Affiliations: Department of Computer Science, University of Delhi, Delhi, India
Correspondence:
[*]
Corresponding author. Chhavi Sharma, Department of Computer Science, University of Delhi, Delhi, India. Tel.: +91 11 27667591; Fax: +91 11 27662553; E-mail: [email protected].
Abstract: With the enormous growth in the volume of online data, users are flooded with a gigantic amount of information. This has made the task of Recommender systems (RSs) even more engrossing. Research in RSs has been revolving around newer concepts like social factors, context of the user and the groups they belong to. This paper presents the design and development of a Community based Collaborative Filtering Recommender System (CCFRS). Louvain method of community detection has been applied to discover communities in the dataset. The method of generating recommendations is based on the proposed idea of Item Frequency-Inverse Community Frequency (IF-ICF) score of each item in the target user’s community. IF scores help finding the set of items which are unique to a particular community. ICF values are inversely proportional to the number of communities in which an item has been rated. It is used to calculate the uniqueness of the item across the communities. The IF-ICF scores of the items are further employed to find the prediction scores of items unseen by the user in order to present a set of top ‘n’ recommendations to the user. A prototype of the system is developed using Java and experimental analysis has been carried out for the domain of books.
Keywords: Recommender Systems (RSs), community detection, Louvain method, IF-ICF
