Ranking Online Social Users by their Influence

Autor: Anastasios Giovanidis, Antoine Vendeville, Bruno Baynat, Clémence Magnien
Přispěvatelé: Networks and Performance Analysis (NPA), LIP6, Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS)-Sorbonne Université (SU)-Centre National de la Recherche Scientifique (CNRS), ComplexNetworks, ANR, ANR-19-CE25-0011,FairEngine,Ingénierie des plates-formes sociales équitables(2019)
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
Theoretical computer science
Computer Networks and Communications
Computer science
Markov chain
Twitter
02 engineering and technology
System of linear equations
Measure (mathematics)
[INFO.INFO-SI]Computer Science [cs]/Social and Information Networks [cs.SI]
Ranking (information retrieval)
law.invention
Computer Science - Networking and Internet Architecture
[INFO.INFO-NI]Computer Science [cs]/Networking and Internet Architecture [cs.NI]
PageRank
ranking
law
0202 electrical engineering
electronic engineering
information engineering

FOS: Mathematics
Electrical and Electronic Engineering
Social and Information Networks (cs.SI)
Networking and Internet Architecture (cs.NI)
Social graph
influence
Computer Science - Performance
model
online social network
Node (networking)
Rank (computer programming)
[INFO.INFO-WB]Computer Science [cs]/Web
Probability (math.PR)
020206 networking & telecommunications
Computer Science - Social and Information Networks
graph
Computer Science Applications
Performance (cs.PF)
Graph (abstract data type)
Weibo
Software
Mathematics - Probability
Zdroj: IEEE/ACM Transactions on Networking
IEEE/ACM Transactions on Networking, IEEE/ACM, 2021, ⟨10.1109/TNET.2021.3085201⟩
IEEE/ACM Transactions on Networking, IEEE/ACM, 2021
ISSN: 1063-6692
DOI: 10.48550/arxiv.2107.01914
Popis: We introduce an original mathematical model to analyse the diffusion of posts within a generic online social platform. The main novelty is that each user is not simply considered as a node on the social graph, but is further equipped with his/her own Wall and Newsfeed, and has his/her own individual self-posting and re-posting activity. As a main result using our developed model, we derive in closed form the probabilities that posts originating from a given user are found on the Wall and Newsfeed of any other. These are the solution of a linear system of equations, which can be resolved iteratively. In fact, our model is very flexible with respect to the modelling assumptions. Using the probabilities derived from the solution, we define a new measure of per-user influence over the entire network, the $\Psi$-score, which combines the user position on the graph with user (re-)posting activity. In the homogeneous case where all users have the same activity rates, it is shown that a variant of the $\Psi$-score is equal to PageRank. Furthermore, we compare the new model and its $\Psi$-score against the empirical influence measured from very large data traces (Twitter, Weibo). The results illustrate that these new tools can accurately rank influencers with asymmetric (re-)posting activity for such real world applications.
Comment: 18 pages, 7 figures, journal publications. arXiv admin note: text overlap with arXiv:1902.07187
Databáze: OpenAIRE