Search results

This paper proposes an approach to identify categorical influencers (i.e. influencers is the person who is active in the targeted categories) in social media channels. Categorical influencers are important for media marketing but to automatically detect them remains a challenge.

We deployed the emerging deep learning approaches. Precisely, we used word embedding to encode semantic information of words occurring in the common microtext of social media and used variational autoencoder (VAE) to approximate the topic modeling process, through which the active categories of influencers are automatically detected. We developed a system known as Categorical Influencer Detection (CID) to realize those ideas.

The approach of using VAE to simulate the Latent Dirichlet Allocation (LDA) process can effectively handle the task of topic modeling on the vast dataset of microtext on social media channels.

This work has two major contributions. The first one is the detection of topics on microtexts using deep learning approach. The second is the identification of categorical influencers in social media.

This work can help brands to do digital marketing on social media effectively by approaching appropriate influencers. A real case study is given to illustrate it.

In this paper, we discuss an approach to automatically identify the active categories of influencers by performing topic detection from the microtext related to the influencers in social media channels. To do so, we use deep learning to approximate the topic modeling process of the conventional approaches (such as LDA).

The purpose of this paper is to provide the theoretical insights with regard to the green purchasing intention–behavior gap and the role played by social media influences in abating this gap. This paper takes into consideration a wider aspect with regard to the antecedents of behavioral intention through personal and social identities in place of the antecedents presented in the theory of planned behavior and social-identity theory. Furthermore, as the theories lack an explanation of how to reduce the intention–behavior gap, this paper also argues the source credibility model (SCM) in explaining the impact that social media influences can have on the behavioral gap.

Hypothetical deductive method is proposed for this concept paper under the positivism research paradigm.

Not applicable as this is a concept paper. However, the paper discusses the theoretical and managerial implications.

This is a concept paper. Yes this paper discusses the theoretical, managerial, and social/ecological implications.

This paper highlights the relevance of consumers' personal and social identities when consumers make purchasing decisions regarding green products. How managers can make marketing strategies, based on credibility model, involving social media influences as product endorsers and ambassadors, as well as the policy makers to design products, earmark consumer behavior and to conduct marketing campaigns in time to come.

As to how policies can be designed and adopted for bio-based economies where sustainability and circularity are given priority and to increase the attention of businesses moving toward sustainable practices.

Original thought developed based on research, theoretical and market gaps.

This study aims to provide a systematic review of the existing literature on the applications of deep learning (DL) in hospitality, tourism and travel as well as an agenda for future research.

Covering a five-year time span (2017–2021), this study systematically reviews journal articles archived in four academic databases: Emerald Insight, Springer, Wiley Online Library and ScienceDirect. All 159 articles reviewed were characterised using six attributes: publisher, year of publication, country studied, type of value created, application area and future suggestions (and/or limitations).

Five application areas and six challenge areas are identified, which characterise the application of DL in hospitality, tourism and travel. In addition, it is observed that DL is mainly used to develop novel models that are creating business value by forecasting (or projecting) some parameter(s) and promoting better offerings to tourists.

Although a few prior papers have provided a literature review of artificial intelligence in tourism and hospitality, none have drilled-down to the specific area of DL applications within the context of hospitality, tourism and travel.

To the best of the authors’ knowledge, this paper represents the first theoretical review of academic research on DL applications in hospitality, tourism and travel. An integrated framework is proposed to expose future research trajectories wherein scholars can contribute significant value. The exploration of the DL literature has significant implications for industry and practice, given that this, as far as the authors know, is the first systematic review of existing literature in this research area.

This study aims to test the effect that the perceived legitimacy of influencers has on the attitude toward the brand from the consumer point of view, as well as the mediating effect brand trust has on the relationship between the perceived legitimacy of influencers and attitude toward the brand.

By using Google Forms to distribute links on various social media platforms, data were collected between January 15, 2021, and February 20, 2021. The population participants were all over 18 and had social media accounts. In the questionnaire, participants were asked to write down three influencers that they followed. They were then asked to answer the other statements in the survey with these three influencers in mind. Participants were included through convenience sampling from the population. A total of 514 people answered the questionnaire. These questions were then subjected to a statistical analysis using PLS-SEM.

