Detecting the research structure and topic trends of social media using static and dynamic probabilistic topic models

DOIhttps://doi.org/10.1108/AJIM-02-2022-0091
Published date14 September 2022
Date14 September 2022
Pages215-245
AuthorMuhammad Inaam ul haq,Qianmu Li,Jun Hou,Adnan Iftekhar
Detecting the research structure
and topic trends of social media
using static and dynamic
probabilistic topic models
Muhammad Inaam ul haq and Qianmu Li
Nanjing University of Science and Technology, Nanjing, China
Jun Hou
Nanjing Vocational University of Industry Technology, Nanjing, China, and
Adnan Iftekhar
Wuhan University, Wuhan, China
Abstract
Purpose A huge volume of published research articles is available on social media which evolves because of
the rapid scientific advances and this paper aims to investigate the research structure of social media.
Design/methodology/approach This study employs an integrated topic modeling and text mining-based
approach on 30381 Scopus index titles, abstracts, and keywords published between 2006 and 2021. It combines
analytical analysis of top-cited reviews with topic modeling as means of semantic validation. The output
sequences of the dynamic model are further analyzed using the statistical techniques that facilitate the
extraction of topic clusters, communities, and potential inter-topic research directions.
Findings This paper brings into vision the research structure of social media in terms of topics, temporal
topic evolutions, topic trends, emerging, fading, and consistent topics of this domain. It also traces various
shiftsin topic themes.The hot research topics are the application of the machine or deep learning towards social
media in general, alcohol consumption in different regions and its impact, Social engagement and media
platforms. Moreover, the consistent topics in both models include food management in disaster, health study of
diverse age groups, and emerging topics include drug violence, analysis of social media news for
misinformation, and problems of Internet addiction.
Originality/value This study extends the existing topic modeling-based studies that analyze the social
media literature from a specific disciplinary viewpoint. It focuses on semantic validations of topic-modeling
output and correlations among the topics and also provides a two-stage cluster analysis of the topics.
Keywords Social media, Topic models, Latent dirichlet allocation, DTM, Topic trends, Temporal evolution
Paper type Research paper
1. Introduction
Social mediaare internet-based mediumsthat permit people to engageand self-present both in
real-timeor asynchronously,with each large and slenderaudience who derive worthfrom user-
generatedmaterial and the notionof interplay with others(Aichner et al., 2021).The term social
media(SM) was first utilized in 1994 in a Tokyo online media environment, referred to as
Matisse(Bercovici, 2010). In thoseearly days of the commercial Internet,it was the primary SM
platformthat had developed and launched.Over time, the count of SM platformsand the active
SM users have elevatedsignificantly, making it one of the vital applications of the internet.
Companies have quickly moved their marketing interests to the SM platform. The
presence of both business and users in SM has further changed the way of interaction with
Detecting the
research
structure
215
This work was supported by the major project of philosophy and social science research in colleges and
universities of Jiangsu Province Research on the Construction of Selective Compulsory Courses of
Ideological and Political Science in Higher vocational Colleges(2022SJZDSZ011) and the Research
Project of Nanjing Polytechnic Institute (2020SKYJo3).
The current issue and full text archive of this journal is available on Emerald Insight at:
https://www.emerald.com/insight/2050-3806.htm
Received 25 February 2022
Revised 7 May 2022
22 June 2022
Accepted 3 July 2022
Aslib Journal of Information
Management
Vol. 75 No. 2, 2023
pp. 215-245
© Emerald Publishing Limited
2050-3806
DOI 10.1108/AJIM-02-2022-0091
customers, who are no longer restricted to their passive role in business relationships
(Malthouse et al., 2013) but also provide feedback to customers, ask questions, and expect
answers to their specific problems that are reasonably quick and customized. In addition,
customers post text, images, and videos. The manager concludes that the rebranding to SM
ultimately involves the restructuring of customer relationships where the customer is not an
audience, but an ally or an enemy (Som and Blanckaer, 2015).
In research, SM is often used as an overarching term describing a variety of online
platforms, including blogs, corporate networks, collaborative projects, corporate social
networks (SNs), forums, microblogging, photo sharing, product reviews, social bookmarking,
and social games, SN, video sharing, and virtual worlds (Aichner and Jacob, 2015). Given the
variety of SM platforms, SM applications are quite diverse and are not limited to sharing
holiday snapshots or advertising and promotions. During the past two decades, various
articles have provided reviews or qualitative studies on social media and its related topics
(Aichner et al., 2021;Nicola et al., 2020;Moorhead et al., 2013;Zhang et al., 2020;Mathew et al.,
2018), particularly the applications of social media in the health sector, tourism, the impact of
social media on children, adolescents, privacy and human behavior (Xiong et al., 2020;
OKeeffe et al., 2011;Acquisti et al., 2018;Leung et al., 2013).
In some studies, researchers provided a quantitative assessment of the social media
literature (Thaha et al., 2021;Wang et al., 2020;Zyoud et al., 2018;Lee et al., 2021;Taneja et al.,
2021). For example, Thaha et al. presented the research trends and mapping of the application
of social media in small and medium enterprises. Wang et al., describe the research progress
on social media big data. Zyoud et al. and Lee et al. trace the social media trends in psychology
and sustainability respectively. Although the aim of these studies discovers the topics from
social media literature, these are limited to a specific disciplinary viewpoint. Therefore, these
studies are inadequate to show a holistic picture of the social media research paradigm and
also utilized small samples, thus, are not able to reflect the full landscape of the social media
research area. Therefore, it is essential to identify the structure of the social media research
domain. To fill the gap, this study analyses scientific literature on social media published
between 2006 and 2021 and maps the scientific discourse in terms of topics, their temporal
trends, temporal topic evolution, topic clusters, and topic communities. Specifically, this
study focuses on the following research questions:
RQ1. What are the major research topics in social media literature?
RQ2. How changes in topic themes are reflected in the context of static and dynamic
models (fading, emerging, and consistent topics)?
RQ3. How topic evolves in temporal perspective
RQ4. What are the important clusters, communities (i.e. correlations), and inter-topic
research directions in the social media research paradigm?
RQ5. How do topics relate to the top-cited literature as means of semantic validations?
We divide this study into seven sections. The first sectioncovers the introduction of the
study. The second section discusses the background and the third section discusses the
materials and methods in detail. In the fourth section, we cover the results, in the fifth section,
we have the discussion, and in the sixth section, we have result implications, and in the
seventh section, this study is concluded.
2. Background
In this section, we describe the (1) top-cited reviews on social media and (2) related work on
topic modeling methodologies.
AJIM
75,2
216

To continue reading

Request your trial

VLEX uses login cookies to provide you with a better browsing experience. If you click on 'Accept' or continue browsing this site we consider that you accept our cookie policy. ACCEPT