Bilimsel dergi tavsiyesi için içerik tabanlı bir yaklaşım

Akademik bilginin yayılımı açısından araştırmacılar tarafından yazılan makalelerin uygun dergilere gönderilmesi oldukça önemlidir. Bilimsel dergilerin sayısındaki artış araştırma alanına yönelik dergileri bulma sürecini zorlaştırmaktadır. Tavsiye sistemleri doğru dergileri bulma konusunda araştırmacılar için büyük kolaylık sağlamaktadır. Genellikle kullanıcı profiline özgü tavsiye yapan sistemler yeni araştırmacılar için kullanışlı değildir. Bu durum göz önünde bulundurulup sadece kullanıcı tarafından girilen makalenin içeriği dikkate alınarak gerçekleştirilen bir tavsiye sistemi sunulmaktadır. Dergilerin konu kapsamının belirlenmesi ise diğer çalışmalardan farklı olarak daha önceden yayınladıkları makalelerden belirlenmiştir. Dergiler için hazırlanan dokümanlar ile makalenin benzerlikleri karşılaştırılarak kullanıcılara dergi tavsiye edilmektedir. Tavsiye sisteminden elde edilen sonuçlar dergi yayıncılarının tavsiye araçlarından elde edilen sonuçlar ile karşılaştırılarak sistemin başarısı değerlendirilmiştir. Farklı yayıncılara ait birçok dergiyi kapsayan sistem iyi bir performans göstermiştir.

Anahtar Kelimeler:

doküman benzerliği, derin öğrenme, dergi tavsiye sistemleri

A content-based approach for scholarly journal recommendation

In terms of the dissemination of academic information, it is very important that the articles written by the researchers are sent to the appropriate journals. The increase in the number of scholarly journals complicates the process of finding journals related to the field of research. Recommendation systems provide a great convenience for researchers in finding the right journals. Generally, user profile-based recommendation systems are not useful for new researchers. Considering this situation, a recommendation system is presented by considering only the content of the article entered by the user. The determination of the subjects of the journals, unlike other studies, was determined from the articles they had previously published. By comparing the similarities of the documents prepared for the journals and the article, suitable journals are recommended to the users. The results obtained from the recommendation system are compared with the results obtained from the recommendation tools of the journal publishers, and the success of the system has been evaluated. The system, covering many journals from different publishers, has performed well.

Keywords:

document similarity, deep learning, journal recommendation systems,

PDF

___

Bobadilla, J., Ortega, F., Hernando, A., Gutiérrez, A. (2013). Recommender systems survey. Knowledge-based systems, 46, 109-132.
Konstan, J. A., Riedl, J. (2012). Recommender systems: from algorithms to user experience. User modeling and user-adapted interaction, 22(1), 101-123.
Bulut, B., Gündoğan, E., Kaya, B., Alhajj, R., 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.
Luong, H. P., Huynh, T., Gauch, S., Hoang, K. (2012, May). Exploiting Social Networks for Publication Venue Recommendations. In Kdir (pp. 239-245).
Jain, S., Khangarot, H., Singh, S. (2019). Journal recommendation system using content-based filtering. In Recent developments in machine learning and data analytics (pp. 99-108). Springer, Singapore.
Pradhan, T., Pal, S. (2020). A hybrid personalized scholarly venue recommender system integrating social network analysis and contextual similarity. Future Generation Computer Systems, 110, 1139-1166.
Sardar, A., Ferzund, J., Suryani, M. A., Shoaib, M. (2017). Recommender system for journal articles using opinion mining and semantics. International Journal of Advanced Computer Science and Applications, 8(12), 213-220.
Ogunde, A. O., Odim, M. O., Olaniyan, O. O., Ojewumi, T. O., Oyenike, A., Oguntunde, M. A. F., Bolanle, T. H. The Design of a Hybrid Model-Based Journal Recommendation System.
Abbasi, I. I., Abbas, M. A., Hammad, S., Jilani, M. T., Ahmed, S., un Nisa, S. (2020, February). A Hybrid Approach for the Recommendation of Scholarly Journals. In 2020 International Conference on Information Science and Communication Technology (ICISCT) (pp. 1-6). IEEE.
Kim, J. (2020, December). Academic journal recommendation for human neuroimaging studies via brain activation-based filtering. In 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) (pp. 1964-1967). IEEE.
Kang, N., Doornenbal, M. A., Schijvenaars, R. J. (2015, September). Elsevier journal finder: recommending journals for your paper. In Proceedings of the 9th ACM Conference on Recommender Systems (pp. 261-264).
Ghosal, T., Chakraborty, A., Sonam, R., Ekbal, A., Saha, S., Bhattacharyya, P. (2019, June). Incorporating full text and bibliographic features to improve scholarly journal recommendation. In 2019 ACM/IEEE Joint Conference on Digital Libraries (JCDL) (pp. 374-375). IEEE.
Gündoğan, E., Kaya, M. (2019, November). Creating Special Issues Automatically for Papers Accepted in Journals. In 2019 1st International Informatics and Software Engineering Conference (UBMYK) (pp. 1-4). IEEE.
Gündoğan, E., Kaya, M. (2020, November). Research paper classification based on Word2vec and community discovery. In 2020 International Conference on Decision Aid Sciences and Application (DASA) (pp. 1032-1036). IEEE.
Le, Q., Mikolov, T. (2014, June). Distributed representations of sentences and documents. In International conference on machine learning (pp. 1188-1196). PMLR.
L. Zhou, (2015). Research on the principle and application of Word2vec, SciTech Information Development & Economy, vo1.25, no.2, pp. 145- 148.
Gargiulo, F., Silvestri, S., Fontanella, M., Ciampi, M., De Pietro, G. (2018, May). A deep learning approach for scientific paper semantic ranking. In International Conference on Intelligent Interactive Multimedia Systems and Services (pp. 471-481). Springer, Cham.
https://dblp.org/db/journals/publ/index.html