Characterizing community behavior in OSNs: Modeling and forecasting activity on Facebook using the SARIMA model

Article type: Research Article

Authors: Idrais, Jaafar^{a; *} | El Abassi, Rida^a | El Moudene, Yassine^a | Sabour, Abderrahim^b

Affiliations: [a] IMI Laboratory, Faculty of Sciences, Ibn Zohr University, Agadir, Morocco | [b] Department of Computer Science High School of Technology, Ibn Zohr University, Agadir, Morocco

Correspondence: [*] Correspondence to: Jaafar Idrais, IMI Laboratory, Faculty of Sciences, Ibn Zohr University, Agadir, Morocco. E-mails: jaafar.idrais@edu.uiz.ac.ma; jaafar.idrais@gmail.com.

Abstract: Online social networks (OSNs) occupy an important part in users’ daily life as they maintain the flow of interaction and information exchange on all local, national, and global scales.This work develops a time series model of interactions on Facebook using the SARIMA (seasonal autoregressive integrated moving average) time series modeling technique based on empiricism with the theoretical model of regular user behavior. A case study of the Moroccan community, which has a high rate of interactions, is carried out to test the conformity of the model with the measurements. The results show that the SARIMA model is better suited to modeling the flow of interactions. The application of the SNR method on the signal energies has allowed to measure the usage damping in the users. The multitude of applied approaches have allowed to extract some main characteristics of this large and complex network.

Keywords: Data mining, OSNs, facebook, social network analysis, time series, social grouping, user behavior

DOI: 10.3233/JIFS-213391

Journal: Journal of Intelligent & Fuzzy Systems, vol. 43, no. 3, pp. 3757-3769, 2022