Explaining and predicting click-baitiness and click-bait virality
| DOI | https://doi.org/10.1108/IMDS-01-2022-0003 |
| Published date | 12 August 2022 |
| Date | 12 August 2022 |
| Pages | 2485-2507 |
| Subject Matter | Information & knowledge management,Information systems,Data management systems,Knowledge management,Knowledge sharing,Management science & operations,Supply chain management,Supply chain information systems,Logistics,Quality management/systems |
| Author | Swagato Chatterjee,Meghraj Panmand |
Explaining and predicting click-
baitiness and click-bait virality
Swagato Chatterjee and Meghraj Panmand
Vinod Gupta School of Management, IIT Kharagpur, Kharagpur, India
Abstract
Purpose –In the age of social media, when publishers are vying for consumer attention, click-baits have
become very common. Not only viral websites but also mainstream publishers, such as news channels, use
click-baits for generating traffic. Therefore, click-bait detection and prediction of click-bait virality have
become important challenges for social media platforms to keep the platform click-bait free and give a better
user experience. The purpose of this studyis to try exploring how the contents of the socialmedia posts and the
article can be used to explain and predict social media posts and the virality of a click-bait.
Design/methodology/approach –This study has used 17,745 tweets from Twitter with 4,370 click-baits
from top 27 publishers and applied econometric along with machine learning methods to explain and predict
click-baitiness and click-bait virality.
Findings –This study finds that language formality, readability, sentiment scores and proper noun usage of
social media posts and various parts of the target article plays differential and important roles in click-baitiness
and click-bait virality.
Research limitations/implications–The paper contributes toward the literature of dark behavior in social
media at large and click-bait prediction and explanation in particular. It focuses on the differential roles of the
social media post, the article shared and the source in explaining click-baitiness and click-bait virality via
psycho-linguistic framework. The paper also provides explanability to the econometric and machine learning
predictive models, thus performing methodological contribution too.
Practical implications –The paper helps social media managers create a mechanism to detect click-baits
and also predict which ones of them can become viral so that corrective measures can be taken.
Originality/value –To the best of the authors’knowledge, this is one of the first papers which focus on both
explaining and predicting click-baitiness and click-bait virality.
Keywords Click-bait, Virality, Formality, Sentiment, Text-mining
Paper type Research paper
1. Introduction
In the age of rampant use of the Internet and instant gratification, the consumption of online
content has increased exponentially. Social media users, for instance, are possibly the biggest
content consumers, consuming all types of content. The fear of missing out (FOMO), online
fatigue and social comparisons have reduced the barriers of consuming and sharing
unverified online content, leading to an exponential increase in fake news, hoax, rumor and
click-baits content (Wessel et al., 2016;Kim and Dennis, 2019;Talwar et al., 2019). This has
happened due to the active participation of some users in such dark social media behavior.
Research on such dark behavior is still in the nascent stage (Talwar et al., 2019;Quandt
et al., 2022).
