Brand-related Social Media Research Articles

Automated curation of brand-related social media images with deep learning

This paper presents a work consisting in using deep convolutional neural networks (CNNs) to facilitate the curation of brand-related social media images. The final goal is to facilitate searching and discovering user-generated content (UGC) with potential value for digital marketing tasks. The images are captured in real time and automatically annotated with multiple CNNs. Some of the CNNs perform generic object recognition tasks while others perform what we call visual brand identity recognition. When appropriate, we also apply object detection, usually to discover images containing logos. We report experiments with 5 real brands in which more than 1 million real images were analyzed. In order to speed-up the training of custom CNNs we applied a transfer learning strategy. We examine the impact of different configurations and derive conclusions aiming to pave the way towards systematic and optimized methodologies for automatic UGC curation.

Bridging the gap between social media and behavioral brand loyalty

Abstract Integrating several streams of theoretical reasoning such as social identity theory and customer engagement theory, this study examines the relationship between consumer responses in social media networks and behavioral brand loyalty in the context of Japanese professional sports: football and baseball. Data were collected from 309 panel registrants of an online research panel service. Based on the analysis, user characteristics as an opinion seeker and the entertainment value of social media pages were found to positively influence online brand community identification which in turn had a positive effect on brand-related social media engagement. Further, brand-related social media engagement and team identification, a type of consumer-brand identification, simultaneously affected behavioral brand loyalty. The theoretical model and results reinforced the importance of brand-related social media engagement toward behavioral brand loyalty, and added new insights into the antecedents of consumer engagement in the brand-related use of social media.

Social media sentiment analysis: lexicon versus machine learning

PurposeWith the soaring volumes of brand-related social media conversations, digital marketers have extensive opportunities to track and analyse consumers’ feelings and opinions about brands, products or services embedded within consumer-generated content (CGC). These “Big Data” opportunities render manual approaches to sentiment analysis impractical and raise the need to develop automated tools to analyse consumer sentiment expressed in text format. This paper aims to evaluate and compare the performance of two prominent approaches to automated sentiment analysis applied to CGC on social media and explores the benefits of combining them.Design/methodology/approachA sample of 850 consumer comments from 83 Facebook brand pages are used to test and compare lexicon-based and machine learning approaches to sentiment analysis, as well as their combination, using the LIWC2015 lexicon and RTextTools machine learning package.FindingsResults show the two approaches are similar in accuracy, both achieving higher accuracy when classifying positive sentiment than negative sentiment. However, they differ substantially in their classification ensembles. The combined approach demonstrates significantly improved performance in classifying positive sentiment.Research limitations/implicationsFurther research is required to improve the accuracy of negative sentiment classification. The combined approach needs to be applied to other kinds of CGCs on social media such as tweets.Practical implicationsThe findings inform decision-making around which sentiment analysis approaches (or a combination thereof) is best to analyse CGC on social media.Originality/valueThis study combines two sentiment analysis approaches and demonstrates significantly improved performance.

Social media-based sponsorship activation – a typology of content

PurposeThe purpose of this paper is to thematically categorise sports sponsorship-linked Twitter content and, by drawing on uses & gratifications theory, to map the extent to which these categories cohere with known user motivations for consuming social media.Design/methodology/approachQualitative content analysis of a sample of 1,502 tweets by London 2012 Olympic and Paralympic Games sponsors posted between January 2011 and September 2012 was used to develop the typology of sponsorship-linked Twitter content.FindingsFrom the data, a typology is developed, comprising 17 categories grouped under four main types: informing, entertaining, rewarding and interacting. The majority of sponsor tweets (68 per cent) fell into the informing type, with 17 per cent categorised as interacting. While few (2 per cent) tweets were categorised as entertaining, the link to the sponsored event implies a degree of entertaining content even in ostensibly informative, rewarding or interactional sponsorship-linked tweets. Therefore, the typology categories highlight Twitter content produced by sponsors which engages customers, fostering dialogue alongside providing informative and entertaining content.Practical implicationsThe typology can inform practitioners’ future sports sponsorship activation planning decisions and can also aid rights holders in tailoring appropriate sponsorship opportunities to potential sponsors, based on an appreciation of the nature of content sought by brand followers.Originality/valueThe typology extends existing understanding of the use of social media within sponsorship activation campaigns by thematically categorising content and mapping this against known user motivations for consuming brand-related social media content.

‘We’ are more likely to endorse than ‘I’: the effects of self-construal and brand symbolism on consumers’ online brand endorsements

Recent research increasingly highlights that consumers engage in online brand endorsements (e.g. Facebook likes) to signal their identity, but has failed to explain why different consumers use this type of signaling to differing degrees. This paper addresses this gap by looking at a culturally constructed individual difference variable, namely self-construal. Self-construal, which can be independent or interdependent, refers to the extent that people define themselves in terms of the relations they have with others. In four studies, this research shows that consumers’ self-construal is related to their intention to endorse brands online. In particular, high levels of interdependent self-construal positively affect consumers’ intention to endorse brands online (Studies 1A & 1B). This effect is mediated by an increased perception of brands’ symbolic value (Study 2). Moreover, this positivity bias toward symbolic brand cues is conditional upon consumers’ brand attitude (Study 3). These findings demonstrate that consumers’ identity plays a central role in their brand perception and brand-related social media use.

Measuring Consumers' Engagement With Brand-Related Social-Media Content

ABSTRACT The purpose of the current study was to develop a scale to measure the consumer9s engagement with brand-related social-media content, based on three dimensions established in the framework of an earlier theoretical construct, “Consumer9s Online Brand-Related Activities” (Muntinga, Moorman, and Smit, 2011). Qualitative techniques were used to generate an initial pool of items that captured different levels of consumer engagement with consumption, contribution, and creation of brand-related social-media content. Quantitative data from a survey of 2,252 consumers across Poland then was collected in two phases to calibrate and validate the ensuing scale, measuring participants9 engagement, with nearly 300 brands spanning a range of industries. Results confirmed the structure and psychometric properties of the scale.

Introducing COBRAs

Social media websites such as Facebook, YouTube and Twitter provide unlimited means for internet users to interact, express, share and create content about anything, including brands. Such consumers’ online brand-related activities (COBRAs) have significant consequences for firms. To effectively anticipate and direct these consequences, understanding people’s motivations to engage in brand-related social media use is imperative. This article makes a first effort to come to such an understanding. Instant messaging (IM) interviews were conducted with people engaged in COBRAs about their motivations to do so. Reporting motivations for the full spectrum of COBRA types (consuming, contributing and creating), the authors provide marketers and brand managers with valuable insights into consumer behaviour in a social media-dominated era.