Twitter as a predictive system: A systematic literature review

Cano-Marin, Enrique; Mora‐Cantallops, Marçal; Sánchez‐Alonso, Salvador

doi:10.1016/j.jbusres.2022.113561

Cited by 27 publications

(16 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Social Network Analysis (SNA) offers valuable insights into studying a network's structure and communications of hidden knowledge (Hansen et al ., 2010), emphasizing relationships rather than isolated individuals or organizations in the “two-way dialogue” (Himelboim et al ., 2014). Twitter data possesses latent predictivity, which has not been adequately explored in previous SNA studies on Twitter, and can help identify influencers in the adoption and diffusion of the Metaverse (Cano-Marin et al ., 2023). Previous research on Twitter has not explicitly investigated the role of word-of-mouth in influencing trend diffusion (Araujo et al ., 2017).…”

Section: Introductionmentioning

confidence: 99%

Exploring the diffusion of digital fashion and influencers' social roles in the Metaverse: an analysis of Twitter hashtag networks

Kim,

Chakraborty

2023

INTR

View full text Add to dashboard Cite

PurposeThe study aims to explore the digital fashion trend within the Metaverse, characterized by non-fungible tokens (NFTs), across Twitter networks. Integrating theories of diffusion of innovation, two-step flow of communication and self-efficacy, the authors aimed to uncover the diffusion structure and the influencer's social roles undertaken by social entities in fostering communication and collaboration for the advancement of Metaverse fashion.Design/methodology/approachSocial network analysis examined the critical graph metrics to profile, visualize, and cluster the unstructured network data. The authors used the NodeXL program to analyze two hashtag keyword networks, “#metaverse fashion” and “#metawear,” using Twitter API data. Cluster, semantic, and time series analyses were performed to visualize the contents and contexts of communication and collaboration in the diffusion of Metaverse fashion.FindingsThe results unraveled the “broadcast network” structure and the influencers' social roles of opinion leaders and market mavens within Twitter's “#metaverse fashion” diffusion. The roles of innovators and early adopters among influencers were comparable in collaborating within the competition venues, promoting awareness and participation in digital fashion diffusion during specific “fad” periods, particularly when digital fashion NFTs and cryptocurrencies became intertwined with the competition in the Metaverse.Originality/valueThe study contributed to theory building by integrating three theories, emphasizing effective communication and collaboration among influencers, organizations, and competition venues in broadcasting digital fashion within shared networks. The validation of multi-faceted Social Network Analysis was crucial for timely insights, highlighting the critical digital fashion equity in capturing consumers' attention and driving engagement and ownership of Metaverse fashion.

show abstract

Section: Introductionmentioning

confidence: 99%

Exploring the diffusion of digital fashion and influencers' social roles in the Metaverse: an analysis of Twitter hashtag networks

Kim,

Chakraborty

2023

INTR

View full text Add to dashboard Cite

show abstract

“…Therefore, a comparison of personal‐attack parodies on different social media networks (Facebook, Twitter, etc.) (Cano‐Marin et al, 2023; Marwick & Boyd, 2011; Šola et al, 2022), media (television, internet), and cultures (Patrício & Ferreira, 2023; Uriarte et al, 2023) would be interesting to explore.…”

Section: Discussionmentioning

confidence: 99%

“…Therefore, a comparison of personal-attack parodies on different social media networks (Facebook, Twitter, etc. )(Cano-Marin et al, 2023;Marwick & Boyd, 2011;…”

mentioning

confidence: 99%

When your supporters become your opponents: Exploring the unintended effects of parodies on social media engagement

Sabri,

El Hana,

Abidi

et al. 2023

Psychology and Marketing

View full text Add to dashboard Cite

Using parodies to mock politicians' personal flaws is a prevalent practice and represents an important threat to their brand image and reputation. However, the ability of parodies based on personal attacks to create positive social media engagement from the parodist's point of view is still unexplored. This study contributes to the attribution–emotion–action theory by exposing the unintended effects of parodies on social media engagement. We began with a content analysis of 331 parodies of political figures posted on YouTube from 2012 to 2019. Then, by using both a machine‐learning‐based analysis of 31,300 comments on those parodies and an experiment, we compared the effectiveness of two types of parodies based on personal attacks, depending on the type of stigma depicted: controllable versus uncontrollable. Our findings are paradoxical. Compared to parodies based on controllable personal stigmas, parodies of uncontrollable stigmas foster less supportive social media engagement toward the parodist and his/her parody (i.e., likes, shares), especially among individuals who were originally detractors and opponents of the parodied politician. Those effects are mediated by the role of moral‐condemning emotions expressing the inappropriateness of the topic selected by the parodist. Henceforth, it is advisable for parodists to refrain from incorporating representations of an uncontrollable stigma into their spoof creations, as such actions may imperil the levels of engagement exhibited by their audience, encompassing both their reception of the parodies and their perception of the parodists themselves.

show abstract

“…Latent Dirichlet allocation (Blei et al, 2003) has gained traction in marketing research (e.g., Büschken & Allenby, 2016;Tirunillai & Tellis, 2014;Zhong & Schweidel, 2020), particularly for topic modeling of reviews or other user-generated content (Tirunillai & Tellis, 2014) and marketing literature abstracts (e.g., Cano-Marin et al, 2023;Schmitt et al, 2022;Wang et al, 2015).…”

Section: Clustering Similar Papers and Eliciting Topicsmentioning

confidence: 99%

How to conduct efficient and objective literature reviews using natural language processing: A step‐by‐step guide for marketing researchers

Pugliese,

Giannetti,

Banerjee

2023

Psychology and Marketing

View full text Add to dashboard Cite

Literature reviews are crucial for attaining a full understanding of the key topics and latest trends in research and instrumental in identifying important research gaps. Unfortunately, conducting literature reviews can be time‐consuming, and the outcomes are frequently subjective. Hence, to address such limitations, we detail an alternative, recent approach to conducting literature reviews. In this research, we outline the steps involved in conducting a literature review via natural language processing. Specifically, we illustrate how to (1) select relevant papers using term frequency‐inverse document frequency and (2) perform topic modeling analysis through latent Dirichlet allocation to identify key research topics. This study and the associated ready‐to‐use Python code provide researchers, including those in consumer behavior, with detailed guidance on how to use natural language processing in their literature reviews.

show abstract

Twitter as a predictive system: A systematic literature review

Cited by 27 publications

References 98 publications

Exploring the diffusion of digital fashion and influencers' social roles in the Metaverse: an analysis of Twitter hashtag networks

Exploring the diffusion of digital fashion and influencers' social roles in the Metaverse: an analysis of Twitter hashtag networks

When your supporters become your opponents: Exploring the unintended effects of parodies on social media engagement

How to conduct efficient and objective literature reviews using natural language processing: A step‐by‐step guide for marketing researchers

Contact Info

Product

Resources

About