The social force model: a behavioral modeling approach for information propagation during significant events

Abstract

Information diffusion otherwise known as the propagation, spread or dissemination of information occurs when a piece of information flows from a particular individual/community to another in a social network. Studies related to information propagation involve problems regarding the factors that affect the information propagation, how the information is disseminated, the speed of propagation, etc. Researchers have proposed information propagation models to understand the phenomenon and to answer these questions. These models have been effectively used in applications such as behavior analysis, public health care, etc. Although several studies are carried out in this field, the literature demands identifying the most influential factors of propagation in real time in cases of sudden unexpected significant disasters/epidemics/pandemics, since the existing propagation models seem unfit during such circumstances. In this paper, a novel information propagation model which predicts the top propagators of information related to a particular context is proposed. This model utilizes the past few weeks' data during a sudden outbreak of a disaster and identifies the most influential attributes of a user profile to predict the top propagators of the future. The proposed Social Force Model is inspired by a model used in studying the fear propagation pattern in pedestrian dynamics in real-life situation [Cornes FE, Frank GA, Dorso CO. Fear propagation and the evacuation dynamics. Simul Model Pract Theory. 2019;95:112–133.]. We have effectively mapped the various forces which constitute the Social Force Model such as the Desired Force, the Social Force and the Granular Force with respect to the online social network context in order to discover the key spreaders of information during a specific context. Apart from identifying the propagators, the proposed model discovers the key attributes by analyzing the behavior of users based on their past activities in the online social network.

Keywords:

• Information propagation
• information diffusion
• behavior modeling

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This work was supported by University Grants Commission[190520481877].

Notes on contributors

A. Saleema

A. Saleema is a part-time doctoral research scholar at the Indian Institute of Information Technology and Management- Kerala (IIITM-K), India. She is working as Scientist-B in National Informatics Centre, Meity, Government of India. She received her M.Tech degree in Computer Science and Engineering from the University of Kerala in 2015 and B.Tech degree in Computer Science and Engineering from Cochin University of Science and Technology in 2013. Her research interests include Social Media Analysis, Social Behavioral Biometrics, Social Media Behavioral Modelling, Voice recognition, Speaker Identification, etc.

Sabu M. Thampi

Sabu M. Thampi is a Professor at the School of Computer Science and Engineering, Digital University Kerala, India. His current research interests include cognitive computing, Internet of Things(IoT), biometrics, and video surveillance. He is currently serving as Editor for Journal of Network and Computer Applications (JNCA), and Associate Editor for IEEE Access. He is a Senior Member of IEEE and ACM.