Tiong Yew Tang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Tiong Yew Tang has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Ha Jin Hwang
School of Creative Industries, Astana IT University, Astana, Kazakhstan
2 shared publications - Muaadh Mukred
Faculty of Information Science and Technology, Universiti Kebangsaan Malaysia, Bangi, Malaysia
2 shared publications Narishah Mohamed Salleh
Department of Business Analytics, Sunway Business School, Sunway University, Bandar Sunway, Selangor, Malaysia
2 shared publications- Narishah Mohamed Salleh
Sunway University
2 shared publications Agamutu Pariatamby
Sunway University
1 shared publicationAmran Ahmad
School of Computing, Universiti Utara Malaysia (UUM),Sintok, Kedah,Malaysia,06010
1 shared publication
Latest Publications
- Open Access
- 6 January 2026
- Published by SAGE Publications in International Journal of Engineering Business Management
- Vol. 18
How urgent environmental challenges and tech advancements reshape commercial food systems: A bibliometric analysis leveraging natural-language processing
With the urgent call for sustainability and the rapid advancement of information technology, especially machine learning and artificial intelligence, the food industry faces unparalleled opportunities and challenges in optimizing resources and enhancing performance. By that call, we foresee a massive change, especially to the way research has been traditionally conducted, it is hypothesized for a surge of research and increasing adoption of innovative tools such as deep learning (DL) and optimization techniques by the research community and the field to address critical challenges in food systems. This study investigates the intersection of commercial, sustainability, and technology domains through advanced bibliometric analysis enhanced by deep document clustering, aims to uncover the multifaceted nature of these interconnected fields, addressing how emerging technologies and sustainability practices shape commercial strategies in the field, providing a panoramic perspective for reader about the dynamic development of the field. Utilizing a multi-tiered literature search strategy and employing deep document clustering techniques, the analysis reveals distinct thematic clusters—ranging from macroeconomic demand challenges to technical advancements in AI-driven agricultural practices and sustainable supply chain management—that underscore the deep connections among commercial, sustainability, and technological domains. The results not only validate the hypothesis of increasing convergence among these fields but also highlight the critical role of advanced methodologies in uncovering latent patterns and facilitating strategic and operational improvements. Moreover, the findings demonstrate that deep document clustering is a powerful tool for bibliometric analysis, offering nuanced insights that can be further refined in future studies. Overall, this research contributes to a holistic understanding of the field, emphasizing the need for continued interdisciplinary collaboration and innovation to drive sustainable development in a global business environment.
- 6 January 2026
- Published by SAGE Publications in International Journal of Engineering Business Management
- Vol. 18
Open AccessHow urgent environmental challenges and tech advancements reshape commercial food systems: A bibliometric analysis leveraging natural-language processing
With the urgent call for sustainability and the rapid advancement of information technology, especially machine learning and artificial intelligence, the food industry faces unparalleled opportunities and challenges in optimizing resources and enhancing performance. By that call, we foresee a massive change, especially to the way research has been traditionally conducted, it is hypothesized for a surge of research and increasing adoption of innovative tools such as deep learning (DL) and optimization techniques by the research community and the field to address critical challenges in food systems. This study investigates the intersection of commercial, sustainability, and technology domains through advanced bibliometric analysis enhanced by deep document clustering, aims to uncover the multifaceted nature of these interconnected fields, addressing how emerging technologies and sustainability practices shape commercial strategies in the field, providing a panoramic perspective for reader about the dynamic development of the field. Utilizing a multi-tiered literature search strategy and employing deep document clustering techniques, the analysis reveals distinct thematic clusters—ranging from macroeconomic demand challenges to technical advancements in AI-driven agricultural practices and sustainable supply chain management—that underscore the deep connections among commercial, sustainability, and technological domains. The results not only validate the hypothesis of increasing convergence among these fields but also highlight the critical role of advanced methodologies in uncovering latent patterns and facilitating strategic and operational improvements. Moreover, the findings demonstrate that deep document clustering is a powerful tool for bibliometric analysis, offering nuanced insights that can be further refined in future studies. Overall, this research contributes to a holistic understanding of the field, emphasizing the need for continued interdisciplinary collaboration and innovation to drive sustainable development in a global business environment.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Leveraging AI-Driven Topic Modeling for Business Analytics: A Bibliometric Analysis of Trends in Antidepressant Efficacy
To uncover thematic trends and patterns through studying articles from 2000 to 2023, this study conducts a bibliometric analysis of research on the efficacy of antidepressants, applying Latent Dirichlet Allocation (LDA). Drawing on data from Scopus, the analysis covers 494 records, shedding light on prominent topics, key studies, and emerging areas in the field. The results indicate a significant rise in research activity, especially around 2010 and after 2018, pointing to an increasing focus on the effectiveness of mental health treatments. The thematic analysis revealed five core areas: treatment efficacy, clinical trials, alternative treatment approaches, efficacy compared to side effects, and outcomes centered on patient experience. These findings underscore critical advances and existing gaps in the research, offering direction for future studies and clinical applications. This work demonstrates how integrating bibliometric methods, and LDA can deepen our understanding and support better decision-making in mental healthcare.
