Optimization of Recommender Systems for Image-Based Website Themes Using Transfer Learning

Arif Mu'amar Wahid, Taqwa Hariguna, Giat Karyono
Pages 952-968
Abstract Views 732
PDF Downloads 993
Crossref Citations -
DOI https://doi.org/10.47738/jads.v6i2.671

Abstract


Recommender systems play a crucial role in personalizing user experiences in e-commerce, digital media, and web design. However, traditional methods such as Collaborative Filtering and Content-Based Filtering struggle to account for visual preferences, limiting their effectiveness in domains were aesthetics influence decision-making, such as website theme recommendations. These systems face challenges such as data sparsity, cold-start problems, and an inability to capture intricate visual features. To address these limitations, this study integrates Convolutional Neural Networks (CNNs) with advanced recommendation models, including Inception V3, DeepStyle, and Visual Neural Personalized Ranking (VNPR), to enhance the accuracy and personalization of visually-aware recommender systems. A quantitative research approach was employed, using controlled experiments to evaluate different combinations of feature extractors and recommendation models. Data was sourced from ThemeForest, a widely used platform for website themes, and underwent preprocessing to ensure consistency. The models were evaluated using precision, recall, F1 score, Mean Average Precision (MAP), and Normalized Discounted Cumulative Gain (NDCG) to measure recommendation quality. The results indicate that Inception V3 + VNPR outperforms other model combinations, achieving the highest accuracy in personalized theme recommendations. The integration of transfer learning further improved feature extraction and performance, even with limited training data. These findings underscore the importance of combining deep learning-based feature extraction with recommendation models to improve visually-driven recommendations. This study provides a comparative analysis of CNN-based recommender systems and contributes insights for optimizing recommendations in visually complex domains. Despite improvements, challenges such as dataset diversity remain a limitation, affecting generalizability. Future research could explore alternative CNN architectures, such as ResNet and DenseNet, and incorporate user feedback mechanisms to further enhance recommendation accuracy and adaptability.

Keywords


Alexnet; Inception V3; Recommender System; VNPR; Deepstyle

Full Text:

PDF

References


Q. Shambour, M. M. Abualhaj, and A. A. Abu-Shareha, “A Trust-Based Recommender System for Personalized Restaurants Recommendation,” Int. J. Electr. Comput. Eng. Syst., vol. 13, no. 4, pp. 293–299, 2022, doi: 10.32985/ijeces.13.4.5.

Dr. M. Alojail and S. Bhatia, “A Novel Technique for Behavioral Analytics Using Ensemble Learning Algorithms in E-Commerce,” Ieee Access, vol. 8, pp. 150072–150080, 2020, doi: 10.1109/access.2020.3016419.

Q. Shambour and J. Lu, “An Effective Recommender System by Unifying User and Item Trust Information for B2B Applications,” J. Comput. Syst. Sci., vol. 81, no. 7, pp. 1110–1126, 2015, doi: 10.1016/j.jcss.2014.12.029.

S. Bhattacharya and V. Anand, “What Makes the Indian Youths to Engage With Online Retail Brands: An Empirical Study,” Glob. Bus. Rev., vol. 22, no. 6, pp. 1507–1529, 2019, doi: 10.1177/0972150918822106.

P. Yürük, “The Mediating Role of Security and Privacy on the Relationship Between Customer Interface Features and E-Word of Mouth Marketing,” Turk. J. Mark., vol. 6, no. 2, pp. 125–142, 2021, doi: 10.30685/tujom.v6i2.118.

R. Hannula, A. Nikkilä, and K. Stefanidis, “GameRecs: Video Games Group Recommendations,” pp. 513–524, 2019, doi: 10.1007/978-3-030-30278-8_49.

A. Iorshase and O. I. Charles, “A Well-Built Hybrid Recommender System for Agricultural Products in Benue State of Nigeria,” J. Softw. Eng. Appl., vol. 08, no. 11, pp. 581–589, 2015, doi: 10.4236/jsea.2015.811055.

F. Ikram and H. Farooq, “Multimedia Recommendation System for Video Game Based on High-Level Visual Semantic Features,” Sci. Program., vol. 2022, pp. 1–12, 2022, doi: 10.1155/2022/6084363.

N. Torres, “A Multimodal User-Adaptive Recommender System,” Electronics, vol. 12, no. 17, p. 3709, 2023, doi: 10.3390/electronics12173709.

R. Mafrur, M. A. Sharaf, and G. Zuccon, “Quality Matters: Understanding the Impact of Incomplete Data on Visualization Recommendation,” pp. 122–138, 2020, doi: 10.1007/978-3-030-59003-1_8.

P. Kouki, J. Schaffer, J. Pujara, J. O’Donovan, and L. Getoor, “Generating and Understanding Personalized Explanations in Hybrid Recommender Systems,” Acm Trans. Interact. Intell. Syst., vol. 10, no. 4, pp. 1–40, 2020, doi: 10.1145/3365843.

R. He and J. McAuley, “VBPR: Visual Bayesian Personalized Ranking From Implicit Feedback,” Proc. Aaai Conf. Artif. Intell., vol. 30, no. 1, 2016, doi: 10.1609/aaai.v30i1.9973.

S. Zhang, L. Yao, A. Sun, and Y. Tay, “Deep Learning Based Recommender System,” Acm Comput. Surv., vol. 52, no. 1, pp. 1–38, 2019, doi: 10.1145/3285029.

A. K. Gahier and S. K. Gujral, “Cross Domain Recommendation Systems Using Deep Learning: A Systematic Literature Review,” SSRN Electron. J., 2021, doi: 10.2139/ssrn.3884919.

