Sangwoo Kang

Dr. Sangwoo Kang

Gachon University, Seongnam-si, Republic of Korea
orcid

Research Focus & Metrics

Academic Career Length

13Years (2014-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 February 2024 in Applied Sciences
Verified
Journal Article
Open access
PDF file
LLaith H. Baniata
Laith H. Baniata
Sangwoo KangSangwoo Kang
Sangwoo Kang
MAMohammad Alsharaiah
Mohammad Alsharaiah
Mohammad BaniataMohammad Baniata
Mohammad Baniata
Educational institutions are increasingly focused on supporting students who may be facing academic challenges, aiming to enhance their educational outcomes through targeted interventions. Within this framework, leveraging advanced deep learning techniques to develop recommendation systems becomes essential. These systems are designed to identify students at risk of underperforming by analyzing patterns in their historical academic data, thereby facilitating personalized support strategies. This research introduces an innovative deep learning model tailored for pinpointing students in need of academic assistance. Utilizing a Gated Recurrent Neural Network (GRU) architecture, the model is rich with features such as a dense layer, max-pooling layer, and the ADAM optimization method used to optimize performance. The effectiveness of this model was tested using a comprehensive dataset containing 15,165 records of student assessments collected across several academic institutions. A comparative analysis with existing educational recommendation models, like Recurrent Neural Network (RNN), AdaBoost, and Artificial Immune Recognition System v2, highlights the superior accuracy of the proposed GRU model, which achieved an impressive overall accuracy of 99.70%. This breakthrough underscores the model’s potential in aiding educational institutions to proactively support students, thereby mitigating the risks of underachievement and dropout.

6 October 2022 in Mathematics
Verified
Journal Article
Open access
PDF file
LLaith H. Baniata
Laith H. Baniata
Sangwoo KangSangwoo Kang
Sangwoo Kang
IAIsaac. K. E. Ampomah
Isaac. K. E. Ampomah
Languages with a grammatical structure that have a free order for words, such as Arabic dialects, are considered a challenge for neural machine translation (NMT) models because of the attached suffixes, affixes, and out-of-vocabulary words. This paper presents a new reverse positional encoding mechanism for a multi-head attention (MHA) neural machine translation (MT) model to translate from right-to-left texts such as Arabic dialects (ADs) to modern standard Arabic (MSA). The proposed model depends on an MHA mechanism that has been suggested recently. The utilization of the new reverse positional encoding (RPE) mechanism and the use of sub-word units as an input to the self-attention layer improve this sublayer for the proposed model’s encoder by capturing all dependencies between the words in right-to-left texts, such as AD input sentences. Experiments were conducted on Maghrebi Arabic to MSA, Levantine Arabic to MSA, Nile Basin Arabic to MSA, Gulf Arabic to MSA, and Iraqi Arabic to MSA. Experimental analysis proved that the proposed reverse positional encoding MHA NMT model was efficiently able to handle the open grammatical structure issue of Arabic dialect sentences, and the proposed RPE MHA NMT model enhanced the translation quality for right-to-left texts such as Arabic dialects.

25 November 2024 in Mathematics
Verified
Journal Article
Open access
PDF file
FFFatema Tuj Johora Faria
Fatema Tuj Johora Faria
LLaith H. Baniata
Laith H. Baniata
Sangwoo KangSangwoo Kang
Sangwoo Kang
The rise in abusive language on social media is a significant threat to mental health and social cohesion. For Bengali speakers, the need for effective detection is critical. However, current methods fall short in addressing the massive volume of content. Improved techniques are urgently needed to combat online hate speech in Bengali. Traditional machine learning techniques, while useful, often require large, linguistically diverse datasets to train models effectively. This paper addresses the urgent need for improved hate speech detection methods in Bengali, aiming to fill the existing research gap. Contextual understanding is crucial in differentiating between harmful speech and benign expressions. Large language models (LLMs) have shown state-of-the-art performance in various natural language tasks due to their extensive training on vast amounts of data. We explore the application of LLMs, specifically GPT-3.5 Turbo and Gemini 1.5 Pro, for Bengali hate speech detection using Zero-Shot and Few-Shot Learning approaches. Unlike conventional methods, Zero-Shot Learning identifies hate speech without task-specific training data, making it highly adaptable to new datasets and languages. Few-Shot Learning, on the other hand, requires minimal labeled examples, allowing for efficient model training with limited resources. Our experimental results show that LLMs outperform traditional approaches. In this study, we evaluate GPT-3.5 Turbo and Gemini 1.5 Pro on multiple datasets. To further enhance our study, we consider the distribution of comments in different datasets and the challenge of class imbalance, which can affect model performance. The BD-SHS dataset consists of 35,197 comments in the training set, 7542 in the validation set, and 7542 in the test set. The Bengali Hate Speech Dataset v1.0 and v2.0 include comments distributed across various hate categories: personal hate (629), political hate (1771), religious hate (502), geopolitical hate (1179), and gender abusive hate (316). The Bengali Hate Dataset comprises 7500 non-hate and 7500 hate comments. GPT-3.5 Turbo achieved impressive results with 97.33%, 98.42%, and 98.53% accuracy. In contrast, Gemini 1.5 Pro showed lower performance across all datasets. Specifically, GPT-3.5 Turbo excelled with significantly higher accuracy compared to Gemini 1.5 Pro. These outcomes highlight a 6.28% increase in accuracy compared to traditional methods, which achieved 92.25%. Our research contributes to the growing body of literature on LLM applications in natural language processing, particularly in the context of low-resource languages.

