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.

Nature’s evolution has shaped intelligent behaviors in creatures like insects and birds, inspiring the field of Swarm Intelligence. Researchers have developed bio-inspired algorithms to address complex optimization problems efficiently. These algorithms strike a balance between computational efficiency and solution optimality, attracting significant attention across domains.

Bio-inspired optimization techniques for feature engineering and its applications are systematically reviewed with chief objective of assessing statistical influence and significance of “Bio-inspired optimization”-based computational models by referring to vast research literature published between year 2015 and 2022.

The Scopus and Web of Science databases were explored for review with focus on parameters such as country-wise publications, keyword occurrences and citations per year. Springer and IEEE emerge as the most creative publishers, with indicative prominent and superior journals, namely, PLoS ONE, Neural Computing and Applications, Lecture Notes in Computer Science and IEEE Transactions. The “National Natural Science Foundation” of China and the “Ministry of Electronics and Information Technology” of India lead in funding projects in this area. China, India and Germany stand out as leaders in publications related to bio-inspired algorithms for feature engineering research.

The review findings integrate various bio-inspired algorithm selection techniques over a diverse spectrum of optimization techniques. Anti colony optimization contributes to decentralized and cooperative search strategies, bee colony optimization (BCO) improves collaborative decision-making, particle swarm optimization leads to exploration-exploitation balance and bio-inspired algorithms offer a range of nature-inspired heuristics.

Knowledge management (KM) is an important topic in the age of big data, and this study adds to the existing body of literature by providing a novel KM perspective on the technological phenomenon of artificial intelligence (AI). This study aims to discover how AI might facilitate knowledge-based business-to-business (B2B) marketing. In this chapter, the authors take a close look at the building blocks of AI and the relationships between them. Future research directions and also the effects of the various market information building components on B2B marketing are discussed. The study’s approach is theoretical; it tries to provide a framework for characterising the phenomenon of AI and its constituent parts. Additionally, this chapter provides a methodical analysis of the three categories of market information crucial to B2B marketing: knowledge of customers, knowledge of users, and knowledge of external markets. This research looks at AI through the lens of the conventional data processing framework, analysing the six pillars upon which AI systems are founded. It also explained how the framework’s components work together to transform data into actionable information. In this chapter, the authors will look at how AI works and how it can benefit B2B knowledge-based marketing. It’s not aimed at AI experts but rather at general marketing managers. In this chapter, the possible effects of AI on B2B marketing are discussed using examples from the real world.

This paper aims to disentangle Chinese-English-rich resources linguistic and speaker timbre features, achieving cross-lingual speaker transfer for Cambodian.

This study introduces a novel approach: the construction of a cross-lingual feature disentangler coupled with the integration of time-frequency attention adaptive normalization to proficiently convert Cambodian speaker timbre into Chinese-English without altering the underlying Cambodian speech content.

Considering the limited availability of multi-speaker corpora in Cambodia, conventional methods have demonstrated subpar performance in Cambodian speaker voice transfer.

The originality of this study lies in the effectiveness of the disentanglement process and precise control over speaker timbre feature transfer.

The study aims to examine the indirect relationships via application (app) brand self-relevance emotions and self-relevance that underlie the relationships between perceived value of mobile apps and (brand) love with respect to mobile apps. The study further investigates the moderating role of user–app relationship duration in the formation process of brand love for mobile apps from a dynamic and long-term perspective.

A multiple moderated-mediation model is developed and empirically tested with a sample of 396 users of popular Chinese mobile educational apps.

The study reveals that utilitarian value exhibits positive indirect relationships with brand love for mobile apps through increased positive self-relevance emotions. All three types of perceived value of mobile apps (utilitarian, hedonic and social) affect app brand love positively via self-relevance. These three types of perceived value were found to be serially linked to brand love through self-relevance and self-relevance emotions. Furthermore, empirical evidence is found for the moderating effects of user–app relationship duration.

By testing mechanisms simultaneously in an integrative model, this study investigates the reasons for app brand love that attract a user into a lasting relationship with an app and extends knowledge of the app brand love building process in inducing strong and positive brand–self connections. Our study also makes practical contributions by offering insights into delivering the most desired benefits to mobile app users according to different contextual conditions, in order to attract and retain users in a more cost-effective manner.

Explore how the degree of humanization affects user misconduct, and provide effective misconduct prevention measures for the wide application of artificial intelligence in the future.

Based on the “Uncanny Valley theory”, three experiments were conducted to explore the relationship between the degree of humanization of service machines and user misbehavior, and to analyze the mediating role of cognitive resistance and the moderating role of social class.

There is a U-shaped relationship between the degree of humanization of service machines and user misbehavior; Social class not only regulates the main effect of anthropomorphism on misbehavior, but also regulates the intermediary effect of anthropomorphism on cognitive resistance, thus affecting misbehavior.

The design of the service robot can be from the user’s point of view, combined with the user’s social class, match different user types, and provide the same preferences as the user’s humanoid service robot.

