Search results

Genre classification of songs based on lyrics is a challenging task even for humans, however, state-of-the-art natural language processing has recently offered advanced solutions to this task. The purpose of this study is to advance the understanding and application of natural language processing and deep learning in the domain of music genre classification, while also contributing to the broader themes of global knowledge and communication, and sustainable preservation of cultural heritage.

The main contribution of this study is the development and evaluation of various machine and deep learning models for song genre classification. Additionally, we investigated the effect of different word embeddings, including Global Vectors for Word Representation (GloVe) and Word2Vec, on the classification performance. The tested models range from benchmarks such as logistic regression, support vector machine and random forest, to more complex neural network architectures and transformer-based models, such as recurrent neural network, long short-term memory, bidirectional long short-term memory and bidirectional encoder representations from transformers (BERT).

The authors conducted experiments on both English and multilingual data sets for genre classification. The results show that the BERT model achieved the best accuracy on the English data set, whereas cross-lingual language model pretraining based on RoBERTa (XLM-RoBERTa) performed the best on the multilingual data set. This study found that songs in the metal genre were the most accurately labeled, as their text style and topics were the most distinct from other genres. On the contrary, songs from the pop and rock genres were more challenging to differentiate. This study also compared the impact of different word embeddings on the classification task and found that models with GloVe word embeddings outperformed Word2Vec and the learning embedding layer.

This study presents the implementation, testing and comparison of various machine and deep learning models for genre classification. The results demonstrate that transformer models, including BERT, robustly optimized BERT pretraining approach, distilled bidirectional encoder representations from transformers, bidirectional and auto-regressive transformers and XLM-RoBERTa, outperformed other models.

This chapter focuses on creativity and innovation, drawing inspiration from Taylor Swift’s song “Sparks Fly.” The chapter highlights the distinction between creativity (generating new ideas) and innovation (implementing these ideas). Using Swift’s authentic and entrepreneurial leadership style as an example, the chapter demonstrates how leaders can foster a supportive environment that encourages both creativity and innovation. It also explores various leadership behaviors that help cultivate these qualities, emphasizing how leaders can drive organizational success by nurturing creativity and innovation within their teams.

This paper aims to examine the lived experiences of a professional accountant, exploring how he navigated the complexity of change in specific accounting processes in the UK housing association (HA). Using an autoethnographic approach, the authors seek to relate individual and collective insights into the changing of social housing organisational processes.

This autoethnographic account draws on participant and participant-observer reflections, as well as several materials maintained by the professional accountant, from a turbulent period in UK social housing. These data are analysed abductively, where the HA was perceived to be a constellation of ritual activities that underpinned a working community.

The professional accountant, who is one of the authors, sought to transform HA’s finance function to be “World-class”. Among others, allegedly outdated accounting processes in the HA seemed to require radical change to enable quicker yet more financially substantiated decision-making. Office rituals facilitated the associated accounting process changes by drawing on camaraderie and team/family bonding, which became amenable to new (accounting) rituals. However, the change process was complex and may well have undermined the existing camaraderie in the finance team. The paper reflects on this, with the professional accountant looking back on his actions within the HA after he had left the HA and had entered academia.

This study demonstrates the potential of autoethnographic reflections in accounting research when accounting is seen as ritualised activity. Hence, abductively, the reflection is theorised through the notion of “ritual” and its antecedent, “liminality”. This autoethnographic narrative may serve as an aid for others who may also face turbulent periods which require navigating change, while they experience personal struggles relating to this change.

This chapter explores Taylor Swift’s leadership in music and business. Highlighting her use of leader–member exchange (LMX) and servant leadership (Dansereau et al., 1975), Swift creates a deep connection with her fans. This chapter demonstrates how Swift empowers her fans through open communication, mutual respect, and shared goals. By fostering high-quality relationships and embodying servant leadership traits such as empathy and stewardship, Swift inspires loyalty and trust. Her high level of engagement with her followers turns her influence into a powerful tool for advocating her values and making impactful decisions.

