What is it about?
paper is about developing a more accurate and efficient scientific article recommendation system by combining community detection and topic modeling techniques. Uses LS-SLM (Linear Scale Smart Local Moving) for detecting communities (groups of related papers) in a citation network. Applies PCC-LDA (Pearson Correlation Coefficient Latent Dirichlet Allocation) for topic modeling, to discover the main topics in each community. Builds recommendations based on the topics and structure of the communities.
Featured Image
Photo by Logan Voss on Unsplash
Why is it important?
It outperforms popular existing methods (like Louvain, SBM, SLM) in accuracy, precision, recall, modularity, and speed. The system is scalable, domain-specific, and helps generate more personalized recommendations.It’s about making it easier and faster for researchers to find useful scientific papers by grouping similar articles and understanding their topics, then recommending the most relevant ones.
Perspectives
Helps researchers discover relevant papers quickly, especially in vast digital libraries. Reduces time spent searching for literature and increases exposure to diverse, high-quality research. Provides domain-specific, interest-aligned recommendations—even for new users (solving the cold start problem).
Sandeep Kumar Rachamadugu
M.S.Ramaiah University of Applied Sciences, Bangalore
Read the Original
This page is a summary of: Effective community detection with topic modeling in article recommender systems using LS-SLM and PCC-LDA, Journal of Intelligent & Fuzzy Systems Applications in Engineering and Technology, March 2024, SAGE Publications,
DOI: 10.3233/jifs-233851.
You can read the full text:
Contributors
The following have contributed to this page
