Providing Personalized Services to Users in a Recommender System

Providing Personalized Services to Users in a Recommender System

Olukunle Oduwobi (Federal University of Technology, Akure, Nigeria) and Bolanle Adefowoke Ojokoh (Department of Computer Science, Federal University of Technology, Akure, Nigeria)
DOI: 10.4018/IJWLTT.2015040103
OnDemand PDF Download:
No Current Special Offers


Instructors recommend learning materials to a class of students not minding the learning ability and reading habit of each student. Learners are finding it problematic to make a decision about which available learning materials best meet their situation and will be beneficial to their course of study. In order to address this challenge, a new e-learning material recommender system that is able to recommend quality items to learners individually is required. The aim of this work is to develop a Personalized Recommender System that switches between Content-based and Collaborative filtering techniques, with an objective to design an algorithm to recommend electronic library materials, as well as personalize recommendations to both new and existing users. Experiments were conducted with evaluations showing that the recommender system was most effective when content-based filtering and collaborative filtering were used to recommend items for new users and existing users respectively, and still achieve personalization.
Article Preview

The current generation of recommendation methods can be classified into: Content-based Recommendations, Collaborative Recommendations, Knowledge-based Recommendations, Demographic Recommendations and Hybrid Recommendation.

Collaborative filtering (CF) is a common Web technique for generating personalized recommendations. Examples of its use include Amazon, iTunes, Netflix, LastFM, StumbleUpon, and Delicious, which are websites offering various multimedia services (Hoppe, 2009).While being the most successful recommendation technique to date (Resnick et al., 1994), it has difficulty dealing with new users. This is because there needs to be some correlation or better still, relationship among existing users. On the other hand, pure content-based recommendations ignore the preferences of other users (Schein, Popescul, & Ungar, 2002). Therefore, items that contain terms that relate well to the search and which are statistically less likely to be common are suggested first (Adomavicius & Tuzhilin, 2005). However, content-based filtering techniques are known to have issues involving limited content data and information, and concentration on bounded data. Knowledge-based recommendation gain leverage on recommendation tasks by using explicitmodels of both the user of the system and the products being recommended (Towle & Quinn, 2000). Demographic Recommendations categorizes the user based on personal attributes and makes recommendations based on demographic classes, e.g. college students, teenagers, women, men, etc. Grundy’s system (Guttman et al., 1998) is an example of a demographic filtering recommender system which recommended books based on personal information gathered through an interactive dialogue. A Hybrid recommendation system combines two or more recommendation techniques to gain better system optimization and fewer of the weaknesses of any individual ones(Prasad & Kumari, 2012). Such combination could be: Weighted, Switched, Featured, Cascaded, Augmented, Levelled or Mixed.

Complete Article List

Search this Journal:
Volume 18: 1 Issue (2023)
Volume 17: 8 Issues (2022)
Volume 16: 6 Issues (2021)
Volume 15: 4 Issues (2020)
Volume 14: 4 Issues (2019)
Volume 13: 4 Issues (2018)
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing