An Author-Centric Framework Error Minimization in Scholarly Recommender System (Acfemsr)

Abstract

In the current landscape of computational innovations, the internet hosts a vast repository of publications sourced from various channels. Consequently, researchers encounter unprecedented challenges in identifying publications relevant to their research interests. Navigating through the multitude of options provided by search engines is not only impractical but also prone to selection errors – termed Recommendation Error (RE). These experiences underscore the need for novel research avenues. Previous studies have proposed numerous recommendation frameworks exclusively for scientific paper recommendations. However, many of these approaches have been plagued by RE, thereby compromising the integrity of recommendation systems. Recommendation Errors typically arise from underutilization of key features in the recommendation process. To mitigate Recommendation Errors, this study leverages publicly available metadata features, including Title, Abstract, Author(s), and keywords. Feature vectors for each candidate paper (CP) and the paper of interest (POI) are computed using CountVectorizer, and cosine similarity formula is employed to identify similar papers suitable for recommendations. The effectiveness of the proposed framework is evaluated using Error evaluation metrics such as Mean Absolute Error (MAE) and Root Mean Square Error (RMSE). Finally, the proposed Framework is compared against two previous Baseline approaches. The evaluation results demonstrate that the proposed approach exhibits lower Recommendation Errors compared to its baseline counterparts. Additionally, this research highlights the Author(s) feature as the most influential among the four features utilized by the Proposed Framework.