Evolution of Scientific Interests: A Time-Aware Recommender System

• Bruno S. B. Contreras USP
• Luciano A. Digiampietri USP

DOI: https://doi.org/10.5753/brasnam.2025.7174

Resumo

The increasing volume of scientific publications makes it challenging for researchers to stay updated. Traditional recommendation systems often overlook the evolving nature of academic interests, leading to outdated suggestions. This article introduces a time-aware recommendation system (TARS) that incorporates temporal dynamics to improve the relevance of scientific article recommendations. In experiments with OpenAlex data, TARS outperformed static models, achieving up to 12% better precision and recall, particularly for active researchers. The study highlights the importance of temporal modeling in capturing evolving preferences and enhancing engagement in academic information systems.

Referências

Bai, X., Wang, M., Lee, I., Yang, Z., Kong, X., and Xia, F. (2019). Scientific paper recommendation: A survey. IEEE Access, 7:9324–9339.

Campos, P. G., Díez, F., and Cantador, I. (2013). Time-aware recommender systems: a comprehensive survey and analysis of existing evaluation protocols. User Modeling and User-Adapted Interaction, 24(1–2):67–119.

Chen, Y.-C., Hui, L., and Thaipisutikul, T. (2020). A collaborative filtering recommendation system with dynamic time decay. The Journal of Supercomputing, 77(1):244–262.

Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Burstein, J., Doran, C., and Solorio, T., editors, Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota. Association for Computational Linguistics.

Grover, A. and Leskovec, J. (2016). node2vec: Scalable feature learning for networks.

Gómez-Losada, A. and Duch-Brown, N. (2019). Time Series Forecasting by Recommendation: An Empirical Analysis on Amazon Marketplace, page 45–54. Springer International Publishing.

Ikoma, T. and Matsubara, S. (2023). Paper recommendation using citation contexts in scholarly documents. In Huang, C.-R., Harada, Y., Kim, J.-B., Chen, S., Hsu, Y.-Y., Chersoni, E., A, P., Zeng, W. H., Peng, B., Li, Y., and Li, J., editors, Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation, pages 710–716, Hong Kong, China. Association for Computational Linguistics.

Jiang, C., Ma, X., Zeng, J., Zhang, Y., Yang, T., and Deng, Q. (2023). Taprec: time-aware paper recommendation via the modeling of researchers’ dynamic preferences. Scientometrics, 128(6):3453–3471.

Kuznetsov, S. and Kordík, P. (2023). Overcoming the Cold-Start Problem in Recommendation Systems with Ontologies and Knowledge Graphs, page 591–603. Springer Nature Switzerland.

Le, Q. V. and Mikolov, T. (2014). Distributed representations of sentences and documents.

Ly, K., Kashnitsky, Y., Chamezopoulos, S., and Krzhizhanovskaya, V. (2024). Article classification with graph neural networks and multigraphs. In Calzolari, N., Kan, M.-Y., Hoste, V., Lenci, A., Sakti, S., and Xue, N., editors, Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 1539–1547, Torino, Italia. ELRA and ICCL.

Mena-Chalco, J. P., Digiampietri, L. A., Lopes, F. M., and Cesar, R. M. (2014). Brazilian bibliometric coauthorship networks. Journal of the Association for Information Science and Technology, 65(7):1424–1445.

Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient estimation of word representations in vector space.

Perera, D. and Zimmermann, R. (2020). Towards comprehensive recommender systems: Time-aware unified recommendations based on listwise ranking of implicit cross-network data. Proceedings of the AAAI Conference on Artificial Intelligence, 34(01):189–197.