Derin Öğrenme Kullanarak Görüntü Tabanlı Web Sayfası Sınıflandırma

Abstract

İnternet hayatımızın her alanında önemli bir yere sahip ve önemi her geçen gün artmaya devam ediyor. Bu nedenle internetin kullanılabilirliği büyük önem taşımaktadır. Düşük veri kalitesi ve dezenformasyon, internetin kullanılabilirliğini ciddi şekilde etkilemektedir. Bu nedenle insanlar doğru ve temiz bilgiye ulaşma konusunda zorluklarla karşılaşmaktadır. Günümüzde web sitelerinde metin tabanlı içerik yerine ağırlıklı olarak resim ve video gibi görsel tabanlı içerikler daha çok yer almaktadır. Bu tür içeriklerin sınıflandırılması arama motorları için büyük önem taşımaktadır. Sonuç olarak web sayfalarının sınıflandırılması bilim insanları için önemli bir araştırma alanı olarak karşımıza çıkmaktadır. Bu çalışma görsel tabanlı web sayfalarının sınıflandırılmasına odaklanmaktadır. Web sayfalarını turizm, makine, müzik ve spor olmak üzere dört ana grupta sınıflandırmak için derin öğrenmeye dayalı bir yöntem önerilmiştir. Önerilen yöntem, 0,9737 accuracy, 0,9474 recall, 0,9474 F1-score ve 0,9649 AUC değeriyle en iyi sonuçları Stokastik Gradyan İnişi (SGD) optimizasyon yöntemi ile elde etmiştir. Ayrıca, Derin Öğrenmenin (DL) kullanılması, web sayfası sınıflandırmasında, özellikle WebScreenshots veri kümesinde, mevcut literatürdeki en iyi sonuçların elde edilmesini sağlamıştır.

Keywords

• Derin öğrenme
• web sayfası sınıflandırma
• DenseNet
• optimizasyon yöntemi

Image Based Web Page Classification by Using Deep Learning

Abstract

The internet holds a significant role in all aspects of our lives, and its importance continues to grow each day. Therefore, the usability of the Internet holds great significance. Low data quality and disinformation severely impact the usability of the internet. Consequently, people face challenges in obtaining accurate and clear information. In the present day, websites predominantly feature image-based content like pictures and videos, as opposed to text-based content. The classification of such content holds immense importance for search engines. As a result, the classification of web pages stands as a crucial research area for scholars. This study focuses on the classification of image-based web pages. A deep learning-based approach is proposed to categorize web pages into four main groups: tourism, machinery, music, and sports. The suggested method yielded the most favourable outcomes when utilizing the Stochastic Gradient Descent (SGD) optimization method, achieving an accuracy of 0.9737, a recall of 0.9474, an F1 score of 0.9474, and an Area Under the ROC Curve (AUC) value of 0.9649. Furthermore, the utilization of Deep Learning (DL) led to achieving the most advanced results in web page classification within the existing literature, particularly on the WebScreenshots dataset.

Keywords

• Deep learning
• web page classification
• DenseNet
• optimization methods

References

1. [1] J. McQuillan, I. Richer and E. Rosen, "The New Routing Algorithm for the ARPANET" IEEE Transactions on Communications, vol. 28, no. 5, pp. 711-719, May 1980, https://doi.org/10.1109/TCOM.1980.1094721
2. [2] C. P. Berges and V. Schafer, “Arpanet (1969–2019),” Internet Histories, vol. 3, no. 1, pp. 1-14, 2019, https://doi.org/10.1080/24701475.2018.1560921
3. [3] M. T. Simsim, “Internet usage and user preferences in Saudi Arabia,” Journal of King Saud University-Engineering Sciences, vol. 23, no. 2, pp. 101–107, 2011, https://doi.org/10.1016/j.jksues.2011.03.006
4. [4] A. Weinstein and M. Lejoyeux, “Internet Addiction or Excessive Internet Use,” The American Journal of Drug and Alcohol Abuse, vol. 36, no. 5, pp. 277-283, 2010, https://doi.org/10.3109/00952990.2010.491880
5. [5] K. Chan and W. Fang, “Use of the internet and traditional media among young people,” Young Consumers, vol. 8, no. 4, pp. 244–256, 2007, https://doi.org/10.1108/17473610710838608
6. [6] F. Aydos, A. M. Özbayoğlu, Y. Şirin, and M. F. Demirci, “Web page classification with Google Image Search results,” arXiv preprint arXiv:2006.00226, 2020, Available https://arxiv.org/abs/2006.00226
7. [7] X. Qi and B. D. Davison, “Web page classification: Features and algorithms,” ACM computing surveys (CSUR), vol. 41, no. 2, pp. 1–31, 2009, https://doi.org/10.1145/1459352.1459357
8. [8] C. Xia and X. Wang, "Graph-Based Web Query Classification," 2015 12th Web Information System and Application Conference, WISA, 11-13 Sept. 2015, Jinan, China [Online]. Available: IEEE Xplore, http://www.ieee.org. [Accessed: 04 February 2016]