In this particular study, we focus on click-baits. Click-baits may be defined as web content,
produced and marketed to maximize advertisement revenue by attracting lots of traffic to a
website via attracting the reader’s attention using stories/headlines/posts that entice them to
click (Munger et al., 2020). Importantly, this is often done at the cost of quality, authenticity
and exactitude (L
opez-S
anchez et al., 2018). One must note that click-baits are different from
fake news, rumors and hoax. While the latter provide false or unverified information, click-
bait gives true information but of lower quality. Therefore, while fake news, rumor and hoax
also strive to make the user believe in the content, click-bait will not try to do that. The
attraction of traffic by the click-baits is achieved by using provocative and sensational text in
social media content or the title text. Often, the language used in the title is just enough to
Click-baitiness
and click-bait
virality
2485
The current issue and full text archive of this journal is available on Emerald Insight at:
https://www.emerald.com/insight/0263-5577.htm
Received 3 January 2022
Revised 11 May 2022
7 June 2022
Accepted 14 July 2022
Industrial Management & Data
Systems
Vol. 122 No. 11, 2022
pp. 2485-2507
© Emerald Publishing Limited
0263-5577
DOI 10.1108/IMDS-01-2022-0003
ensure curiosity, but not enough to get the full information about the topic, creating thereby a
curiosity gap, which, in turn, leads the reader to click the link for further info (Potthast et al.,
2016). However, the article that the click-bait refers to usually fails to deliver on the promise of
exciting/surprising information. As the curiosity and expectations of the users are not
fulfilled by the website content, often the websites pointed by click-bait links are not rated
well, as they have higher bounce rates (L
opez-S
anchez et al., 2018). Some examples of click-
bait headlines include for instance “20 celebrities who have beaten cancer”;“Cabin Crew
Takes Secret Pictures, You Won’t Believe the Results”;or“Life Insurance companies hate this
new trick,”etc. We have chosen click-baits as the domain of study as social media platforms
have fairly tackled the other three social media evils such as rumor, hoax and fake news.
However, social media platforms are still struggling with how to tackle click-baits. Zhang and
Clough (2020) report almost 70% of the social media content in WeChat, the most popular
social networking site in China, are click-baits. Such huge number makes the domain very
relevant for the researchers.
Detecting the click-baits on a social media and stopping them from being viral is very
important for the social media platforms and their users. While click-bait cannot be
considered illegal or dangerous, they are usually frowned upon, as they tend to waste the
reader’s time and generate discontent (L
opez-S
anchez et al., 2018). In fact, click-baits are
disliked by both public institutions and private organizations due to their deceptive nature
(Mihaylov et al., 2018). For instance, the European Union has declared that they would work
against click-bait articles published in online media with “catchy, provocative, and
sensationalist front-page”headlines and without quality content (Orosa et al., 2017). On the
other hand, social media platforms like Facebook may face trust issues both for their users
and public institutions due to such click-baits. Thus, these platforms (notably Facebook) have
begun taking initiatives to reduce the number of click-baits by correctly identifying them and
punishing the perpetrators (Babu et al., 2017). The viral nature coupled with the low-quality
content of click-baits has led these platforms to create algorithms, which can automatically
detect and filter out click-baits (L
opez-S
anchez et al., 2018). Extant literature has talked about
a number of natural language processing and machine learning-based methods to detect
click-baits automatically (Chen et al., 2015;Biyani et al., 2016;Chakraborty et al., 2016;
Potthast et al., 2016;Khater et al., 2018;Zhang and Clough, 2020). Yet, every new type of click-
baits is evolving, suggesting some drawbacks of the existing models. One problem that most
of these studies face is that they lack any conceptual model or framework while exploring
click-baits as the studies primarily focused on click-bait detection instead of focusing on the
impact of click-baits on readers (Zhang et al., 2020). Studies on the psychological process
involved in click-bait response of the users are very limited. While some researchers have
focused on the emotional response of the click-bait headline (Pengnate, 2019), others have
focused on how the impact of click-baitiness on source derogation and sharing behavior of the
users (Mukherjee et al., 2022). However, none of these studies focused on the drivers of click-
baitiness and the psychological process under it. A better understanding of the psychological
process will not only help the platform managers detect click-bait better today but also help
them to mitigate future threats. Social media houses and marketers will keep on trying new
techniques and applying new technologies to catch users’attention. Combating such
strategies will be easier for the platform managers if they can understand the psychological
process of click-baits better. However, the psychological process of a social media post being
considered click-bait has not been addressed, although such an exploration is important to
better understand the possible drivers of click-baitiness. This creates a gap in the literature.
We fill this gap by exploring click-bait drivers which are governed by the psychological
process as proposed in this study. Moreover, the click-baitiness of a link does not only depend
on the potential of the social media post to attract readers but also depend on the
attractiveness of the article title, which is often displayed when a link is shared, and the article
IMDS
122,11
2486
To continue reading
Request your trial