Factoring Personalization in Social Media Recommendations

GE, Mouzhi and Fabio PERSIA. Factoring Personalization in Social Media Recommendations. In Proceedings of the 13th IEEE International Conference on Semantic Computing. California, USA: IEEE, 2019, p. 344-347. ISBN 978-1-5386-6783-5. Available from: https://dx.doi.org/10.1109/ICOSC.2019.8665624.

Basic information

• Original name: Factoring Personalization in Social Media Recommendations
• Authors: GE, Mouzhi (156 China, guarantor, belonging to the institution) and Fabio PERSIA (380 Italy).
• Edition: California, USA, Proceedings of the 13th IEEE International Conference on Semantic Computing, p. 344-347, 4 pp. 2019.
• Publisher: IEEE

Other information

• Original language: English
• Type of outcome: Proceedings paper
• Field of Study: 10201 Computer sciences, information science, bioinformatics
• Country of publisher: United States of America
• Confidentiality degree: is not subject to a state or trade secret
• Publication form: printed version "print"
• RIV identification code: RIV/00216224:14330/19:00108947
• Organization unit: Faculty of Informatics
• ISBN: 978-1-5386-6783-5
• ISSN: 2325-6516
• Doi: http://dx.doi.org/10.1109/ICOSC.2019.8665624
• UT WoS: 000467270600058
• Keywords in English: recommender systems; personalization
• Tags: firank_B
• Tags: International impact, Reviewed

Abstract

Nowadays, since social media sites and online social networks have created big media data, it is thus complex and time-consuming for users to find the preferred social media from a large media catalog. Social media recommender systems are therefore emerged to recommend personalized media objects. However, most media recommender systems only focus on one aspect of social media. It is lacking a big picture of how to build an effective social media recommender system. Therefore, this paper tackles this challenge first for specifying the distinct features of media object that can be used for recommender systems, and then discusses five critical aspects that can affect the design of social media recommender systems. This paper further indicates how to assemble these critical aspects and concludes that when we apply traditional recommender algorithms in the media context, those are the critical aspects to improve and optimize social media recommneder systems.