The results showed that cognitive, moral and pragmatic legitimacies significantly affect brand trust. Moreover, the moral and pragmatic legitimacies significantly affect the attitude towards the brand. Regarding the mediation effect, results showed that brand trust has a mediating effect between the perceived legitimacy of influencers and attitude towards the brand.

One of the main limitations of this study is that the data were collected by convenience sampling. Therefore, the research results cannot be generalised. Another limitation is that the study measures general perceptions of influencers' legitimacy, so it has not been addressed in terms of a specific product group, follower or influencer self-branding issues.

The managerial contribution of this research centers on the ability to evaluate the influencers and their legitimacy in society; not only by their follower count but also by the legitimacy factors that can be named under the name of primary legitimacy norms. Managers will then be able to use this framework to determine which influencers they want to work with.

When the literature was reviewed, no study was found that examined and measured the perceived legitimacy of influencers in terms of social norms, values and morals. This research aims to add the concept of the perceived legitimacy of influencers to the discussion in the literature, embody the legitimate framework of influencers' activities and provide a more general conceptual basis for persuasiveness in influencer marketing.

This study aims to provide a holistic review of social media influencers (SMIs) research based on a unique approach of bibliometric analysis and content analysis between 2011 and 2020. The review examines the main influential aspects, themes and research streams to identify research directions for the future.

The sample selection and data collection were done from the Scopus database. The sample dataset was refined based on the inclusion and exclusion criteria to determine the final dataset of 183 articles. The dataset was exported in the BibTeX format and then imported into the BiblioShiny app for bibliometric analysis. The content analysis was done following the theory-context-methodology framework.

The several findings of this study include (1) Co-word analysis of most used keywords; (2) Longitudinal thematic evolution; (3) The focus of the research papers as per the theory-context-methodology review protocol are persuasion knowledge model, fashion and beauty industries, Instagram and content analysis, respectively; and (4) The network analysis of the research studies is known as the co-citation analysis and depicts the intellectual structure in the domain. This analysis resulted in four clusters of the research streams from the literature and two emergent themes (Chen et al., 2010)

In general, the previous reviews in the area are either domain, method or theory-based. Thus, this study aims to complement and extend the existing literature by presenting the overall picture of the SMI research with the help of a unique combined approach and further highlighting the trends and future research directions based on the findings of this study.

This study aims to elucidate the dynamics of social media discourse during global health events, specifically investigating how users across different platforms perceive, react to and engage with information concerning such crises.

A mixed-method approach was employed, combining both quantitative and qualitative data collection. Initially, thematic analysis was applied to a data set of social media posts across four major platforms over a 12-month period. This was followed by sentiment analysis to discern the predominant emotions embedded within these communications. Statistical tools were used to validate findings, ensuring robustness in the results.

The results showcased discernible thematic and emotional disparities across platforms. While some platforms leaned toward factual information dissemination, others were rife with user sentiments, anecdotes and personal experiences. Overall, a global sense of concern was evident, but the ways in which this concern manifested varied significantly between platforms.

The primary limitation is the potential non-representativeness of the sample, as only four major social media platforms were considered. Future studies might expand the scope to include emerging platforms or non-English language platforms. Additionally, the rapidly evolving nature of social media discourse implies that findings might be time-bound, necessitating periodic follow-up studies.

Understanding the nature of discourse on various platforms can guide health organizations, policymakers and communicators in tailoring their messages. Recognizing where factual information is required, versus where sentiment and personal stories resonate, can enhance the efficacy of public health communication strategies.

The study underscores the societal reliance on social media for information during crises. Recognizing the different ways in which communities engage with, and are influenced by, platform-specific discourse can help in fostering a more informed and empathetic society, better equipped to handle global challenges.

This research is among the first to offer a comprehensive, cross-platform analysis of social media discourse during a global health event. By comparing user engagement across platforms, it provides unique insights into the multifaceted nature of public sentiment and information dissemination during crises.

