•  
  •  
 

Abstract

Recommender systems are information filtering systems that offer personalized suggestions to users. Recommender-based applications are used in numerous areas, such as e-commerce, streaming services, textual media, restaurants, and tourism. Compared to traditional keyword-based search techniques, especially on systems with text-based storage, recommender systems stand out as more effective and customized systems for big data. With the expansion of the content pool on platforms where scientific study sharing is made, there is a significant increase in textual data use. This situation makes it difficult for researchers to access reliable and accurate papers in their domains. Researchers may spend a lot of time finding the most accurate publications to contribute to their studies. The scientific study recommender system helps researchers quickly find papers that are suitable for their interests. Scientific study recommender system offers publications to researchers, who have limited experience, to broaden their horizons and research interests. The content-based filtering method is the most widely used procedure in scientific study recommender system designs and is modeled independently from the user. In this study, a new content-based scientific study recommender system is comparatively suggested over different similarity methods. Although the methods and recommender weights vary, it is seen that the same publications are recommended within the same data set. When it is necessary to choose between methods that are close to each other as measurement values, it is concluded that the calculation time should be considered.

DOI

10.24012/dumf.838084

Included in

Engineering Commons

Share

COinS