Korab Rrmoku
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Korab Rrmoku has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Besnik Selimi
South East European University
2 shared publications - Lule Ahmedi
University of Prishtina
2 shared publications Besnik Selimi
South East Europe University
1 shared publication
Latest Publications
- Open Access
- 1 October 2022
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 12 (5) , 5383-5392
Provenance and social network analysis for recommender systems: a literature review
Recommender systems (RS) and their scientific approach have become very important because they help scientists find suitable publications and approaches, customers find adequate items, tourists find their preferred points of interest, and many more recommendations on domains. This work will present a literature review of approaches and the influence that social network analysis (SNA) and data provenance has on RS. The aim is to analyze differences and similarities using several dimensions, public datasets for assessing their impacts and limitations, evaluations of methods and metrics along with their challenges by identifying the most efficient approaches, the most appropriate assessment data sets, and the most appropriate assessment methods and metrics. Hence, by correlating these three fields, the system will be able to improve the recommendation of certain items, by being able to choose the recommendations that are made from the most trusted nodes/resources within a social network. We have found that content-based filtering techniques, combined with term frequency-inverse document frequency (TF-IDF) features are the most feasible approaches when combined with provenance since our focus is to recommend the most trusted items, where trust, distrust, and ignorance are calculated as weight in terms of the relationship between nodes on a network.
- 1 October 2022
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 12 (5) , 5383-5392
Open AccessProvenance and social network analysis for recommender systems: a literature review
Recommender systems (RS) and their scientific approach have become very important because they help scientists find suitable publications and approaches, customers find adequate items, tourists find their preferred points of interest, and many more recommendations on domains. This work will present a literature review of approaches and the influence that social network analysis (SNA) and data provenance has on RS. The aim is to analyze differences and similarities using several dimensions, public datasets for assessing their impacts and limitations, evaluations of methods and metrics along with their challenges by identifying the most efficient approaches, the most appropriate assessment data sets, and the most appropriate assessment methods and metrics. Hence, by correlating these three fields, the system will be able to improve the recommendation of certain items, by being able to choose the recommendations that are made from the most trusted nodes/resources within a social network. We have found that content-based filtering techniques, combined with term frequency-inverse document frequency (TF-IDF) features are the most feasible approaches when combined with provenance since our focus is to recommend the most trusted items, where trust, distrust, and ignorance are calculated as weight in terms of the relationship between nodes on a network.
- Open Access
- 12 January 2022
- Published by MDPI AG in Computation
- Vol. 10 (1) , 6
Application of Trust in Recommender Systems—Utilizing Naive Bayes Classifier
Receiving a recommendation for a certain item or a place to visit is now a common experience. However, the issue of trustworthiness regarding the recommended items/places remains one of the main concerns. In this paper, we present an implementation of the Naive Bayes classifier, one of the most powerful classes of Machine Learning and Artificial Intelligence algorithms in existence, to improve the accuracy of the recommendation and raise the trustworthiness confidence of the users and items within a network. Our approach is proven as a feasible one, since it reached the prediction accuracy of 89%, with a confidence of approximately 0.89, when applied to an online dataset of a social network. Naive Bayes algorithms, in general, are widely used on recommender systems because they are fast and easy to implement. However, the requirement for predictors to be independent remains a challenge due to the fact that in real-life scenarios, the predictors are usually dependent. As such, in our approach we used a larger training dataset; hence, the response vector has a higher selection quantity, thus empowering a higher determining accuracy.
- 12 January 2022
- Published by MDPI AG in Computation
- Vol. 10 (1) , 6
Open AccessApplication of Trust in Recommender Systems—Utilizing Naive Bayes Classifier
Receiving a recommendation for a certain item or a place to visit is now a common experience. However, the issue of trustworthiness regarding the recommended items/places remains one of the main concerns. In this paper, we present an implementation of the Naive Bayes classifier, one of the most powerful classes of Machine Learning and Artificial Intelligence algorithms in existence, to improve the accuracy of the recommendation and raise the trustworthiness confidence of the users and items within a network. Our approach is proven as a feasible one, since it reached the prediction accuracy of 89%, with a confidence of approximately 0.89, when applied to an online dataset of a social network. Naive Bayes algorithms, in general, are widely used on recommender systems because they are fast and easy to implement. However, the requirement for predictors to be independent remains a challenge due to the fact that in real-life scenarios, the predictors are usually dependent. As such, in our approach we used a larger training dataset; hence, the response vector has a higher selection quantity, thus empowering a higher determining accuracy.