9. [9] M. Hashemi, “Web page classification: a survey of perspectives, gaps, and future directions,” Multimed Tools Appl, vol. 79, no. 17–18, pp. 11921–11945, 2020, https://doi.org/10.1007/s11042-019-08373-8
10. [10] H. Alvari, E. Shaabani, P. Shakarian, H. Alvari, E. Shaabani, and P. Shakarian, “Semi-Supervised Causal Inference for Identifying Pathogenic Social Media Accounts,” Identification of Pathogenic Social Media Accounts: From Data to Intelligence to Prediction, pp. 51–61, 2021, https://doi.org/10.1007/978-3-030-61431-7_5
11. [11] A. Ahmadi, M. Fotouhi, and M. Khaleghi, “Intelligent classification of web pages using contextual and visual features,” Applied Soft Computting, vol. 11, no. 2, pp. 1638–1647, 2011, https://doi.org/10.1016/j.asoc.2010.05.003
12. [12] A. Sun, E. P. Lim, and W. K. Ng, “Web classification using support vector machine,” in Proceedings of the 4th international workshop on Web information and data management, New York, NY, USA, WIDM02, Association for Computing Machinery,2002, pp. 96–99.
13. [13] X. Qi and B. D. Davison, “Knowing a web page by the company it keeps,” in Proceedings of the 15th ACM international conference on Information and knowledge management, CIKM06, New York, NY, USA, Association for Computing Machinery, 2006, pp. 228–237.
14. [14] L. Tian, D. Zheng, and C. Zhu, “Image classification based on the combination of text features and visual features,” International journal of intelligent systems, vol. 28, no. 3, pp. 242–256, 2013, https://doi.org/10.1002/int.21567
15. [15] O. W. Kwon and J. H. Lee, “Web page classification based on k-nearest neighbor approach,” in Proceedings of the fifth international workshop on Information retrieval with Asian languages, IRAL00, New York, NY, USA, Association for Computing Machinery, 2000, pp. 9–15.
16. [16] P. Calado, M. Cristo, E. Moura, N. Ziviani, B. Ribeiro-Neto, and M. A. Gonçalves, “Combining link-based and content-based methods for web document classification,” in Proceedings of the twelfth international conference on Information and knowledge management, CIKM03, New York, NY, USA , Association for Computing Machinery, 2003, pp. 394–401.
17. [17] K. Gürkahraman and R. Karakiş, “Brain tumors classification with deep learning using data augmentation,” Journal of the Faculty of Engineering and Architecture of Gazi University, vol. 36, no. 2, pp. 997–1011, 2021, https://doi.org/10.17341/gazimmfd.762056
18. [18] A. Tekerek, “A novel architecture for web-based attack detection using convolutional neural network,” Computers & Security, vol. 100, pp. 102096, 2021, https://doi.org/10.1016/j.cose.2020.102096
19. [19] R. Karakis, K. Gurkahraman, G. D. Mitsis, and M. H. Boudrias, “Deep learning prediction of motor performance in stroke individuals using neuroimaging data,” Journal of Biomedical Informatics, vol. 141, pp. 104357, 2023, https://doi.org/10.1016/j.jbi.2023.104357
20. [20] S. Savaş, N. TOPALOĞLU, Ö. KAZCI, and P. KOŞAR, “Comparison of deep learning models in carotid artery Intima-Media thickness ultrasound images: CAIMTUSNet,” Bilişim Teknolojileri Dergisi, vol. 15, no. 1, pp. 1–12, 2022, https://doi.org/10.17671/gazibtd.804617
21. [21] M. Kizilgul, R. Karakis, N. Dogan, H. Bostan, M. M. Yapici, U. Gul et al., “Real-time detection of acromegaly from facial images with artificial intelligence,” European journal of endocrinology, vol. 188, no. 1, pp. 158-165, 2023, https://doi.org/10.1093/ejendo/lvad005
22. [22] S. Savaş, “Detecting the stages of Alzheimer’s disease with pre-trained deep learning architectures,” Arabian Journal for Science and Engineering, vol. 47, no. 2, pp. 2201–2218, 2022, https://doi.org/10.1007/s13369-021-06131-3
23. [23] Y. Lin, “RNN-Enhanced Deep Residual Neural Networks for Web Page Classification,” Ph.D. dissertation, University of Calgary, Calgary, Canada, 2016.
24. [24] E. Buber and B. Diri, “Web page classification using RNN,” Procedia Computer Science, vol. 154, pp. 62–72, 2019, https://doi.org/10.1016/j.procs.2019.06.011
