Emojis serve as an established means for people to express emotions and sentiments while interacting on social media. This paper examines the task of emoji prediction from text by developing accurate classification methods. The model uses a pre-trained and fine-tuned BERT framework on a dataset consisting of text sentences along with their corresponding emojis. This structured data allows the model to capture contextual meaning and emotional nuances, which are crucial for practical applications. Challenges associated with emoji usage are addressed through tokenization techniques in text preprocessing, while performance advances are achieved using stemming and feature extraction. Research conclusions indicate that the BERT-based model outperforms traditional deep learning approaches like LSTM. This study spotlights how NLP and sentiment analysis contribute to emoji prediction and shows its practical applications in social media monitoring, sentiment analysis, and enhancing user experiences.