Emotion analysis of user reactions to online news
| DOI | https://doi.org/10.1108/IDD-04-2022-0027 |
| Published date | 14 November 2022 |
| Date | 14 November 2022 |
| Pages | 179-193 |
| Subject Matter | Library & information science,Library & information services,Lending,Document delivery,Collection building & management,Stock revision,Consortia |
| Author | Marina Bagić Babac |
Emotion analysis of user reactions to
online news
Marina Bagi
c Babac
Faculty of Electrical Engineering and Computing, University of Zagreb, Zagreb, Croatia
Abstract
Purpose –Social media allow for observing different aspects of human behaviour, in particular, those that can be evaluated from explicit user
expressions. Based on a data set of posts with user opinions collected from social media, this paper aims to show an insight into how the readers of
different news portals react to online content. The focus is on users’emotions about the content, so the findings of the analysis provide a furthe r
understanding of how marketers should structure and deliver communication content such that it promotes positive engagement behaviour.
Design/methodology/approach –More than 5.5 million user comments to posted messages from 15 worldwide popular news portals were
collected and analysed, where each post was evaluated based on a set of variables that represent either structural (e.g. embedded in intra- or inter-
message structure) or behavioural (e.g. exhibiting a certain behavioural pattern that appeared in response to a posted message) component of
expressions. The conclusions are based on a set of regression models and exploratory factor analysis.
Findings –The findings show and theorise the influence of social media content on emotional user engagement. This provides a more
comprehensive understanding of the engagement attributed to social media content and, consequently, could be a better predictor of future
behaviour.
Originality/value –This paper provides original data analysis of user comments and emotional reactions that appeared on social media news
websites in 2018.
Keywords Social media, Opinion mining, User comments, Online news, User reactions
Paper type Research paper
1. Introduction
The interactive properties of social media have transformed
users from passive observers to active participants, which
provided a significant amount of social and network value to
both users and organisations through social media, as users
comment, review and share information online (Dolan et al.,
2015). To make a better understanding of the utility of this type
of information, it is necessary to unveil a hidden relationship
between content pages on social media and their users. One of
the most significant latent variables that exist in this
relationship is emotion. Over the decades, researchers were
trying to understand how and why emotions appear and
disappear, and how we can influence various communication
processes. People always influence others’decisions in their
daily interactions in different ways. One way of influenceis via
emotion transfer (e.g. word-of-a-mouth) which overwhelms
social media (Khobzi et al.,2019). Nowadays many people
share almost every moment of their lives online, ranging from
their opinions, sentiments and views to multimedia content
such as personal photographs or home videos (Kümpel et al.,
2015). The massive user-generatedcontent, commonly known
as big data, attracts researchers to investigate what causes such
behaviour, and how to use the acquired knowledge to the best
benefit. And the essence of it is an emotion, which stimulates
the behaviour.
Emotions are a part of our internal activity (Plutchik, 1962)
and execute a crucial role in decision-making and cognitive
relation processes (Shen et al.,2017). Moreover, Kramer et al.
(2014) confirmed that emotionalcontagion is possible via text-
only communication and that emotions flow through social
media. Therefore, the focus of this study is put on certain
aspects of emotion mining as seen from the social media
perspective. This study provides an insight into the user
reactions to online news on Facebook, a social media service
that is increasingly engaged for purposes of news distribution
(Al-Rawi, 2017). The focus of this studyis placed on assessing
users’activities on the Facebook pages of 15 world-class
newspapers, i.e. on user comments to posted messages, their
likes and shares as well as their emotional reactions provided by
emojis (Angry,Haha,Love,Sad and Wow). More specifically,
the relationship between the emotions from the text (e.g.
posted messages and comments to these) and the emotional
reactions of users is investigated in detail. While there are
numerous studies that investigate social media activities and
The current issue and full text archiveof this journal is available on Emerald
Insight at: https://www.emerald.com/insight/2398-6247.htm
Information Discovery and Delivery
51/2 (2023) 179–193
Emerald Publishing Limited [ISSN 2398-6247]
[DOI 10.1108/IDD-04-2022-0027]
© Marina Bagi
c Babac. Published by Emerald Publishing Limited. This
article is published under the Creative Commons Attribution (CC BY 4.0)
licence. Anyone may reproduce, distribute, translate and create derivative
works of this article (for both commercial and non-commercial purposes),
subject to full attribution to the original publication and authors. The full
terms of this licence may be seen at http://creativecommons.org/licences/
by/4.0/legalcode
Received 10 April 2022
Revised 31 July 2022
Accepted 21 September 2022
179
To continue reading
Request your trial