New time-based model to identify the influential users in online social networks
| DOI | https://doi.org/10.1108/DTA-08-2017-0056 |
| Pages | 278-290 |
| Date | 03 April 2018 |
| Published date | 03 April 2018 |
| Author | Amin Mahmoudi,Mohd Ridzwan Yaakub,Azuraliza Abu Bakar |
| Subject Matter | Library & information science,Librarianship/library management,Library technology,Information behaviour & retrieval,Metadata,Information & knowledge management,Information & communications technology,Internet |
New time-based model to identify
the influential users in online
social networks
Amin Mahmoudi, Mohd Ridzwan Yaakub and Azuraliza Abu Bakar
National University of Malaysia, Bangi, Malaysia
Abstract
Purpose –Users are the key players in an online social network (OSN), so the behavior of the OSN is strongly
related to their behavior. User weight refers to the influence of the users on the OSN. The purpose of this
paper is to propose a method to identify the user weight based on a new metric for defining the time intervals.
Design/methodology/approach –The behavior of an OSN changes over time, thus the user weightin the
OSN is differentin each time frame. Therefore,a good metricfor estimating the user weight in an OSN depends
on the accuracyof the metric used todefine the time interval.New metric for defining thetime intervals is based
on the standarddeviation and identifiesthat the user weight is based on a simple exponentialsmoothing model.
Findings –The results show that the proposed method covers the maximum behavioral changes of the OSN
and is able to identify the influential users in the OSN more accurately than existing methods.
Research limitations/implications –In event detection, when a terrorist attack occurs as an event,
knowing the influential users help us to know the leader of the attack. Knowing the influential user in each
time interval based on this study can help us to detect communities which formed around these people.
Finally, in marketing, this issue helps us to have a targeted advertising.
Practical implications –User effect is a significant issue in many OSN domain problems, such as
community detection, event detection and recommender systems.
Originality/value –Previousstudies do not give priorityto the recent time intervals inidentifying the relative
importanceof users. Thus, defininga metricto compute a time interval that coversthe maximum changes in the
networkis a major shortcomingof earlier studies. Someexperiments were conductedon six different datasets to
test the performanceof the proposed model in terms of the computed time intervals anduser weights.
Keywords Influential users, OSN, Simple exponential smoothing, Standard deviation, Time interval,
User weight
Paper type Research paper
Introduction
In an online social network (OSN), each user has a specific weight, which refers to the
influence of the user on the OSN, and the weight of each user is different. A user’s weight is a
key indicator of the user’s influence on the OSN; where the weight of the user is greater, the
more influence that user has on the OSN as compared to other users. An accurate
understanding of the role of users is fundamental to the solving of many OSN domain
problems, such as community detection, event detection and marketing. In event detection,
when a terrorist attack occurs as an event, knowing the influential users helps us to discover
the leader of the attack. Through applying the method proposed in this study, we can also
identify the influential users in each time interval, which can help us to detect the
communities that are formed around these individuals. On the other hand, in marketing, this
work helps in targeting advertising at specific individuals.
In recent years, many researchers have tried to identify the influential users in OSNs
(Hangal et al., 2010; Trusov et al., 2010; Erlandsson et al., 2016; Heidemann et al., 2010;
Nan et al., 2016; Jianqiang et al., 2017) and to distinguish the influential users (leaders) from
the followers in OSNs (Shafiq et al., 2013) or estimate the user weight (Zafarani et al., 2014).
In this study, we consider a user as influential, if he/she could attract many users in each
Data Technologies and
Applications
Vol. 52 No. 2, 2018
pp. 278-290
© Emerald PublishingLimited
2514-9288
DOI 10.1108/DTA-08-2017-0056
Received 5 August 2017
Revised 4 October 2017
Accepted 18 October 2017
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/2514-9288.htm
This work is supported by Fundamental Research Grant Scheme (FRGS/1/2017/ICT02/UKM/02/4) of
UKM University (National University of Malaysia).
278
DTA
52,2
To continue reading
Request your trial