TEXT CLASSIFICATION USING BERT

TEXT CLASSIFICATION USING BERT

Gokul K,  Milind Krishna,  Gayathri N

1Student, Department of Artificial Intelligence and Machine Learning

2 Student, Department of Artificial Intelligence and Machine Learning

3Supervisor, Department of Artificial Intelligence and Machine Learning

---------------------------------------------------------------------***---------------------------------------------------------------------

Abstract - Text classification, a fundamental task in natural language processing (NLP), involves automatically assigning predefined categories or labels to textual data. It finds applications in various domains such as sentiment analysis, topic categorization, spam detection, and customer support ticket routing. Traditional methods include algorithms such as support vector machines (SVM), naive Bayes, and decision trees, which rely on handcrafted features and shallow learning architectures. In contrast, deep learning models, particularly transformer-based architectures like BERT (Bidirectional Encoder Representations from Transformers), have shown remarkable performance by capturing intricate linguistic patterns and contextual information from text data. The paper discusses the data preprocessing steps, feature engineering techniques, model architectures, and evaluation metrics commonly used in text classification. Furthermore, it highlights the challenges and considerations in deploying text classification models in real-world applications, such as scalability, interpretability, and model drift. By providing insights into the latest advancements and best practices in text classification, this paper aims to serve as a valuable resource for researchers, practitioners, and enthusiasts in the field of NLP and machine learning.