This chapter examines Taylor Swift’s exceptional team-building and sustaining efforts that enhance her brand. Using social capital and Hackman’s team effectiveness model (Hackman, 1987, 2002, 2009), the chapter delves into how Swift surrounds herself with talented professionals and forms strategic relationships with emerging musicians. These connections foster trust, reciprocity, and collaborative success. By aligning her team with shared goals and maintaining strong interpersonal relationships, Swift exemplifies effective leadership in the music industry. This chapter provides insights into building and managing high-performing teams through unity and shared purpose.

The global music industry has witnessed a tumultuous development in recent years with the emergence of music streaming services (MSSs) which played a pivotal role in rescuing the industry from persistent losses caused by piracy. MSSs are predominantly accessed via mobile applications making it imperative for the music streaming service providers (MSSPs) to focus on enhancing their app-based service quality. Furthermore, the sphere of music streaming has received only limited attention in research thus far, and to address this research void, this study contributes to the existing body of literature by introducing a scale to measure the service quality of music streaming apps, i.e. the MSASQ scale.

A mixed-method approach encompassing both qualitative as well as quantitative research techniques involving two-stage data collection was adopted. Items for the scale were collected via secondary (reports, articles, customer reviews, etc.) as well as primary sources (focus groups and interviews). The scale was tested on a sample of 1,129 Music Streaming App (MSA) users for reliability and validity.

A multidimensional MSASQ scale with 36 items measuring nine dimensions (hedonic quality, efficiency, user interface content, customer support, personalisation, ease of use, privacy/security and quality of ad exposure) was developed and validated.

The research endeavours to explore new perspectives on service quality within the music streaming industry, particularly in relation to the freemium model.

The resurgence of VR began in 2009 with Palmer Luckey's project to create a head-mounted 3D VR gaming device, leading to the development of Oculus. This movement was heavily influenced by hardcore gaming values, particularly those of John Carmack, a pioneer in first-person shooter games. The Oculus Kickstarter in 2012 emphasised VR for hardcore gamers, aiming for high graphical fidelity and immersive experiences. However, this focus has limited VR's potential. The chapter examines two case studies: SuperHot VR and Beat Saber. SuperHot VR challenges the emphasis on photorealism by offering immersion-through-proprioception, providing a unique VR experience without relying on high graphical fidelity. Beat Saber, though often seen as a casual game, has become the bestselling VR game by offering a pleasurable, short-play experience reminiscent of Nintendo Wii's casual games. The success of these games suggests that VR can thrive by appealing to a broader audience beyond hardcore gamers. By focusing on embodiment rather than purely visual immersion, these games highlight the potential for diverse VR experiences. This chapter argues that the fixation on hardcore gaming values, characterised by hyper-realistic graphics and intense gameplay, has restricted VR's growth. The success of games like SuperHot VR and Beat Saber demonstrates that VR can achieve broader appeal and greater success by catering to more varied gaming preferences and moving beyond the narrow confines of hardcore gamer culture.

Aside from grappling with technological advancements, enterprises in the industrial internet era are embracing business model innovation to align with the evolution of the industrial internet. However, a gap persists in the existing research regarding the strategies and methods available to small and medium-sized enterprises (SMEs) for executing business model innovation. Therefore, this paper aims to explore the connotation, characteristics and logic of business model innovation for SMEs in the industrial internet era.

To explore the business model innovation logic of small and medium-sized enterprises in the era of industrial internet, the paper adopts a longitudinal single-case study approach, with PAYA, a medium-sized enterprise in the electromechanical industry, serving as the subject of research. It systematically analyzes PAYA’s business model innovation, centering on four key elements of the business model: value proposition, value creation, value delivery and value capture.