- 6 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Leveraging AI-Driven Topic Modeling for Business Analytics: A Bibliometric Analysis of Trends in Antidepressant Efficacy
To uncover thematic trends and patterns through studying articles from 2000 to 2023, this study conducts a bibliometric analysis of research on the efficacy of antidepressants, applying Latent Dirichlet Allocation (LDA). Drawing on data from Scopus, the analysis covers 494 records, shedding light on prominent topics, key studies, and emerging areas in the field. The results indicate a significant rise in research activity, especially around 2010 and after 2018, pointing to an increasing focus on the effectiveness of mental health treatments. The thematic analysis revealed five core areas: treatment efficacy, clinical trials, alternative treatment approaches, efficacy compared to side effects, and outcomes centered on patient experience. These findings underscore critical advances and existing gaps in the research, offering direction for future studies and clinical applications. This work demonstrates how integrating bibliometric methods, and LDA can deepen our understanding and support better decision-making in mental healthcare.
- Open Access
- 11 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 57326-57344
Data Augmentation With Semantic Enrichment for Deep Learning Invoice Text Classification
Natural language processing (NLP) is a research field that provides huge potential to automate accounting tasks dealing with text data. This research studies the application of NLP in automatically categorizing invoices based on the invoice text description. The study employs semantic enrichment, data augmentation, and deep learning to address the NLP unique issues posed by the inherent short text and multi-class imbalance nature of invoice descriptions. Semantic enrichment was done using labels as an information source. Training data was artificially increased with either WordNet synonym replacement, Global Vectors for Word Representation (GloVe) word replacement, or the Bidirectional Encoder Representations from Transformers (BERT) word replacement method. Each training dataset was then supplied for training with one nondeep learning classifier and two deep learning classifiers respectively, namely Linear Support Vector Machine (LSVM), Bidirectional Long Short-Term Memory (Bi-LSTM), and BERT. Overall, the semantically enriched, WordNet augmented training set paired with the BERT classifier yielded the best results, successfully preserving semantics, reducing noise and overfitting while improving accuracy per class, achieving an increase of performance up to 20 percentage points (ppts) for macro F1 score and 6.7 ppts for accuracy.
- 11 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 57326-57344
Open AccessData Augmentation With Semantic Enrichment for Deep Learning Invoice Text Classification
Natural language processing (NLP) is a research field that provides huge potential to automate accounting tasks dealing with text data. This research studies the application of NLP in automatically categorizing invoices based on the invoice text description. The study employs semantic enrichment, data augmentation, and deep learning to address the NLP unique issues posed by the inherent short text and multi-class imbalance nature of invoice descriptions. Semantic enrichment was done using labels as an information source. Training data was artificially increased with either WordNet synonym replacement, Global Vectors for Word Representation (GloVe) word replacement, or the Bidirectional Encoder Representations from Transformers (BERT) word replacement method. Each training dataset was then supplied for training with one nondeep learning classifier and two deep learning classifiers respectively, namely Linear Support Vector Machine (LSVM), Bidirectional Long Short-Term Memory (Bi-LSTM), and BERT. Overall, the semantically enriched, WordNet augmented training set paired with the BERT classifier yielded the best results, successfully preserving semantics, reducing noise and overfitting while improving accuracy per class, achieving an increase of performance up to 20 percentage points (ppts) for macro F1 score and 6.7 ppts for accuracy.
- 20 October 2023
- Published by Springer Nature
- p. 40-51
Deep Learning and Sentiment Analysis-Based Cryptocurrency Price Prediction
- 20 October 2023
- Published by Springer Nature
- p. 40-51
Deep Learning and Sentiment Analysis-Based Cryptocurrency Price Prediction
- 30 June 2023
- Published by Springer Nature
- p. 489-506
Bibliometric Analysis of Robotic Process Automation Domain: Key Topics, Challenges and Solutions
- 30 June 2023
- Published by Springer Nature
- p. 489-506
Bibliometric Analysis of Robotic Process Automation Domain: Key Topics, Challenges and Solutions