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.

The increasing popularity of music streaming services also increases the need to customize the services for each user to attract and retain customers. Most of the music streaming services will not have explicit ratings for songs; they will have only implicit feedback data, i.e user listening history. For efficient music recommendation, the preferences of the users have to be infered, which is a challenging task.

Preferences of the users can be identified from the users' listening history. In this paper, a hybrid music recommendation system is proposed that infers features from user's implicit feedback and uses the hybrid of content-based and collaborative filtering method to recommend songs. A Content Boosted K-Nearest Neighbours (CBKNN) filtering technique was proposed, which used the users' listening history, popularity of songs, song features, and songs of similar interested users for recommending songs. The song features are taken as content features. Song Frequency–Inverse Popularity Frequency (SF-IPF) metric is proposed to find the similarity among the neighbours in collaborative filtering. Million Song Dataset and Echo Nest Taste Profile Subset are used as data sets.

The proposed CBKNN technique with SF-IPF similarity measure to identify similar interest neighbours performs better than other machine learning techniques like linear regression, decision trees, random forest, support vector machines, XGboost and Adaboost. The performance of proposed SF-IPF was tested with other similarity metrics like Pearson and Cosine similarity measures, in which SF-IPF results in better performance.

This method was devised to infer the user preferences from the implicit feedback data and it is converted as rating preferences. The importance of adding content features with collaborative information is analysed in hybrid filtering. A new similarity metric SF-IPF is formulated to identify the similarity between the users in collaborative filtering.

Researcher agreed that job performance has a positive effect on productivity as well as an organisation’s efficiency. Thus, this study aims to investigate the impact of mindfulness skill, inclusive leadership (IL), employee work engagement and self-compassion on the overall job performance of secondary school teachers in Hong Kong. It then evaluates the mediating effect of employee work engagement between the relationships of mindfulness skill, IL and job performance, as well as the moderate effect of self-compassion between the relationships of mindfulness skill, IL and employee work engagement.

The sample comprised 263 teachers working from three secondary schools in Sha Tin, Hong Kong. The data was then analysed using Smart PLS version 4.0.9.

The results showed significant positive relationships between mindfulness skill and IL towards employee work engagement and between employee work engagement and job performance; meanwhile, there emerged a significant effect on the relationship between mindfulness skill and IL towards job performance. Furthermore, this research has confirmed that self-compassion did not moderate the relationship between mindfulness skill, IL and employee work engagement, but employee work engagement plays a mediating effect on the relationship between mindfulness skill, IL and job performance.

This research has helped to fill the literature gap by examining the mediating roles of employee work engagement and mediator role of self-compassion in the integrated relationship of multi-factor and job performance. Examining the mediating role of employee work engagement has helped to enhance the understanding of the underlying principle of the indirect influence of mindfulness skill, IL and job performance. The result of this research shows that self-compassion plays a vital role in influencing the employees’ work engagement. Hence, it is important that companies design human resource management policy that enables self-compassion to be used as a consideration psychological-related strategy when structing organisation or teams. It is also crucial for top management and policymakers to define and communicate the organisation’s operating principle, value and goals.

This study aims to extend the literature on psychological contracts, employee mental health, self-control and equity sensitivity among employees in Ghana.

Data for this study came from a sample of 484 employees from an organisation in the telecommunication sector of Ghana. The details of the study were discussed with employees after which they were given the choice to participate in the study.

The present study found that psychological contract breach is directly associated with mental health and indirectly related to mental health through equity sensitivity and self-control.

The findings suggest that psychological contracts are important aspects of the employment relationship that could be used to enhance employee mental health. Furthermore, enhancing employees’ self-control and resolving issues of individuals high on equity sensitivity are effective ways that organisations can deploy to sustain mental health in the face of psychological contract breaches.

The consequences of corporate corruption control (CCC) have either been investigated outside the firm (e.g. foreign direct investment inflows) or inside the firm (e.g. profitability). Yet prior research addresses these implications separately, treating them as distinct phenomena, ignoring questions at their intersection. However, corruption control can be leveraged to benefit both organizations (internally) and environments (externally). In line with open systems theory, this study aims to explore a ripple effect of corruption control not only inside organizations (efficiency through adoption of sustainable resource management practices) but also outside [community-centered corporate social performance (CSP)].

Using a longitudinal sample of multinational enterprises from Forbes list of “The World’s Largest Public Companies,” the authors use a cross-lagged panel design to provide clarity regarding causal effects.

Results confirm causal directionality and support the positive effect of corruption control on resource management and community CSP, contributing toward understanding implications at the organization–environment interface.

The authors examine both internal and external implications of CCC. The use of a cross-lagged design that is relatively novel to the management field allows to check for casual effects between CSP elements that were previously assumed to have reciprocal casual effects.