence results from simple association rules suggest that using individual terms to identify pornographic web pages is useful for description, but unreliable for prediction. However, Bayesian classification provided 99.1\% accuracy in classifying test pages from both pornographic and non-pornographic corpora. The challenges for multimodal filtering are discussed. ? 2005 IEEE.",

author = "Paul Watters and Wai-han Ho",

year = "2005",

doi = "10.1109/ICDE.2005.227",

language = "English",

isbn = "0769522858",

pages = "113--120",

editor = "Shin'ichi Satoh and Edward Chang",

booktitle = "Proceedings of the International Workshop on Managing Data for Emerging Multimedia Applications, EMMA 2005. In Conjunction with IEEE ICDE 2005",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

note = "The International Workshop on Managing Data for Emerging Multimedia Applications, EMMA 2005. In Conjunction with IEEE International Conference on Data Engineering, ICDE 2005 ; Conference date: 09-04-2005 Through 09-04-2005",

}

Watters, P & Ho, W 2005, Identifying and blocking pornographic content. in S Satoh & E Chang (eds), Proceedings of the International Workshop on Managing Data for Emerging Multimedia Applications, EMMA 2005. In Conjunction with IEEE ICDE 2005. Institute of Electrical and Electronics Engineers (IEEE), NJ, USA, pp. 113-120, The International Workshop on Managing Data for Emerging Multimedia Applications, EMMA 2005. In Conjunction with IEEE International Conference on Data Engineering, ICDE 2005, Tokyo, Japan, 9/04/05. https://doi.org/10.1109/ICDE.2005.227

Identifying and blocking pornographic content. / Watters, Paul; Ho, Wai-han.
Proceedings of the International Workshop on Managing Data for Emerging Multimedia Applications, EMMA 2005. In Conjunction with IEEE ICDE 2005. ed. / Shin'ichi Satoh; Edward Chang. NJ, USA: Institute of Electrical and Electronics Engineers (IEEE), 2005. p. 113-120.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Identifying and blocking pornographic content

AU - Watters, Paul

AU - Ho, Wai-han

PY - 2005

Y1 - 2005

N2 - Content filtering on the WWW is significant social issue, since children can easily access pornography and other illegal material with ease. In this study, a descriptive and predictive model of pornographic web page characteristics was developed, to assist with recognition of pornographic pages in a content filter. Support and confidence results from simple association rules suggest that using individual terms to identify pornographic web pages is useful for description, but unreliable for prediction. However, Bayesian classification provided 99.1% accuracy in classifying test pages from both pornographic and non-pornographic corpora. The challenges for multimodal filtering are discussed. ? 2005 IEEE.

AB - Content filtering on the WWW is significant social issue, since children can easily access pornography and other illegal material with ease. In this study, a descriptive and predictive model of pornographic web page characteristics was developed, to assist with recognition of pornographic pages in a content filter. Support and confidence results from simple association rules suggest that using individual terms to identify pornographic web pages is useful for description, but unreliable for prediction. However, Bayesian classification provided 99.1% accuracy in classifying test pages from both pornographic and non-pornographic corpora. The challenges for multimodal filtering are discussed. ? 2005 IEEE.

UR - https://www.scopus.com/pages/publications/33947108415

U2 - 10.1109/ICDE.2005.227

DO - 10.1109/ICDE.2005.227

M3 - Conference proceeding contribution

SN - 0769522858

SP - 113

EP - 120

BT - Proceedings of the International Workshop on Managing Data for Emerging Multimedia Applications, EMMA 2005. In Conjunction with IEEE ICDE 2005

A2 - Satoh, Shin'ichi

A2 - Chang, Edward

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - NJ, USA

T2 - The International Workshop on Managing Data for Emerging Multimedia Applications, EMMA 2005. In Conjunction with IEEE International Conference on Data Engineering, ICDE 2005

Y2 - 9 April 2005 through 9 April 2005

ER -

Identifying and blocking pornographic content

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this