K. Danyluk, T. Ulusoy, W. Wei, and W. Willett, “Touch and Beyond: Comparing Physical and Virtual Reality Visualizations,” Ieee Trans. Vis. Comput. Graph., vol. 28, no. 4, pp. 1930–1940, 2022, doi: 10.1109/tvcg.2020.3023336.

F. Nagy, A. Haroun, H. Abdelkader, and A. Keshk, “A Review for Recommender System Models and Deep Learning,” Ijci Int. J. Comput. Inf., vol. 8, no. 2, pp. 170–176, 2021, doi: 10.21608/ijci.2021.207864.

R. A. Okaka, W. Mwangi, and G. Okeyo, “A Hybrid Approach for Personalized Recommender System Using Weighted TFIDF on RSS Contents,” Int. J. Comput. Appl. Technol. Res., vol. 5, no. 12, pp. 764–774, 2016, doi: 10.7753/ijcatr0512.1006.

W. Yu et al., “Visually Aware Recommendation With Aesthetic Features,” VLDB J., vol. 30, no. 4, pp. 495–513, 2021, doi: 10.1007/s00778-021-00651-y.

Y. Deldjoo, M. Schedl, P. Cremonesi, and G. Pasi, “Recommender Systems Leveraging Multimedia Content,” Acm Comput. Surv., vol. 53, no. 5, pp. 1–38, 2020, doi: 10.1145/3407190.

K. Wongsuphasawat, D. Moritz, A. Anand, J. D. Mackinlay, B. Howe, and J. Heer, “Voyager: Exploratory Analysis via Faceted Browsing of Visualization Recommendations,” Ieee Trans. Vis. Comput. Graph., vol. 22, no. 1, pp. 649–658, 2016, doi: 10.1109/tvcg.2015.2467191.

V. Puzyrev, “Deep Learning Electromagnetic Inversion With Convolutional Neural Networks,” Geophys. J. Int., vol. 218, no. 2, pp. 817–832, 2019, doi: 10.1093/gji/ggz204.

H. Wu and S. Prasad, “Convolutional Recurrent Neural Networks forHyperspectral Data Classification,” Remote Sens., vol. 9, no. 3, p. 298, 2017, doi: 10.3390/rs9030298.

S. Hosni, “Prediction of Postoperative Visual Acuity in Rhegmatogenous Retinal Detachment Using OCT Images,” Ieee Access, vol. 11, pp. 135435–135448, 2023, doi: 10.1109/access.2023.3338362.

S. Aghayari, A. Hadavand, S. M. Niazi, and M. Omidalizarandi, “Building Detection From Aerial Imagery Using Inception Resnet Unet and Unet Architectures,” Isprs Ann. Photogramm. Remote Sens. Spat. Inf. Sci., vol. X-4/W1-2022, pp. 9–17, 2023, doi: 10.5194/isprs-annals-x-4-w1-2022-9-2023.

S. Zhang, L. Yao, A. Sun, and Y. Tay, “Deep Learning Based Recommender System,” Acm Comput. Surv., vol. 52, no. 1, pp. 1–38, 2019, doi: 10.1145/3285029.

A. Potapov, S. A. Rodionov, H. Latapie, and E. Fenoglio, “Metric Embedding Autoencoders for Unsupervised Cross-Dataset Transfer Learning,” pp. 289–299, 2018, doi: 10.1007/978-3-030-01424-7_29.

A. Kensert, P. J. Harrison, and O. Spjuth, “Transfer Learning With Deep Convolutional Neural Networks for Classifying Cellular Morphological Changes,” Slas Discov., vol. 24, no. 4, pp. 466–475, 2019, doi: 10.1177/2472555218818756.

M. Hasanat, “Performance Evaluation of Transfer Learning Based Deep Convolutional Neural Network With Limited Fused Spectro-Temporal Data for Land Cover Classification,” Int. J. Electr. Comput. Eng. Ijece, vol. 13, no. 6, p. 6882, 2023, doi: 10.11591/ijece.v13i6.pp6882-6890.

N. Kimura, I. Yoshinaga, K. Sekijima, I. Azechi, and D. Baba, “Convolutional Neural Network Coupled With a Transfer-Learning Approach for Time-Series Flood Predictions,” Water, vol. 12, no. 1, p. 96, 2019, doi: 10.3390/w12010096.

M. J. Afridi, A. Ross, and E. M. Shapiro, “On Automated Source Selection for Transfer Learning in Convolutional Neural Networks,” Pattern Recognit., vol. 73, pp. 65–75, 2018, doi: 10.1016/j.patcog.2017.07.019.

N. Gozzi et al., “Image Embeddings Extracted From CNNs Outperform Other Transfer Learning Approaches in Classification of Chest Radiographs,” Diagnostics, vol. 12, no. 9, p. 2084, 2022, doi: 10.3390/diagnostics12092084.

S. Rajaraman et al., “Pre-Trained Convolutional Neural Networks as Feature Extractors Toward Improved Malaria Parasite Detection in Thin Blood Smear Images,” Peerj, vol. 6, p. e4568, 2018, doi: 10.7717/peerj.4568.

X. Chen, Y. Liu, L. Zhao, J. Fang, V. S. Sheng, and Z. Cui, “Exploiting Aesthetic Features in Visual Contents for Movie Recommendation,” Ieee Access, vol. 7, pp. 49813–49821, 2019, doi: 10.1109/access.2019.2910722.




DOI: https://doi.org/10.47738/jads.v6i2.671

Refbacks

  • There are currently no refbacks.


Barcode

Journal of Applied Data Sciences

ISSN:2723-6471 (Online)
Publisher:Bright Publisher
Website:http://bright-journal.org/JADS
Email:taqwa@amikompurwokerto.ac.id (principal contact)
  support@bright-journal.org (technical issues)

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0