Companies in all industries are searching for new sources of competitive advantage since the competition in their marketplace is becoming increasingly intensive. The resource-based view of the firm explains the sources of sustainable competitive advantages. From a resource-based view perspective, relational based assets (i.e., the assets resulting from firm contacts in the marketplace) enable competitive advantage. The relational based assets examined in this work are brand image and corporate reputation, as components of brand equity, and customer value. This paper explores how they create value. Despite the relatively large amount of literature describing the benefits of firms in having strong brand equity and delivering customer value, no research validated the linkage of brand equity components, brand image, and corporate reputation, simultaneously in the customer value–customer loyalty chain. This work presents a model of testing these relationships in consumer goods, in a business-to-business context. The results demonstrate the differential roles of brand image and corporate reputation on perceived quality, customer value, and customer loyalty. Brand image influences the perception of quality of the products and the additional services, whereas corporate reputation actions beyond brand image, estimating the customer value and customer loyalty. The effects of corporate reputation are also validated on different samples. The results demonstrate the importance of managing brand equity facets, brand image, and corporate reputation since their differential impacts on perceived quality, customer value, and customer loyalty. The results also demonstrate that companies should not limit to invest only in brand image. Maintaining and enhancing corporate reputation can have a stronger impact on customer value and customer loyalty, and can create differential competitive advantage.

The problem of choosing the utmost useful features from hundreds of features from time-series user click data arises in online advertising toward fraudulent publisher's classification. Selecting feature subsets is a key issue in such classification tasks. Practically, the use of filter approaches is common; however, they neglect the correlations amid features. Conversely, wrapper approaches could not be applied due to their complexities. Moreover, in particular, existing feature selection methods could not handle such data, which is one of the major causes of instability of feature selection.

To overcome such issues, a majority voting-based hybrid feature selection method, namely feature distillation and accumulated selection (FDAS), is proposed to investigate the optimal subset of relevant features for analyzing the publisher's fraudulent conduct. FDAS works in two phases: (1) feature distillation, where significant features from standard filter and wrapper feature selection methods are obtained using majority voting; (2) accumulated selection, where we enumerated an accumulated evaluation of relevant feature subset to search for an optimal feature subset using effective machine learning (ML) models.

Empirical results prove enhanced classification performance with proposed features in average precision, recall, f1-score and AUC in publisher identification and classification.

The FDAS is evaluated on FDMA2012 user-click data and nine other benchmark datasets to gauge its generalizing characteristics, first, considering original features, second, with relevant feature subsets selected by feature selection (FS) methods, third, with optimal feature subset obtained by the proposed approach. ANOVA significance test is conducted to demonstrate significant differences between independent features.

The purpose of this paper is to use the Twitter Search Network of the Apache NodeXL data discovery tool to extract over 5,000 data from Twitter accounts that twitted, re-twitted or commented on the hashtag, #NigeriaDecides, to gain insight into the impact of the social media on the politics and administration of developing countries.

Several algorithms like the Fruchterman-Reingold algorithm, Harel-Koren Fast Multiscale algorithm and the Clauset-Newman-Moore algorithms are used to analyse the social media metrics like betweenness, closeness centralities, etc., and visualize the sociograms.

Results from a typical application of this tool, on the Nigeria general election of 2015, show the social media as the major influencer and the contribution of the social media data analytics in predicting trends that may influence developing economies.

With this type of work, stakeholders can make informed decisions based on predictions that can yield high degree of accuracy as this case. It is also important to stress that this work can be reproduced for any other part of the world, as it is not limited to developing countries or Nigeria in particular or it is limited to the field of politics.

Increasingly, during the 2015 general election, citizens have taken over the blogosphere by writing, commenting and reporting about different issues from politics, society, human rights, disasters, contestants, attacks and other community-related issues. One of such instances is the #NigeriaDecides network on Twitter. The effect of these showed in the opinion polls organized by the various interest groups and media houses which were all in favour of GMB.

The case study the authors took on the Nigeria’s general election of 2015 further strengthens the fact that the developing countries have joined the social media race. The major contributions of this work are that policy makers, politicians, business managers, etc. can use the methods shown in this work to harness and gain insights from Big Data, like the social media data.