25. [25] D. Alsaleh and S. Larabi-Marie-Sainte, "Arabic Text Classification Using Convolutional Neural Network and Genetic Algorithms," IEEE Access, vol. 9, pp. 91670-91685, 2021, https://doi.org/10.1109/ACCESS.2021.3091376
26. [26] A. P. García-Plaza, V. Fresno, R. M. Unanue and A. Zubiaga, "Using Fuzzy Logic to Leverage HTML Markup for Web Page Representation," in IEEE Transactions on Fuzzy Systems, vol. 25, no. 4, pp. 919-933, Aug. 2017, https://doi.org/10.1109/TFUZZ.2016.2586971
27. [27] V. Petridis and V. G. Kaburlasos, "Clustering and classification in structured data domains using Fuzzy Lattice Neurocomputing (FLN)," in IEEE Transactions on Knowledge and Data Engineering, vol. 13, no. 2, pp. 245-260, March-April 2001, https://doi.org/10.1109/69.917564
28. [28] C. Haruechaiyasak, Mei-Ling Shyu and Shu-Ching Chen, "Web document classification based on fuzzy association," Proceedings 26th Annual International Computer Software and Applications, Oxford, UK, 2002, pp. 487-492.
29. [29] V. de Boer, M. van Someren, and T. Lupascu, “Web page classification using image analysis features,” in Web Information Systems and Technologies: 6th International Conference, WEBIST 2010, Valencia, Spain, April 7-10, 2011, pp. 272–285.
30. [30] D. S. Ugalde, “Android App for Automatic Web Page Classification: Analysis of Text and Visual Features,” Ph.D. dissertation, Universidade de Coimbra, Portugal, 2015.
31. [31] T. Gogar, O. Hubacek, and J. Sedivy, “Deep neural networks for web page information extraction,” in Artificial Intelligence Applications and Innovations, AIAI 2016, Thessaloniki, Greece, September 16-18 2016, Proceedings 12, 2016, pp. 154–163.
32. [32] L. Li, G. Gou, G. Xiong, Z. Cao, and Z. Li, “Identifying gambling and porn websites with image recognition,” in Advances in Multimedia Information Processing: 18th Pacific-Rim Conference on Multimedia, PCM 2017, Harbin, China, September 28-29, 2017, pp. 488–497.
33. [33] J. Sasaki, S. Li, and E. Herrera-Viedma, “A classification method of photos in a tourism website by color analysis,” in Advances and Trends in Artificial Intelligence. From Theory to Practice: 32nd International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2019, Graz, Austria, July 9–11, 2019, Proceedings 32, 2019, pp. 265–278.
34. [34] S. Abdali, R. Gurav, S. Menon, D. Fonseca, N. Entezari, N. Shah and E. E. Papalexakis, “Identifying misinformation from website screenshots,” in Proceedings of the International AAAI Conference on Web and social media, ICWSM-21, California, USA, June 7-10, 2021, pp. 2–13.
35. [35] M. M. Yapıcı, A. Tekerek and N. Topaloğlu, "Performance Comparison of Convolutional Neural Network Models on GPU," IEEE 13th International Conference on Application of Information and Communication Technologies (AICT), 23-25 October 2019, Baku, Azerbaijan [Online]. Available: IEEE Xplore, http://www.ieee.org. [Accessed: 06 Feb. 2020]
36. [36] Y. LeCun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard and L. Jackel, Advances in Neural Information Processing Systems: Handwritten digit recognition with a back-propagation network, Morgan-Kaufmann, 1990
37. [37] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, November 1998, https://doi.org/10.1109/5.726791
38. [38] A. Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep convolutional neural networks,” Communications of the ACM, vol. 60, no. 6, pp. 84-90, June 2017 https://doi.org/10.1145/3065386
39. [39] A. Tekerek and M. M. Yapici, “A novel malware classification and augmentation model based on convolutional neural network,” Computer & Security, vol. 112, pp. 102515, January 2022, https://doi.org/10.1016/j.cose.2021.102515
40. [40] K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, CVPR 2016, 26-29 June 2016, Las Vegas, USA [Online]. Available: https://cvpr2016.thecvf.com/. [Accessed: 01 July. 2016].
41. [41] G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” in Proceedings of the IEEE conference on computer vision and pattern recognition, CVPR 2017, 21-26 July 2016, Honolulu, Hawaii [Online]. Available: https://cvpr2017.thecvf.com/, [Accessed: 29 July. 2017].