A comparative study of the effectiveness of sentiment tools and human coding in sarcasm detection

2018 ◽  
Vol 20 (3) ◽  
pp. 358-374
Author(s):  
Phoey Lee Teh ◽  
Pei Boon Ooi ◽  
Nee Nee Chan ◽  
Yee Kang Chuah

Purpose Sarcasm is often used in everyday speech and writing and is prevalent in online contexts. The purpose of this paper is to investigate the analogy between sarcasm comments from sentiment tools and the human coder. Design/methodology/approach Using the Verbal Irony Procedure, eight human coders were engaged to analyse comments collected from an online commercial page, and a dissimilarity analysis was conducted with sentiment tools. Three constants were tested, namely, polarity from sentiment tools, polarity rating by human coders; and sarcasm-level ratings by human coders. Findings Results found an inconsistent ratio between these three constants. Sentiment tools used did not have the capability or reliability to detect the subtle, contextualized meanings of sarcasm statements that human coders could detect. Further research is required to refine the sentiment tools to enhance their sensitivity and capability. Practical implications With these findings, it is recommended that further research and commercialization efforts be directed at improving current sentiment tools – for example, to incorporate sophisticated human sarcasm texts in their analytical systems. Sarcasm exists frequently in media, politics and human forms of communications in society. Therefore, more highly sophisticated sentiment tools with the abilities to detect human sarcasm would be vital in research and industry. Social implications The findings suggest that presently, of the sentiment tools investigated, most are still unable to pick up subtle contexts within the text which can reverse or change the message that the writer intends to send to his/her receiver. Hence, the use of the relevant hashtags (e.g. #sarcasm; #irony) are of fundamental importance in detection tools. This would aid the evaluation of product reviews online for commercial usage. Originality/value The value of this study lies in its original, empirical findings on the inconsistencies between sentiment tools and human coders in sarcasm detection. The current study proves these inconsistencies are detected between human and sentiment tools in social media texts and points to the inadequacies of current sentiment tools. With these findings, it is recommended that further research and commercialization efforts be directed at improving current sentiment tools – to incorporate sophisticated human sarcasm texts in their analytical systems. The system can then be used as a reference for psychologists, media analysts, researchers and speech writers to detect cues in the inconsistencies in behaviour and language.

2014 ◽  
Vol 22 (5) ◽  
pp. 39-41 ◽  
Author(s):  
John Chelliah ◽  
James Field

Purpose – The purpose of this paper is to highlight the risks employers face when employees use social media. Design/methodology/approach – This paper considers the types of risks and suggests how they could be mitigated. Findings – It is revealed that employers need two policies to manage risks associated with the use of social media: one covering business use of social media and another covering employees’ personal use of social media. Practical implications – This paper guides managers in assessing the exposure of their organizations and clients to the risks identified. Social implications – This paper draws attention to the risks associated with the widespread use of social media for both business and employees’ personal purposes. Originality/value – The issue of organizational awareness and preparedness to tackle the challenges posed by social media has been raised.


2018 ◽  
Vol 22 (1) ◽  
pp. 35-48 ◽  
Author(s):  
Andrea Geissinger ◽  
Christofer Laurell

PurposeThe purpose of this paper is to explore the effects of fashion weeks on brand constellations of participating fashion companies in social media.Design/methodology/approachThe study analyses how brand constellations take form for seven Swedish fashion companies before, during and after Fashion Week Stockholm. In total, 3,449 user-generated contents referring to the sampled brands were collected and analysed.FindingsOn average, brand constellations of participating companies are increasingly incorporating other participating brands as a result of the fashion week. Based on the presented results, four brand constellation outcomes for participating fashion companies are identified: brand constellation amplification, concentration, division and dilution.Research limitations/implicationsAs this paper is focussed on the Swedish market, additional results from fashion weeks taking place in other cities would be beneficial to verify the four brand constellation outcomes.Practical implicationsThe results question the resilience of professionally curated brand constellations due to the emergence of user-driven constellations that also shape the position of fashion brands. Therefore, this development can potentially have a considerable impact on often carefully orchestrated brand positioning strategies executed by fashion companies.Social implicationsDigitally fuelled interdependences of brand constellations by professionals and consumers attest to the dilution of borders between consumers and producers.Originality/valueThis paper contributes to the field of fashion marketing and management by identifying four different brand constellation outcomes in social media for participating fashion companies as a result of fashion weeks and how to managerially handle these respective outcomes.


