Search results

Although numerous signal modalities are available for emotion recognition, audio and visual modalities are the most common and predominant forms for human beings to express their emotional states in daily communication. Therefore, how to achieve automatic and accurate audiovisual emotion recognition is significantly important for developing engaging and empathetic human–computer interaction environment. However, two major challenges exist in the field of audiovisual emotion recognition: (1) how to effectively capture representations of each single modality and eliminate redundant features and (2) how to efficiently integrate information from these two modalities to generate discriminative representations.

A novel key-frame extraction-based attention fusion network (KE-AFN) is proposed for audiovisual emotion recognition. KE-AFN attempts to integrate key-frame extraction with multimodal interaction and fusion to enhance audiovisual representations and reduce redundant computation, filling the research gaps of existing approaches. Specifically, the local maximum–based content analysis is designed to extract key-frames from videos for the purpose of eliminating data redundancy. Two modules, including “Multi-head Attention-based Intra-modality Interaction Module” and “Multi-head Attention-based Cross-modality Interaction Module”, are proposed to mine and capture intra- and cross-modality interactions for further reducing data redundancy and producing more powerful multimodal representations.

Extensive experiments on two benchmark datasets (i.e. RAVDESS and CMU-MOSEI) demonstrate the effectiveness and rationality of KE-AFN. Specifically, (1) KE-AFN is superior to state-of-the-art baselines for audiovisual emotion recognition. (2) Exploring the supplementary and complementary information of different modalities can provide more emotional clues for better emotion recognition. (3) The proposed key-frame extraction strategy can enhance the performance by more than 2.79 per cent on accuracy. (4) Both exploring intra- and cross-modality interactions and employing attention-based audiovisual fusion can lead to better prediction performance.

The proposed KE-AFN can support the development of engaging and empathetic human–computer interaction environment.

This study aims to explore how a postmodern tribe enacts and re-interprets ideologies as a part of consumers’ collective experience, to enhance our understanding of consumer communities in conjunction with ideological capacities.

The community of “presenteers” is conceptualized as a self-organized tribe with heterogeneous components that generate capacities to act. Netnographic observation was conducted on 18 presenteer accounts and lasted around six months. Real-time data were collected by taking screenshots of the posts and stories that these users created and publicly shared. Data were analysed by adopting assemblage theory, combining inductive and deductive approaches. Firstly, a qualitative visual-textual content analysis of the tribe’s defining components was conducted. Then, the process continued with the thematic analysis of the ideological underpinnings of the tribe’s enactments.

Findings shed light on the ways in which consumer communities interpret the entanglement of religious, political, and cultural ideologies in shaping their experiences. In the case of the presenteers tribe, findings reflect a novel ideological interplay between neo-Ottomanism, post-feminism and consumerism.

The study offers a deep dive into a unique tribe that is being organized around the consumer-created practice of “presenteering” and investigates consumer communalization in alignment with the ideological turn in culture-oriented interpretative research on consumers, consumption, and markets. This exploration helps to bridge the research on the communalization of consumers with the recent discussions of ideology in the postmodern market.

The study offers a deep dive into a unique tribe that is being organized around the consumer-created practice of “presenteering” and investigates consumer communalization in alignment with the ideological turn in culture-oriented interpretative research on consumers, consumption, and markets. This exploration helps to bridge the research on the communalization of consumers with the recent discussions of ideology in the postmodern market.

This research explores the differential effects of pixel-level and object-level visual complexity in firm-generated content (FGC) on consumer engagement in terms of the number of likes and shares, and further investigates the moderating role of image brightness.

Drawing on a deep learning analysis of 85,975 images on a social media platform in China, this study investigates visual complexity in FGC.

The results indicate that pixel-level complexity increases both the number of likes and shares. Object-level complexity has a U-shaped relationship with the number of likes, while it has an inverted U-shaped relationship with the number of shares. Moreover, image brightness mitigates the effect of pixel-level complexity on likes but amplifies the effect on shares; contrarily, it amplifies the effect of object-level complexity on likes, while mitigating its effect on shares.

Although images play a critical role in FGC, visual data analytics has rarely been used in social media research. This study identified two types of visual complexity and investigated their differential effects. We discuss how the processing of information embedded in visual content influences consumer engagement. The findings enrich the literature on social media and visual marketing.

This study aims to investigate the influence of the reviewed establishment’s price level and the user’s social network size and reputation status on consumers’ tendency to post more visual imagery content. Furthermore, it explores the moderating effects of user experiences and geographic distance on these dynamics.

This study adopts a multi-method approach to explore both the determinants behind the sharing of user-generated photos in online reviews and their internal mechanisms. Using a comprehensive secondary data set from Yelp.com, the authors focused on restaurant reviews from a prominent tourist destination to construct econometric models incorporating time-fixed effects. To enhance the robustness of the authors’ findings, the authors complemented the big data analysis with a series of controlled experiments.

The reviewed establishments price level and the users reputation status and social network size incite corresponding motivations conspicuous display “reputation seeking” and social approval motivating users to incorporate more images in reviews. “User experiences can amplify the influence of these factors on image sharing.” An increase in the users geographical distance lessens the impact of the price level on image sharing, but it heightens the influence of the users reputation and social network size on the number of shared images.

As a result of this study, high-end establishments can increase their online visibility by leveraging user-generated visual content. A structured rewards program could significantly boost engagement by incentivizing photo sharing, particularly among users with elite status and extensive social networks. Additionally, online review platforms can enhance users’ experiences and foster more dynamic interactions by developing personalized features that encourage visual content production.

