Abstract
A challenge for many young adults is to find the right institution to follow higher education. Global university rankings are a commonly used, but inefficient tool, for they do not consider a person's preferences and needs. For example, some persons pursue prestige in their higher education, while others prefer proximity. This paper develops and evaluates a university recommender system, eliciting user preferences as ratings to build predictive models and to generate personalized university ranking lists. In Study 1, we performed offline evaluation on a rating dataset to determine which recommender approaches had the highest predictive value. In Study 2, we selected three algorithms to produce different university recommendation lists in our online tool, asking our users to compare and evaluate them in terms of different metrics (Accuracy, Diversity, Perceived Personalization, Satisfaction, and Novelty). We show that a SVD algorithm scores high on accuracy and perceived personalization, while a KNN algorithm scores better on novelty. We also report findings on preferred university features.
Highlights
Recommender Systems have been used in various domains to retrieve and suggest personalized content to users
We examined which of our collaborative filtering recommender approaches had the highest predictive value when generating personalized university rankings
We found that the recommendation lists generated by the Singular Value Decomposition (SVD) algorithm (51%) led to higher levels of satisfaction than those produced by KNN2 (12–15%); both for Q9: t(40) = 3.56, p = 0.001, as well as for Q10: t(40) = 3.19, p = 0.003
Summary
Recommender Systems have been used in various domains to retrieve and suggest personalized content to users. Whereas the former has been the topic of various recommender system and learning analytics approaches [cf., Hasan et al (2016)], universities are rarely featured in personalized approaches (Rivera et al, 2018) This is arguably surprising, because a significant proportion of students attending higher education in G20 countries is not native to those countries (OECD, 2013) – even though most prospective students opt for institutions that are close to home, based on Evaluating a University Recommender System proximity (Simões and Soares, 2010; White and Lee, 2020). Those who would like venture further in terms of proximity, would benefit from a personalized information-filtering system, such as a recommender system, since there are over ten thousand of higher education institutions worldwide to choose from 1
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