28 June 2023 in Mathematics
Verified
Journal Article
Open access
PDF file
EJEunseo Jeong
Eunseo Jeong
GKGyunyeop Kim
Gyunyeop Kim
Sangwoo KangSangwoo Kang
Sangwoo Kang
Prompt learning has improved the performance of language models by reducing the gap in language model training methods of pre-training and downstream tasks. However, extending prompt learning in language models pre-trained with unimodal data to multimodal sources is difficult as it requires additional deep-learning layers that cannot be attached. In the natural-language emotion-recognition task, improved emotional classification can be expected when using audio and text to train a model rather than only natural-language text. Audio information, such as voice pitch, tone, and intonation, can give more information that is unavailable in text to predict emotions more effectively. Thus, using both audio and text can enable better emotion prediction in speech emotion-recognition models compared to semantic information alone. In this paper, in contrast to existing studies that use multimodal data with an additional layer, we propose a method for improving the performance of speech emotion recognition using multimodal prompt learning with text-based pre-trained models. The proposed method is using text and audio information in prompt learning by employing a language model pre-trained on natural-language text. In addition, we propose a method to improve the emotion-recognition performance of the current utterance using the emotion and contextual information of the previous utterances for prompt learning in speech emotion-recognition tasks. The performance of the proposed method was evaluated using the English multimodal dataset MELD and the Korean multimodal dataset KEMDy20. Experiments using both the proposed methods obtained an accuracy of 87.49%, F1 score of 44.16, and weighted F1 score of 86.28.

20 July 2022 in Expert Systems with Applications
Verified
Journal Article
Closed access
JKJuae Kim
Juae Kim
YKYejin Kim
Yejin Kim
Sangwoo KangSangwoo Kang
Sangwoo Kang

18 February 2025 in Electronics
Verified
Journal Article
Open access
PDF file
FFFatema Tuj Johora Faria
Fatema Tuj Johora Faria
LLaith H. Baniata
Laith H. Baniata
Mohammad BaniataMohammad Baniata
Mohammad Baniata
MKMohannad A. Khair
Mohannad A. Khair
ABAhmed Baniata
Ahmed Baniata
Sangwoo KangSangwoo Kang
Sangwoo Kang
Social media has increasingly relied on memes as a tool for expressing opinions, making meme sentiment analysis an emerging area of interest for researchers. While much of the research has focused on English-language memes, under-resourced languages, such as Bengali, have received limited attention. Given the surge in social media use, the need for sentiment analysis of memes in these languages has become critical. One of the primary challenges in this field is the lack of benchmark datasets, particularly in languages with fewer resources. To address this, we used the MemoSen dataset, designed for Bengali, which consists of 4368 memes annotated with three sentiment labels: positive, negative, and neutral. MemoSen is divided into training (70%), test (20%), and validation (10%) sets, with an imbalanced class distribution: 1349 memes in the positive class, 2728 in the negative class, and 291 in the neutral class. Our approach leverages advanced deep learning techniques for multimodal sentiment analysis in Bengali, introducing three hybrid approaches. SentimentTextFormer is a text-based, fine-tuned model that utilizes state-of-the-art transformer architectures to accurately extract sentiment-related insights from Bengali text, capturing nuanced linguistic features. SentimentImageFormer is an image-based model that employs cutting-edge transformer-based techniques for precise sentiment classification through visual data. Lastly, SentimentFormer is a hybrid model that seamlessly integrates both text and image modalities using fusion strategies. Early fusion combines textual and visual features at the input level, enabling the model to jointly learn from both modalities. Late fusion merges the outputs of separate text and image models, preserving their individual strengths for the final prediction. Intermediate fusion integrates textual and visual features at intermediate layers, refining their interactions during processing. These fusion strategies combine the strengths of both textual and visual data, enhancing sentiment analysis by exploiting complementary information from multiple sources. The performance of our models was evaluated using various accuracy metrics, with SentimentTextFormer achieving 73.31% accuracy and SentimentImageFormer attaining 64.72%. The hybrid model, SentimentFormer (SwiftFormer with mBERT), employing intermediate fusion, shows a notable improvement in accuracy, achieving 79.04%, outperforming SentimentTextFormer by 5.73% and SentimentImageFormer by 14.32%. Among the fusion strategies, SentimentFormer (SwiftFormer with mBERT) achieved the highest accuracy of 79.04%, highlighting the effectiveness of our fusion technique and the reliability of our multimodal framework in improving sentiment analysis accuracy across diverse modalities.