MindRon: An AI-Driven NLP Framework for Story Analysis, Summarization, and Emotion Recognition

MindRon is an advanced Natural Language Processing (NLP) system designed for automated story classification, summarization, and emotion recognition. This research integrates multiple transformer-based models to enhance text analysis and provide comparative insights into their performance. The system utilizes DeBERTa for genre classification, Pegasus for abstractive text summarization, and DistilBERT for sentiment analysis. The datasets used include BookCorpus, GoEmotions, and various open-source short stories. Text preprocessing techniques like tokenization, stopword removal, and vectorization are applied to improve input quality. MindRon is evaluated against SciBERT and RoBERTa to benchmark its efficiency and accuracy, with performance assessed using accuracy, precision, recall, F1-score, ROUGE, BLEU. Experimental results demonstrate that MindRon effectively classifies stories, generates coherent summaries, and accurately detects emotions in textual data, outperforming traditional NLP methods and showing competitive results against other transformer models. The system offers a scalable NLP framework suitable for content moderation, automated storytelling, and digital media analytics. Future enhancements will focus on optimizing computational efficiency, incorporating multilingual capabilities, and improving model explainability for better interpretability.