2016 ◽  
Vol 14 (2) ◽  
pp. 200-212
Author(s):  
Matthew Warren ◽  
Shona Leitch

Purpose The aim of the paper is to assess the hacktivist group called the Syrian Electronic Army and determine what their motivations in terms of ethical and poetical motivations. Design/methodology/approach This paper looks at chronological examples of Syrian Electronic Army activities and assess them using a developed hacktivist criteria to try and gain a greater understanding of the motivations of the Syrian Electronic Army. The paper uses a netnography research approach. Findings This paper determines that the Syrian Electronic Army is motivated to protect the Syrian Government. This protection is highlighted by the new media and social media organisations that the Syrian Electronic Army attacks online. Research limitations/implications This paper focuses only on one group the Syrian Electronic Army. Practical implications A greater understanding of the Syrian Electronic Army. Social implications A greater understanding of the development of hacktivism. Originality/value A unique study into the motivation of the Syrian Electronic Army.


2018 ◽  
Vol 42 (5) ◽  
pp. 718-731 ◽  
Author(s):  
Jason Gainous ◽  
Andrew Segal ◽  
Kevin Wagner

Purpose Early information technology scholarship centered on the internet’s potential to be a democratizing force was often framed using an equalization/normalization lens arguing that either the internet was going to be an equalizing force bringing power to the masses, or it was going to be normalized into the existing power structure. The purpose of this paper is to argue that considered over time the equalization/normalization lens still sheds light on our understanding of how social media (SM) strategy can shape electoral success asking if SM are an equalizing force balancing the resource gap between candidates or are being normalized into the modern campaign. Design/methodology/approach SM metrics and electoral data were collected for US congressional candidates in 2012 and 2016. A series of additive and interactive models are employed to test whether the effects of SM reach on electoral success are conditional on levels of campaign spending. Findings The results suggest that those candidates who spend more actually get more utility for their SM campaign than those who spend less in 2012. However, by 2016, spending inversely correlates with SM campaign utility. Research limitations/implications The findings indicate that SM appeared to be normalizing into the modern congressional campaign in 2012. However, with higher rates of penetration and greater levels of usage in 2016, the SM campaign utility was not a result of higher spending. SM may be a greater equalizing force now. Practical implications Campaigns that initially integrate digital and traditional strategies increase the effectiveness of the SM campaign because the non-digital strategy both complements and draws attention to the SM campaign. However, by 2016 the SM campaign was not driven by its relation to traditional campaign spending. Originality/value This is the first large N study to examine the interactive effects of SM reach and campaign spending on electoral success.


2013 ◽  
Vol 17 (5) ◽  
pp. 741-754 ◽  
Author(s):  
Moria Levy

Purpose – This paper is aimed at both researchers and organizations. For researchers, it seeks to provide a means for better analyzing the phenomenon of social media implementation in organizations as a knowledge management (KM) enabler. For organizations, it seeks to suggest a step-by-step architecture for practically implementing social media and benefiting from it in terms of KM. Design/methodology/approach – The research is an empirical study. A hypothesis was set; empirical evidence was collected (from 34 organizations). The data were analyzed both quantitatively and qualitatively, thereby forming the basis for the proposed architecture. Findings – Implementing social media in organizations is more than a yes/no question; findings show various levels of implementation in organizations: some implementing at all levels, while others implement only tools, functional components, or even only visibility. Research limitations/implications – Two main themes should be further tested: whether the suggested architecture actually yields faster/eased KM implementation compared to other techniques; and whether it can serve needs beyond the original scope (KM, Israel) as tested in this study (i.e. also for other regions and other needs – service, marketing and sales, etc.). Practical implications – Organizations can use the suggested four levels architecture as a guideline for implementing social media as part of their KM efforts. Originality/value – This paper is original and innovative. Previous studies describe the implementation of social media in terms of yes/no; this research explores the issue as a graded one, where organizations can and do implement social media step-by-step. The paper's value is twofold: it can serve as a foundational study for future researches, which can base their analysis on the suggested architecture of four levels of implementation. It also serves as applied research that will help organizations searching for social media implementation KM enablers.


