Problem Statement
Navigating through vast repositories of scientific research papers can be
overwhelming for researchers. An efficient recommendation system is needed to
assist researchers in discovering relevant papers tailored to their interests.
Abstract
This project aims to implement an AI-based recommendation system for
scientific research papers. Using machine learning algorithms, the system will
analyze researchers’ preferences, citation patterns, and topics of interest to
provide personalized recommendations, fostering efficient knowledge discovery
in the scientific community.
Outcome
An intelligent recommendation system that assists researchers in finding
relevant scientific papers, accelerating the literature review process and
promoting interdisciplinary knowledge discovery
Reference
Artificial Intelligence (AI) is a modern engineering method to make machines think or use their intelligence like humans by mimicking traits and by learning to take appropriate decisions and to perform assigned tasks properly. Some of the companies which have done remarkable work in the field of Artificial Intelligence (AI) are Facebook, Google, Microsoft, IBM, etc. which are investing millions and billions in this very field of AI development and research. Currently there is a huge market and need for building Intelligent Systems for Recommendation. To counter this, one of the easiest and most preferable System is Recommendation System (RS). Recommendation Systems had proved to play an important role in the field of E-Commerce websites, Online Shopping, Dating Apps, Social-Networking, Digital Marketing, Online Advertisements, etc. by providing personalized recommends and feedback to users according to their preferences and choices. The topic of this report is AI based Recommendation System. As the topic of this paper suggests we are going to discuss about various ways and approaches of Artificial Intelligence (AI) to build a Recommendation System (RS) application. There are many approaches to build a recommendation system according to one’s need like Collaborative Filtering, Content based Recommendation Systems, Hybrid Systems, Artificial Neural Networks, Swarm Intelligence, Evolutionary Computing, Fuzzy Sets, etc. which will be briefly discussed in this report, but we will primarily discuss and work on Collaborative Filtering approach and about the problems like Cold start, Sparsity, Scalability and some others.
- R. Armstrong, D. Freitag, T. Joahims, and T. Mitchell, “WebWatcher: A learning apprentice for the World Wide Web,” Proceedings of the 12th National Conference on Artificial Intelligence, 1995.
- M. Balabanovic and Y. Shoham, “Fab: Content-based collaborative recommendation,” Communications of the ACM, vol. 40, no. 3, 1997.
- C. Basu, H. Hirsh, and W. Cohen, “Recommendation as classification: Using social and content-based information in recommendation,” Proceedings of the 15th National Conference on Artificial Intelligence, 1998.
- D. Billsus and M. Pazzani, “Learning collaborative information filters,” Proceedings of the International Conference on Machine Learning, 1998.
- J. Breese, D. Heckerman, and C. Kadie, “Empirical analysis of predictive algorithms for collaborative filtering,” Proceedings of the 14th Conference of Uncertainty in Artificial Intelligence, 1998.
https://ieeexplore.ieee.org/document/9362962/references#references