TY  - JOUR
AU  - Saeed, Muhammad
AU  - Ahmed, Naeem
AU  - Ali, Danish
AU  - Ramzan, Muhammad
AU  - Mohib, Muzamil
AU  - Bagga, Kajol
AU  - Rahman, Atif Ur
AU  - Khan, Ikram Majeed
PY  - 2024
DA  - 2024/11/09
TI  - In-depth Urdu Sentiment Analysis Through Multilingual BERT and Supervised Learning Approaches
JO  - ICCK Transactions on Intelligent Systematics
T2  - ICCK Transactions on Intelligent Systematics
JF  - ICCK Transactions on Intelligent Systematics
VL  - 1
IS  - 3
SP  - 161
EP  - 175
DO  - 10.62762/TIS.2024.585616
UR  - https://www.icck.org/article/abs/TIS.2024.585616
KW  - machine learning
KW  - sentiment analysis
KW  - Urdu language
KW  - natural language processing (NLP)
KW  - intelligent systems
AB  - Sentiment analysis is a crucial component of intelligent information processing systems, enabling machines to understand and categorize human opinions expressed in text. While extensively studied for high-resource languages such as English and Chinese, it remains underexplored for low-resource languages like Urdu. This paper presents an intelligent multilingual sentiment analysis framework for Urdu text by integrating supervised machine learning techniques with a transformer-based model. We manually annotated and preprocessed a dataset collected from various Urdu blog websites, categorizing sentiments into positive, neutral, and negative classes. Four machine learning classifiers—Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naive Bayes, and Multinomial Logistic Regression (MLR)—along with the transformer-based multilingual BERT (mBERT) model were systematically evaluated. The mBERT model was fine-tuned to capture deep contextual embeddings tailored for Urdu, leveraging transfer learning from a model pre-trained on 104 languages. Experimental results demonstrate that the proposed intelligent framework significantly outperforms traditional classifiers, achieving an accuracy of 96.5% on the test set. This study highlights the effectiveness of transfer learning and deep contextual models in building robust intelligent systems for low-resource language processing, contributing to the advancement of inclusive and systematic intelligence in natural language understanding.
SN  - 3068-5079
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  - 

@article{Saeed2024Indepth,
  author = {Muhammad Saeed and Naeem Ahmed and Danish Ali and Muhammad Ramzan and Muzamil Mohib and Kajol Bagga and Atif Ur Rahman and Ikram Majeed Khan},
  title = {In-depth Urdu Sentiment Analysis Through Multilingual BERT and Supervised Learning Approaches},
  journal = {ICCK Transactions on Intelligent Systematics},
  year = {2024},
  volume = {1},
  number = {3},
  pages = {161-175},
  doi = {10.62762/TIS.2024.585616},
  url = {https://www.icck.org/article/abs/TIS.2024.585616},
  abstract = {Sentiment analysis is a crucial component of intelligent information processing systems, enabling machines to understand and categorize human opinions expressed in text. While extensively studied for high-resource languages such as English and Chinese, it remains underexplored for low-resource languages like Urdu. This paper presents an intelligent multilingual sentiment analysis framework for Urdu text by integrating supervised machine learning techniques with a transformer-based model. We manually annotated and preprocessed a dataset collected from various Urdu blog websites, categorizing sentiments into positive, neutral, and negative classes. Four machine learning classifiers—Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Naive Bayes, and Multinomial Logistic Regression (MLR)—along with the transformer-based multilingual BERT (mBERT) model were systematically evaluated. The mBERT model was fine-tuned to capture deep contextual embeddings tailored for Urdu, leveraging transfer learning from a model pre-trained on 104 languages. Experimental results demonstrate that the proposed intelligent framework significantly outperforms traditional classifiers, achieving an accuracy of 96.5\% on the test set. This study highlights the effectiveness of transfer learning and deep contextual models in building robust intelligent systems for low-resource language processing, contributing to the advancement of inclusive and systematic intelligence in natural language understanding.},
  keywords = {machine learning, sentiment analysis, Urdu language, natural language processing (NLP), intelligent systems},
  issn = {3068-5079},
  publisher = {Institute of Central Computation and Knowledge}
}