This research, anchored in trait activation theory, offers an innovative examination of the determinants of photo-posting behavior in online reviews by enriching the understanding of how the intricate interplay between users’ characteristics and situational cues can shape online review practices.

The study seeks to contribute to a deeper understanding of the relationship between remediations and participation in new media. By lending some transparency, the analysis hopes to contribute toward generating a critical optics aware of the potentials and pitfalls of emergent media.

The methodology is visual semiotic analysis. The author make no claim for one, true interpretation or critical judgment about the images.

In demonstrating some shortfalls of Instagram affordances, the analysis shows how social media sites can develop tools that encourage users to engage in civic consciousness and respectful political debate. The study makes clear that new media tools can hamper or aid participatory logics.

To author’s knowledge, no other study that has analyzed remediated images related to the controversial confirmation of Brett Kavanaugh to the U.S. Supreme Court. It is also important to place these images in the contexts of “iconicity” in emergent media (a concept increasingly being eroded in new media environment).

Based on sensory marketing theory and cognitive appraisal theory, this study investigates whether and how the background visual complexity of live-streaming affects consumers' purchase intention and reveals the underlying mechanisms through which background visual complexity influences consumers' purchase decisions.

The experiment was conducted with 180 college students, using eye-tracking technology to explore the impact mechanism of live background visual complexity on consumers' purchase intention, considering three types of background visual complexity (high vs medium vs low) and two levels of need for cognitive closure (high vs low).

Firstly, the background visual complexity of live-streaming positively influences consumers' purchase intention by eliciting positive emotions (pleasure and arousal), and the relationship between consumer emotions and purchase intention is nonlinear. Secondly, need for cognitive closure to significantly moderate the influence of background visual complexity on purchase intention.

The limited sample size makes it difficult to generalize to other consumer groups. Also, the study only focuses on one visual factor, lacking comprehensive analysis from multiple perspectives.

It is recommended that live e-commerce companies optimize the visual design of live-streaming backgrounds and identify consumer traits to match the visual complexity with consumers' level of need for cognitive closure, thereby stimulating positive emotions and facilitating more satisfactory shopping decisions.

This paper addresses an interesting and practical issue related to the effects of live background visual complexity on consumers' purchase intention.

The purpose of this paper is to examine how users on social media view brands with a heritage. Consumers commonly post opinions and accounts of their experiences with brands on social media. Such consumer-generated content may or may not overlap with content desired by brand managers. Drawing from “The medium is the message” paradigm, this study text-mines user narratives on Twitter1 to shed light on the role of social media in shaping public images of brands with heritage through the lens of the stereotype content model.

The study uses a data set of almost 80,000 unique tweets on 12 brands across six categories, compares brands high versus low in heritage and combines dictionary-based content analysis with sentiment analysis.

The results indicate that both user-generated content and sentiment are significantly more positive for brands low rather than high in heritage. Regarding warmth, consumers use significantly more positive words on sociability and fewer negative words on morality for brands low rather than high in heritage. Regarding competence, tweets include more positive words on assertiveness and ability for low-heritage brands. Finally, overall sentiment is more positive for brands low rather than high in heritage.

Important from co-creation and integrated marketing communication perspectives, the findings provide brand managers with actionable insights on how to more effectively use social media.

To the best of the authors’ knowledge, this research is among the first to examine user-generated content in a brand heritage context. It demonstrates that heritage brands, with their longevity and strong links to the past, need to be aware of how contemporary social media can detract from their image.

Early childhood and early elementary are key times when children develop internal and external antifat attitudes; thus, it is necessary to better understand the available children’s literature around fatness.This paper aims to examine children's picture books with fat protagonists to better understand the current landscape of children's literature. Drawing on relevant literature around fat characters and the fat studies movement, this critical content analysis considers five children’s books featuring fat protagonists.

This study uses critical content analysis to analyze texts featuring fat protagonists, including two rounds of initial reading and analysis. Using lenses of critical literacy and critical multicultural analysis, the author looks for common themes, silences and absences in the texts, images and peritext.

This paper identifies themes of characters initially internalizing antifatness, then pushing back against antifat bias toward existing with joy and without stigma. Several of these texts even draw on the history of fat activism, highlighting societal critique and a potential activist component of children’s literature with fat protagonists.

The study has a small number of books, due to the limited number of texts that fit the study parameters.

The paper concludes with examples of scaffolding for teachers and parents to have conversations with young children about antifat bias while also acknowledging notable absences, particularly boy protagonists.

These themes illustrate the power of young children to push back against antifat bias and critique oppressive social structures.

There have been very few studies looking at antifatness in children’s picture books. With more books with fat protagonists coming out in the 2020s, this study offers an understanding of the themes present, while also emphasizing the need for an intersectional approach to literature with fat protagonists.

The social media industry has entered a new stage with intensifying competition and heightened uncertainty about future directions. The purpose of this paper is to provide analyses of the current challenges and to identify industry-wide trends that may offer a roadmap for the future.

Drawing on publicly available key performance metrics, company reports and press reports, this paper offers critical analyses of the challenges facing the major social media platforms and new trends in the social media industry.

This study identified five major trends in the current social media industry: 1) content is king, and that content is moving to visual; 2) artificial intelligence is key to competitive advantage; 3) network effects still matter, but business model innovation can overcome that barrier; 4) the need to broaden revenue sources; and 5) the strive for the everything app. In this changing environment, social media companies need to adapt and innovate their business models proactively to stay ahead.

This paper not only sheds light on the current challenges of individual social media platforms but also identifies industry-wide trends that may apply across all platforms. Taken together, these insights paint a comprehensive picture of the current industry landscape, as well as offer clues about its future directions.

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.