Konu benzerliğine dayalı makale tavsiye sistemi

Year 2021, Volume: IDAP-2021 : 5th International Artificial Intelligence and Data Processing symposium Issue: Special, 175 - 183, 20.10.2021

Esra Gündoğan Mehmet Kaya

https://doi.org/10.53070/bbd.990438

Abstract

Akademik ilerleme ile beraber araştırmacılar tarafından yayınlanan makale sayısı her geçen gün artmaktadır. Yayın sayısındaki artış ilgilenilen konu ile ilgili çalışmalara ulaşmayı zorlaştırmaktadır. Tavsiye sistemleri bu noktada araştırmacılar için önemli bir araçtır. Kullanıcıların profiline ya da yayınların konu benzerliğine dayalı makale tavsiye sistemleri istenilen bilgiye ulaşmada kullanıcılara oldukça yardımcı olmaktadır. Bu çalışmada girilen makalenin konusuna benzer makaleleri tavsiye etmek için bir yaklaşım önerilmiştir. Oluşturulan sistem doküman benzerliği, kümeleme ve anahtar kelime çıkarımı konularının birleştirilmesiyle hem anahtar kelime hem de içerik benzerliklerini dikkate alarak makale tavsiye etmektedir. Derin öğrenme tabanlı yöntemlerin çalışmanın her adımında kullanılması tavsiye sisteminin performansını artırmıştır. Çalışma bilgisayar biliminde makine öğrenmesi, yapay zeka, insan bilgisayar etkileşimi gibi farklı kategorilerden makaleleri içeren bir veri seti üzerinde uygulanmıştır. Kullanıcılara sorguları ile yüksek benzerliğe sahip makaleler önerilmiştir. Böylece istenilen konuya yönelik çalışmalara erişim daha hızlı ve daha kolay bir hale getirilmiştir.

Keywords

anahtar kelime çıkarımı, doküman benzerliği, kümeleme, makale tavsiye sistemi

Supporting Institution

Fırat Üniversitesi Bilimsel Araştırma Projeleri Koordinasyon Birimi

Project Number

MF.20.09

Thanks

Bu çalışma Fırat Üniversitesi Bilimsel Araştırma Projeleri Koordinasyon Birimi tarafından MF.20.09 numaralı proje kapsamında desteklenmiştir.

Paper recommendation system based on topic similarity

Abstract

Along with academic progress, the number of papers published by researchers is increasing day by day. The increase in the number of publications makes it difficult to reach studies on the subject of interest. Recommendation systems are an important tool for researchers at this point. Paper recommendation systems based on the profile of the users or the topic similarity of the publications are very helpful to the users in reaching the desired information. In this study, an approach is proposed to recommend papers similar to the subject of the paper searched. The created system recommends papers considering both keyword and content similarities by combining document similarity, clustering, and keyword extraction. The use of deep learning-based methods in every step of the study has increased the performance of the recommendation system. The study has been applied to a dataset containing papers from different categories such as machine learning in computer science, artificial intelligence, human-computer interaction. Users are offered papers with high similarity to their queries. Thus, access to studies on the subject of interest has been made faster and easier.

Keywords

keyword extraction, document similarity, clustering, paper recommendation system

Project Number

MF.20.09

References

• Xia, F., Wang, W., Bekele, T. M., and Liu, H. (2017). Big scholarly data: A survey. IEEE Transactions on Big Data, 3(1), 18-35.
• Liu, H., Kou, H., Yan, C., and Qi, L. (2020). Keywords-driven and popularity-aware paper recommendation based on undirected paper citation graph. Complexity, 2020.
• Y. C. Lee et al., “Recommendation of research papers in DBpia: A Hybrid approach exploiting content and collaborative data,” in 2016 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2016 - Conference Proceedings, 2017, pp. 2966–2971.
• Pan, L., Dai, X., Huang, S., and Chen, J. (2015). Academic paper recommendation based on heterogeneous graph. In Chinese computational linguistics and natural language processing based on naturally annotated big data (pp. 381-392). Springer, Cham.
• J. D. West, I. Wesley-Smith, and C. T. Bergstrom, (2016). “A Recommendation System Based on Hierarchical Clustering of an Article-Level Citation Network,” IEEE Trans. Big Data, vol. 2, no. 2, pp. 113–123.
• Son, J., and Kim, S. B. (2018). Academic paper recommender system using multilevel simultaneous citation networks. Decision Support Systems, 105, 24-33.
• F. Xia, H. Liu, I. Lee, and L. Cao, (2016). Scientific Article Recommendation: Exploiting Common Author Relations and Historical Preferences, IEEE Trans. Big Data, vol. 2, no. 2, pp. 101–112.
• Bulut, B., Gündoğan, E., Kaya, B., Alhajj, R., and Kaya, M. (2020). User’s research interests based paper recommendation system: A deep learning approach. In Putting Social Media and Networking Data in Practice for Education, Planning, Prediction and Recommendation (pp. 117-130). Springer, Cham.
• L. Steinert, and H. U. Hoppe, (2016). A comparative analysis of networkbased similarity measures for scientific paper recommendations. In 2016 Third European Network Intelligence Conference (ENIC) (pp. 17-24). IEEE.
• Q. Le, and T. Mikolov, (2014). Distributed representations of sentences and documents. In International conference on machine learning (pp. 1188-1196).
• Gündoğan, E., and Kaya, M. (2019, September). Evaluation of Session-Suitability of Papers in Conference Programs. In 2019 International Artificial Intelligence and Data Processing Symposium (IDAP) (pp. 1-5). IEEE.
• Shirkhorshidi, A. S., Aghabozorgi, S., Wah, T. Y., and Herawan, T. (2014). Big data clustering: a review. In International conference on computational science and its applications (pp. 707-720). Springer, Cham.
• Lorbeer, B., Kosareva, A., Deva, B., Softić, D., Ruppel, P., and Küpper, A. (2018). Variations on the clustering algorithm BIRCH. Big data research, 11, 44-53.
• Xia, X. (2020). Clustering Analysis of Interactive Learning Activities Based on Improved BIRCH Algorithm. arXiv preprint arXiv:2010.03821.
• Wang, H., Ye, J., Yu, Z., Wang, J., and Mao, C. (2020). Unsupervised keyword extraction methods based on a word graph network. International Journal of Ambient Computing and Intelligence (IJACI), 11(2), 68-79.
• Firoozeh, N., Nazarenko, A., Alizon, F., and Daille, B. (2020). Keyword extraction: Issues and methods. Natural Language Engineering, 26(3), 259-291.
• Bharti, S. K., and Babu, K. S. (2017). Automatic keyword extraction for text summarization: A survey. arXiv preprint arXiv:1704.03242.
• Qingyun, Z., Yuansheng, F., Zhenlei, S., and Wanli, Z. (2020). Keyword extraction method for complex nodes based on TextRank algorithm. In 2020 International Conference on Computer Engineering and Application (ICCEA) (pp. 359-363). IEEE.
• Pan, S., Li, Z., and Dai, J. (2019). An improved TextRank keywords extraction algorithm. In Proceedings of the ACM Turing Celebration Conference-China (pp. 1-7).