The study proposes two types of business model innovation, namely, “Migration” and “Expansion”, and explains the logic of business model innovation for SMEs in the industrial internet era: faced with a rapidly changing market environment, entrepreneurs put forward the value proposition through the insight of the market environment, then enterprises conduct technological innovation to support the value creation by their own unique experience and knowledge, and then improve the legitimacy of the market by expanding the influence of market acceptance of the new business model to promote the value delivery, and finally capture the economic value and ecological value.

The types and logic of business model innovation proposed in this paper contribute to supplementing and developing the theory of business model innovation and meanwhile have important reference value for SMEs in the industrial internet era.

This paper aims to regulate the oil retention rate and tribological properties of pored polytetrafluoroethylene (PPTFE) using polyvinyl alcohol (PVA)-based oil gel.

PPTFE was first prepared by using citric acid (CA) as an efficient pore-making agent. Subsequently, PVA and chitosan solution was introduced into the pores and experienced a freezing-thawing process, forming PVA-based gels inside the pores. Then, the PPTFE/PVA composite was impregnated with polyethylene glycol 200 (PEG200), yielding an oil-impregnated PPTFE/PVA/PEG200 composite.

It was found that the oil-impregnated PPTFE/PVA/PEG200 composite exhibited advanced tribological properties than neat PTFE with reductions of 53% and 70% in coefficient of friction and wear rate, respectively.

This study shows an efficient strategy to regulate the tribological property of PTFE using a PVA-based oil-containing gel.

The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-11-2024-0432/

The assessment of risk to existing tunnels within the context of pit construction is influenced by a multitude of factors. The conventional fuzzy analytic hierarchy process (FAHP) method may lack precision due to its inability to incorporate the inherent randomness associated with numerous risk factors. To enhance the precision of risk evaluation for existing tunnels, this research introduces an improved FAHP approach grounded in cloud modeling theory.

We developed a risk assessment index system for existing tunnels, categorizing risk sources into three areas: hydrogeological conditions, foundation pit construction and tunnel structural bearing capacity. The system includes 11 evaluation indicators linked to these sources, with defined risk level thresholds for each. Using the cloud model, we calculated the membership degree of these indicators to risk levels, replacing traditional membership function formulas. The cloud model’s three digital characteristics (Ex, En and He) account for the randomness and ambiguity between qualitative descriptions and quantitative values, enhancing assessment accuracy. We applied hierarchical analysis to determine the weights of each risk factor and combined these with the membership degrees to evaluate overall risk levels. Engineering applications and model comparisons confirmed the method’s reliability, while sensitivity analysis identified key risk indicators affecting evaluation outcomes, allowing for targeted risk control measures to safeguard existing tunnels during foundation pit construction.

The evaluation results of engineering applications show the same results with the traditional FAHP method, which proves the reliability of the improved method. Furthermore, when comparing the evaluation result vectors between the two methods, it is observed that the outcomes of the improved method are more concentrated on a specific risk level compared to the traditional FAHP. This concentration mitigates the potential for bias in the evaluation results, thereby enhancing their accuracy. Through sensitivity analysis, four indicators were identified to have a significant influence on the evaluation result. After implementing targeted risk control measures, a downgrade in risk level to III was revealed. This aligns with the actual construction circumstances, as no safety incidents occurred in the Line 1 metro tunnel throughout the duration of the pit construction. This confirms the efficacy of the measures taken based on the evaluation results.

The novelty of this study is demonstrated through two key advancements. First, in response to the lack of a mature evaluation index system for risk assessment of existing tunnels during pit construction, the authors have meticulously curated a comprehensive risk evaluation index system. This system provides a valuable reference for the selection of appropriate risk evaluation indices in similar projects. Second, building upon the established index system, the study introduces a cloud model FAHP risk evaluation method. This method automates the generation of the membership degree between indicators and risk levels. The improved method has good reliability for the risk evaluation of existing tunnels, and it can provide decision-making reference for related studies when they carry out risk evaluations of similar projects.