Evaluating collaborative filtering content recommenders for mobile phones

• Main Author: Piyasena, Indika Weliwe Gamage
• Other Authors: Chan, H Anthony
• Format: Dissertation
• Language: English
• Published: University of Cape Town 2014
• Subjects: Electrical Engineering
• Online Access: http://hdl.handle.net/11427/5124

Includes bibliographical references (leaves 64-67). === The high adoption of mobile phones coupled with 3G technology can extend Internet access to new communities. Yet such access is currently impractical because mobile phone interfaces are cumbersome to use. In addition, hierarchical menus and search engines pose an interaction barrier to the unfamiliar. A content recommender is proposed to address these issues. Collaborative filtering is a technique developed to make predictions on unobserved items based on the preferences of similar users. User-based collaborative filtering has been identified as a simple, yet reasonably accurate scheme. An evaluation is conducted into how quickly this algorithm can identify preferred content based on user-content interactions.