Social media content ranking based on social computing and user influence
Authors: Ntalianis, Klimis 
Emary, Ibrahiem El 
Salem, Abdel-Badeeh M. 
Issue Date: 1-Apr-2015
Conference: International Conference on Communications, management, and Information technology (ICCMIT'2015), 20-22 April 2015, Prague, Czech Republic 
Journal: Procedia Computer Science 
Volume: 65
Keywords: Bonacich's centrality, Business information processing, Content ranking, Degree centrality, Influence, Machine learning, Social computing, Social media
Abstract: 
In this paper an innovative social media content ranking scheme is proposed. The proposed unsupervised architecture takes into consideration user-content interactions, since social media posts receive likes, comments and shares from friends and other users. Additionally the influence of each user is modeled, based on the centrality theory. Towards this direction both the degree and Bonacich's centrality are estimated for each user. Finally, a novel content ranking component is introduced, which ranks posted items based on a social computing method, driven by the power and influence of social network users. Initial experiments on real life social networks content illustrate the promising performance of the proposed architecture. Additionally comparisons with random selection chronological ordering (RSPICO), random selection non-chronological ordering (RSPIn-CO) and "My Facebook Movie" algorithms are provided.
ISSN: 1877-0509
DOI: 10.1016/j.procs.2015.09.103
URI: https://uniwacris.uniwa.gr/handle/3000/2844
Type: Conference Paper
Department: Department of Business Administration 
School: School of Administrative, Economics and Social Sciences 
Affiliation: University of West Attica (UNIWA) 
Appears in Collections:Articles / Άρθρα

CORE Recommender
Show full item record

SCOPUSTM   
Citations

3
checked on Nov 3, 2024

Page view(s)

6
checked on Nov 5, 2024

Google ScholarTM

Check

Altmetric

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.