Keywords
How to Cite
Abstract
In modern science, researchers are faced with problems with the analysis and selection of the necessary information in a large flow of information. This article is devoted to the development of an artificial intelligence system adapted to the needs of the user to optimize scientific activities. The system has the capabilities of a user profile, material analysis and creating suitable recommendations. The results of the experiment with the participation of 50 researchers showed that the system analyzed the loaded materials in an average of 3.2 minutes and presented recommendations corresponding to the needs of the user with an accuracy of 87%. The recommendations were rated useful by 92% of users. This research significantly simplifies scientific activity and opens up new opportunities in the management of information flow. Future work focuses on adapting the system to multilingualism, in-depth analysis of complex terms, and providing real-time recommendations.
CCS Concepts
- Artificial Intelligence → Natural Language Processing
- Human-Centered Computing → Recommendation Systems
- Computing Methodologies → Machine Learning Approaches
References
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. arXiv preprint arXiv:1810.04805.
Beel, J., Gipp, B., Langer, S., & Breitinger, C. (2016). Research-paper recommender systems: A literature survey. International Journal on Digital Libraries, 17(4), 305-338.
Ortega, J. L., & Aguillo, I. F. (2014). Microsoft Academic Search and Google Scholar: The accuracy of citation graphs. Scientometrics, 94(3), 979-985.
Ammar, W., Groeneveld, D., Bhagavatula, C., et al. (2018). Construction of the literature graph in Semantic Scholar. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.
Nallapati, R., Zhou, B., Gulcehre, C., & Xiang, B. (2017). Abstractive Text Summarization using Sequence-to-Sequence RNNs and Beyond. arXiv preprint arXiv:1602.06023.
Jones, K., & Richardson, M. (2017). Enhancing personalized academic recommendations through collaborative filtering. Journal of Information Science, 43(6), 837-850.
This work is licensed under a Creative Commons Attribution 4.0 International License.