Novel Hybrid Approach to Content Recommendation based on Predicted Profiles

• Type: Article in International Conference Proceedings Book
• Date: 2013

Authors

Maria Teresa Andrade (Author) FEUP; Fábio Almeida (Author) Other

Conference proceedings International

Title: 2013 IEEE 10TH INTERNATIONAL CONFERENCE ON AND 10TH INTERNATIONAL CONFERENCE ON AUTONOMIC AND TRUSTED COMPUTING (UIC/ATC) UBIQUITOUS INTELLIGENCE AND COMPUTING

Pages: 507-514

IEEE 10th International Conference on Ubiquitous Intelligence and Computing (UIC) / IEEE 10th International Conference on Autonomic and Trusted Computing (ATC)

Sorrento Peninsula, ITALY, DEC 18-21, 2013

Indexing

ISI Web of Knowledge - 0 Citations

Scopus - 4 Citations

Scientific classification

FOS: Engineering and technology > Electrical engineering, Electronic engineering, Information engineering

CORDIS: Technological sciences > Technology > Internet technology

Other information

Authenticus ID: P-00G-DTS

DOI: 10.1109/uic-atc.2013.49

Abstract (EN): The present phenomenon of technology convergence is blurring away the frontiers between the Internet and the TV, operating a shift on the way TV is consumed. TV viewers have now access to a huge selection of TV programming as well as online contents, either previously broadcasted or natively produced for the Internet. This reality creates new necessities whilst opening new opportunities for the creation of services capable of filtering this information and presenting the user with the most relevant content. This article describes an innovative hybrid strategy for delivering recommendations of TV content to individual users. It was developed specifically for the TV entertainment services of hotels, but it can be applied to any multimedia consumption service. Without requiring users to explicitly rate the programs they have watched, it is still able to recommend similar programs to similar users. It adopts an improved Pearson correlation method to establish similarities between different users, comparing profiles that have been automatically generated based on the user viewing history. It builds a predicted user profile, which is then used within a content-based approach to generate recommendations.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 8