An overview and evaluation of citation recommendation models

Recommendation systems assist web users with personalized suggestions based on past preferences for products, or items including documents, books, movies, and research papers. The plethora and variety of research papers on the Web and digital libraries make it challenging for researchers to find relevant publications to their scholarly interests. To cope with this inevitable challenge, various models and algorithms have been proposed to assist researchers with personalized citation recommendations. Nevertheless, so far, no research study has exploited the validity and suitability of evaluations conducted for these models to find the most promising among them. This study investigates and examines the existing citation recommendation algorithms based on the following criteria: evaluation methods adopted, comparative baselines employed, the complexity of the proposed algorithm, reproducibility of the experimental results, and consistency and universality of the evaluation methods. Besides this, our study presents a generic architecture and process of a typical citation recommendation system and provides a brief overview of information filtering methods used in the existing models. The findings of the study have implications for researchers and practitioners working on research paper recommendation and related areas.