Corporate disclosure via social media: a data science approach
| Published date | 08 January 2020 |
| Date | 08 January 2020 |
| DOI | https://doi.org/10.1108/OIR-03-2019-0084 |
| Pages | 278-298 |
| Author | Marian H. Amin,Ehab K.A. Mohamed,Ahmed Elragal |
| Subject Matter | Library & information science,Information behaviour & retrieval,Collection building & management,Bibliometrics,Databases,Information & knowledge management,Information & communications technology,Internet,Records management & preservation,Document management |
Corporate disclosure via social
media: a data science approach
Marian H. Amin and Ehab K.A. Mohamed
Faculty of Management Technology,
German University in Cairo, Cairo, Egypt, and
Ahmed Elragal
Department of Computer Science,
Luleå University of Technology, Lulea, Sweden
Abstract
Purpose –The purpose of this paper is to investigate corporate financial disclosure via Twitter among the
top listed 350 companies in the UK as well as identify the determinants of the extent of social media usage to
disclose financial information.
Design/methodology/approach –This study applies an unsupervised machine learning technique,
namely, Latent Dirichlet Allocation topic modeling to identify financial disclosure tweets. Panel, Logistic and
Generalized Linear Model Regressions are also run to identify the determinants of financial disclosure on
Twitter focusing mainly on board characteristics.
Findings –Topic modeling results reveal that companies mainly tweet about 12 topics, including financial
disclosure, which has a probability of occurrence of about 7 percent. Several board characteristics are found
to be associated with the extent of Twitter usage as a financial disclosure platform, among which are board
independence, gender diversity and board tenure.
Originality/value –The extensive literatur e examines disclosure v ia traditional media and it s
determinants, yet this p aper extends the literature by invest igating the relatively new disclosur e channel of
social media. This st udy is among the first to utili ze machine learning, inst ead of manual coding techni ques,
to automatically unve il the tweets’topics an d reveal financial disc losure tweets. It is als o among the
first to investigate the rel ationships between seve ral board characteristic s and financial disclosure on
Twitter; providing a dis tinction between the rol es of executive vs non-exec utive directors relat ing to
disclosure decisions .
Keywords Social media, Board structure, Corporate disclosure, LDA, Topic modeling
Paper type Research paper
1. Introduction
Over the past couple of decades, research on corporate disclosure has emerged to become
one of the most popular and important areas in the accounting literature. Such momentum
has been driven by the growing awareness of the value of disclosure and its tremendous
effects on different stakeholders and the capital markets at large. Technological
advancements have even fueled researchers’interest in this field (Miller and Skinner,
2015). Corporate disclosure has been traditionally in the form of paper-based printed media,
yet after the invention of the internet, companies had started adopting a new paradigm of
online information disclosure (Lodhia et al., 2004). However, within the internet platform
itself, the media for disclosure have also evolved from corporate websites to social media, as
a result of the continuous technological developments (Zhou et al., 2015). Despite of the
growing adoption of social media for the purpose of information disclosure (Blankespoor
et al., 2014; Elliott et al., 2018), yet such phenomenon still represents a field of unexplored
research due to the very limited studies that exist on the subject matter (Debreceny, 2015;
Zhou et al., 2015; Miller and Skinner, 2015; Elliott et al., 2018).
The decision to disclose information on social media, like any corporate decision, is
usually controlled by the company’s board of directors who is seen as “the apex of the firm’s
decision control system”(Fama and Jensen, 1983, p. 311). Therefore, in order to study the
Online Information Review
Vol. 44 No. 1, 2020
pp. 278-298
© Emerald PublishingLimited
1468-4527
DOI 10.1108/OIR-03-2019-0084
Received 10 March 2019
Revised 5 September 2019
Accepted 5 December 2019
The current issue and full text archive of this journal is available on Emerald Insight at:
https://www.emerald.com/insight/1468-4527.htm
278
OIR
44,1
determinants of financial disclosure on social media, it is crucial to account for board
characteristics, as they reflect the motives, values, perspectives and choices of those who
formulate strategies and control decisions within companies, including disclosure related
decisions (Basuony et al., 2018; Donnelly and Mulcahy, 2008).
The significance of this study stems from the fact that the disclosure phenomenon on
social media is very fast paced influencing greatly the way stakeholders obtain information
about a company, and hence formulating their decisions accordingly. In fact, the
tremendous importance and influence of social media disclosure can be observed from
various incidents, one of which is the incident of Netflix’s CEO who posted company
metrics on his personal Facebook account affecting Netflix’s stock price greatly, leading the
SEC to initiate an investigation against the company since the post was not released in
official filings or other traditional disclosure media. The investigations ended by clearing
the CEO of any wrongdoings, and announcing updated disclosure guidelines that include
social media, acknowledging them as an official platform via which companies can disclose
material information (Basuony et al., 2018). Hence, it is becoming increasingly important for
the various stakeholders as well as researchers to understand how companies utilize social
media for the purpose of information disclosure and what factors influence such decision to
disclose on social media. Accordingly, this paper aims to examine financial disclosures on
Twitter among the top 350 companies listed on the London Stock Exchange (LSE) using a
machine learning approach, as well as, identify the determinants of such financial
disclosures focusing on the board of directors’characteristics making a distinction between
executive directors’and non-executive directors’characteristics.
The paper contributes to the literature in several ways. First, from a methodological
perspective, it utilizes an automated machine learning approach to automatically analyze
the content of the tweets and unveil financial disclosures, which is considered a fairly new
approach to mainstream accounting research which usually analyzes online disclosures
using manual techniques. Second, this paper contributes to the literature examining the
determinants of financial disclosure, as to the best of our knowledge, it is among the first
few studies that investigate the relationship between board composition and the extent of
Twitter usage for the purpose of financial information disclosure providing new insights
on the differences between executive and non-executive members’characteristics and
their associations with social media disclosure. The investigation of such determinants
helps to extend the voluntary disclosure theories established for traditional platforms to
the new platform of social media. Moreover, the paper also extends the disclosure media
literature by examining Twitter which represents nowadays one of leading edge
communication media.
The remainder of the paper is organized as follows. The next section provides an
overview on the relevant literature and hypotheses development, followed by the research
methodology in Section 3. Section 4 presents the results and discusses them in light of the
literature and then Section 5 summarizes and concludes the paper.
2. Literature review
2.1 Emergence of social media
Recent years have witnessed a rapid growth of a relatively new class of information
technology, known as social media, which is mainly used for interpersonal communications
using internet as its platform. The term “social media”is given numerous, yet similar
definitions in the literature, for example, Kaplan and Haenlein (2010) define social media as
internet-based applications that are built on the foundations of web 2.0 that enable the
creation and exchange of user generated content. Lee et al. (2015, p. 372) also refer to social
media as “web-based technologies that enable people to create, share and exchange
information in virtual communities and networks.”
279
Corporate
disclosure via
social media
To continue reading
Request your trial