Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Recent Advances and Trends in Research Paper Recommender Systems: A Comprehensive Survey

Iratxe Pinedo, Mikel Larrañaga, Ana Arruarte

TL;DR

The study addresses the challenge of locating relevant scientific literature amid exponential growth by surveying Research Paper Recommender Systems from 2021 to 2024. It analyzes how recommendations are generated, what data and representations are used, how systems are evaluated, and what challenges persist or have emerged, extending the methodology of prior work to enable cross-study comparability. Key contributions include a structured breakdown of inputs, representations, and procedures, a comprehensive catalog of datasets and evaluation practices, and a synthesis of evolving challenges—such as multidisciplinarity, dynamic preferences, and data accessibility—that guide future research. The findings highlight progress in personalization and embedding-based representations while underscoring ongoing gaps in explainability, reproducibility, and real-world deployment, with practical implications for deploying scalable, user-centered RPRS in diverse scholarly ecosystems.

Abstract

As the volume of scientific publications grows exponentially, researchers increasingly face difficulties in locating relevant literature. Research Paper Recommender Systems have become vital tools to mitigate this information overload by delivering personalized suggestions. This survey provides a comprehensive analysis of Research Paper Recommender Systems developed between November 2021 and December 2024, building upon prior reviews in the field. It presents an extensive overview of the techniques and approaches employed, the datasets utilized, the evaluation metrics and procedures applied, and the status of both enduring and emerging challenges observed during the research. Unlike prior surveys, this survey goes beyond merely cataloguing techniques and models, providing a thorough examination of how these methods are implemented across different stages of the recommendation process. By furnishing a detailed and structured reference, this work aims to function as a consultative resource for the research community, supporting informed decision-making and guiding future investigations in the advances of effective Research Paper Recommender Systems.

Recent Advances and Trends in Research Paper Recommender Systems: A Comprehensive Survey

TL;DR

The study addresses the challenge of locating relevant scientific literature amid exponential growth by surveying Research Paper Recommender Systems from 2021 to 2024. It analyzes how recommendations are generated, what data and representations are used, how systems are evaluated, and what challenges persist or have emerged, extending the methodology of prior work to enable cross-study comparability. Key contributions include a structured breakdown of inputs, representations, and procedures, a comprehensive catalog of datasets and evaluation practices, and a synthesis of evolving challenges—such as multidisciplinarity, dynamic preferences, and data accessibility—that guide future research. The findings highlight progress in personalization and embedding-based representations while underscoring ongoing gaps in explainability, reproducibility, and real-world deployment, with practical implications for deploying scalable, user-centered RPRS in diverse scholarly ecosystems.

Abstract

As the volume of scientific publications grows exponentially, researchers increasingly face difficulties in locating relevant literature. Research Paper Recommender Systems have become vital tools to mitigate this information overload by delivering personalized suggestions. This survey provides a comprehensive analysis of Research Paper Recommender Systems developed between November 2021 and December 2024, building upon prior reviews in the field. It presents an extensive overview of the techniques and approaches employed, the datasets utilized, the evaluation metrics and procedures applied, and the status of both enduring and emerging challenges observed during the research. Unlike prior surveys, this survey goes beyond merely cataloguing techniques and models, providing a thorough examination of how these methods are implemented across different stages of the recommendation process. By furnishing a detailed and structured reference, this work aims to function as a consultative resource for the research community, supporting informed decision-making and guiding future investigations in the advances of effective Research Paper Recommender Systems.

Paper Structure

This paper contains 40 sections, 3 figures.

Table of Contents

  1. Introduction
  2. Methodology
  3. Results
  4. How do the RPRS generate the recommendations?
  5. What type of input do the RPRS use to generate the recommendations?
  6. What kinds of information do the RPRS use to generate the recommendations?
  7. How do the RPRS represent the papers?
  8. How do the RPRS represent the users?
  9. How do the RPRS generate the recommendations?
  10. What datasets are used to train and evaluate the RPRS?
  11. ACL dataset
  12. DBLP
  13. AMiner
  14. CiteULike
  15. Other source datasets
  16. ...and 25 more sections

Figures (3)

  • Figure 1: Literature review process
  • Figure 2: Baselines and datasets
  • Figure :