2016 ◽  
Vol 88 (6) ◽  
pp. 866-872 ◽  
Author(s):  
Yair Wiseman

Purpose The purpose of this paper is to study extensive enlargement and safety of flight data recorder memory. Design/methodology/approach The study involves the moving the memory of flight data recorders from an internal embedded device to a cloud. Findings The implementation has made the embedded memory device of flight data recorder effectively unlimited, and, hence, much more information can be stored. Research limitations/implications The possibility of a flight data recorder to be damaged or lost in a crash is not so high, but the implementation can be very helpful in cases such as aerial disappearances. Practical implications The implication is larger and protected memory for flight data recorders. Social implications Finding reasons for crashes is faster, and immediate actions can be taken to find remedy to the failures. Originality/value The use of internet and cellphones in airplanes is nothing special at present. It is suggested to take this technology for flight data recorders as well.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Paula Castro Pires de Souza Chimenti ◽  
Marco Aurelio de Souza Rodrigues ◽  
Marcelo Guedes Carneiro ◽  
Roberta Dias Campos

Purpose Through a literature review, a gap has been identified regarding the role of competition as a driver of social network (SN) usage. This study aims to design to address this gap, seeking motivators for SN usage based on how SN consumption may be related to users’ experience of competition. Therefore, the purpose of this study is to investigate the influence of competition in social media usage. Design/methodology/approach The authors used an exploratory qualitative approach, conducting a set of focus groups with young social media users. Data was analyzed with software. Findings Two new drivers for SN use are proposed, namely, competition and collective narrative. Research limitations/implications This is an exploratory study, and it does not seek to generalize results or quantify causal relationships among variables. Practical implications This paper offers SN managers a deeper understanding of key growth drivers for these media. Social implications This research can help society understand and debate the impacts of SNs on users’ lives, providing insights into drivers of excessive usage. Originality/value This paper proposes the following two SN usage drivers yet to be described in the literature: competition and collective narrative.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
V. V. Singh ◽  
Abubakkar Idris Mohhammad ◽  
Kabiru Hamisu Ibrahim ◽  
Ibrahim Yusuf

PurposeThis paper analyzed a complex system consisting n-identical units under a k-out-of-n: G; configuration via a new method which has not been studied by previous researchers. The computed results are more supportable for repairable system performability analysis.Design/methodology/approachIn this paper, the authors have analyzed a complex system consisting n-identical units under a k-out-of-n: G; configuration via a new method which has not been studied by previous researchers. The supplementary variable technique has employed for analyzing the performance of the system.FindingsReliability measures have been computed for different types of configuration. It generalized the results for purely series and purely parallel configurations.Research limitations/implicationsThis research may be beneficial for industrial system performances whereas a k-out-of-n-type configuration exists.Practical implicationsNot sure as it is a theoretical assessment.Social implicationsThis research may not have social implications.Originality/valueThis work is the sole work of authors that have not been communicated to any other journal before.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Peter Buell Hirsch

Purpose This paper aims to examine the challenges to sustaining corporate culture in a world of hybrid working. Design/methodology/approach This paper is a review of current literature on the impact of remote and hybrid working on white-collar employees. Findings There is little consensus on whether remote/hybrid working will harm or strengthen corporate culture. Research limitations/implications The viewpoint is a subjective assessment of a limited number of articles on the subject Practical implications It is not entirely clear how those responsible for corporate culture can act on the findings. Social implications In a world in which corporations are experiencing a shortage of talent, how they handle corporate culture will be increasingly important. Originality/value While much has been written on the impact of remote working, this viewpoint takes the original view that strong corporate cultures rely more on the attitudes and actions of individual employees that company programs or initiatives.


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Khudejah Ali ◽  
Cong Li ◽  
Khawaja Zain-ul-abdin ◽  
Muhammad Adeel Zaffar

PurposeAs the epidemic of online fake news is causing major concerns in contexts such as politics and public health, the current study aimed to elucidate the effect of certain “heuristic cues,” or key contextual features, which may increase belief in the credibility and the subsequent sharing of online fake news.Design/methodology/approachThis study employed a 2 (news veracity: real vs fake) × 2 (social endorsements: low Facebook “likes” vs high Facebook “likes”) between-subjects experimental design (N = 239).FindingsThe analysis revealed that a high number of Facebook “likes” accompanying fake news increased the perceived credibility of the material compared to a low number of “likes.” In addition, the mediation results indicated that increased perceptions of news credibility may create a situation in which readers feel that it is necessary to cognitively elaborate on the information present in the news, and this active processing finally leads to sharing.Practical implicationsThe results from this study help explicate what drives increased belief and sharing of fake news and can aid in refining interventions aimed at combating fake news for both communities and organizations.Originality/valueThe current study expands upon existing literature, linking the use of social endorsements to perceived credibility of fake news and information, and sheds light on the causal mechanisms through which people make the decision to share news articles on social media.


Sign in / Sign up

Export Citation Format

Share Document