This study is an important reference value for enterprises and governments to provide intelligent services in public places. It can prevent the robot from being vandalized and also provide users with a comfortable human-computer interaction experience, expanding the positive effects of providing smart services by government and enterprises.

This study avoids and reduces users' misbehavior towards intelligent service robots, improves users' satisfaction in using service robots, and avoids service robots being damaged, resulting in waste of government, enterprise and social resources.

From the perspective of product factors to identify the inducing factors of improper behavior, from the perspective of social class of users to analyze the moderating effect of humanization degree and user improper behavior.

Social media (SM) platforms tempt individuals to communicate their perspectives in real-time, rousing engaging discussions on countless topics. People, besides using these platforms to put up their problems and solutions, also share activist content (AC). This study aims to understand why people participate in activist AC sharing on SM by investigating factors related to planned and unplanned human behaviour.

The study adopted a quantitative approach and administered a close-ended structured questionnaire to gather data from 431 respondents who shared AC on Facebook. The data was analysed using hierarchical regression in SPSS.

The study found a significant influence of both planned (perceived social gains (PSGs) , altruism and perceived knowledge (PK)) and unplanned (extraversion and impulsiveness) human behaviour on activist content-sharing behaviour on SM. The moderating effect of enculturation and general public opinion (GPO) was also examined.

Sharing AC on SM is not like sharing other forms of content such as holiday recommendations – the former can provoke consequences (sometimes undesirable) in some regions. Such content can easily leverage the firehose of deception, maximising the vulnerability of those involved. This work, by relating human behaviour to AC sharing on SM, offers significant insights to enable individuals to manage their shared content and waning probable consequences.

This work combined two opposite constructs of human behaviour: planned and unplanned to explain individual behaviour in a specific context of AC sharing on SM.

It is important to implement artificial intelligence (AI) because it can simplify and solve complex problems faster than humans. Because AI learns about people and their behavior from the first purchase, AI marketing can boost marketing efforts by leveraging data to target extremely precise consumer groups. There is a debate about the efficacy of AI marketing due to the constraints and limits imposed by the system's nature. This chapter presents insights from published studies regarding the relationship of AI with marketing and how AI can affect marketing. A real-world example of Netflix's usage of AI in marketing has been demonstrated. Then, consumer attitudes regarding AI were revealed. Then, several ethical considerations concerning AI were highlighted. Finally, the anticipated future of AI marketing was addressed. This chapter demonstrated the significance of firms implementing AI marketing to get a competitive advantage. Although some of the difficulties mentioned in this study need to be resolved, AI marketing has a bright future. There are ethical concerns about bias and privacy that should be addressed further. This chapter will encourage firms to use AI systems in marketing, and it will open the door to concerns that will need to be investigated academically in the future.

Skilled workers are crucial for an organization’s success, and managing, retaining and attracting them is vital in long-term. This study aims to explore talent management practices in the Finnish restaurant industry and to align workers' expectations with the real-world experiences of their work to reduce turnover and enhance job satisfaction.

The study adopts a mixed methods approach, including a survey and interviews with workers and managers to gain insights into their expectations and experiences of work. The study considers themes for designing and implementing effective talent management procedures.

This study highlights the importance of employees' experiences of their work conditions, leveraging positive emotions and fair utilization of temporary agency work (TAW). Understanding the different work preferences of generational cohorts and addressing the challenges associated with owner disengagement and TAW can also contribute to attracting and retaining talent in the restaurant industry.

Skilled workers have often been portrayed as targets that need to be managed, with insufficient consideration given to their preferences, needs and expectations. With the findings of this study, companies can establish mutual understanding with their employees and attract diverse talent.

This study aims to delve into the lived experiences, challenges and visions of women entrepreneurs in Jordan, placing a magnifying glass on those spearheading or co-pioneering start-ups. It aims to understand the myriad factors that influence their entrepreneurial journey, from motivation to the future of their niche.

Adopting a qualitative lens, this study is anchored in semi-structured interviews encompassing 20 Jordanian women entrepreneurs. Following this, thematic analysis was deployed to dissect and categorize the garnered insights into ten salient themes.

The study reveals that personal experiences and challenges are pivotal in directing these women towards niche markets, aligning with the theory of planned behaviour (TPB). Tools such as digital instruments, customer feedback and innovative strategies like storytelling and augmented reality are integral to their entrepreneurial success, resonating with the resource-based view (RBV). Additionally, challenges like cultural barriers and infrastructural limitations are navigated through adaptive strategies, reflecting the resilience inherent in these entrepreneurs. Networking, mentorship, embracing technological advancements and implementing sustainable practices are highlighted as crucial elements underpinned by the social identity theory (SIT).

Contrary to the extant body of research, this study provides new insights into the challenges faced by women entrepreneurs in Jordan, highlighting the practical relevance of theories like TPB, RBV and SIT for both policymakers and the start-up community in niche markets.