Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{197925,
        author = {Prof. S. P. Shintre and Siddhesh Mose and Aditya Patil and Raghav Patil and Shruti Zalpure},
        title = {Hybrid Deep Neural Architecture for Fine-Grained Sentiment and Sarcasm Detection in Movie Reviews},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {11203-11206},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197925},
        abstract = {In the digital era, people express their opinions on movies through online reviews and social media. Analyzing such vast and unstructured data manually is difficult, while traditional sentiment analysis methods fail to capture sarcasm, irony, and aspect-specific sentiments.
This project, “AI-Based Sentiment Analysis for Movie Re- views,” presents a deep learning model using LSTM, Graph Convolutional Networks (GCN), and BERT embeddings to per- form fine-grained, aspect-based sentiment analysis. The system identifies sentiments for specific film attributes such as acting, direction, and music, while also detecting sarcasm for improved accuracy.
An interactive dashboard visualizes results and trends, enabling filmmakers and marketers to understand audience perceptions more effectively. With cloud integration and strong accuracy, the system transforms movie reviews into actionable insights, bridging the gap between audience emotion and data- driven decision-making.
Index Terms - Sentiment Analysis, Aspect-Based Sentiment Analysis (ABSA), Deep Learning, Natural Language Processing (NLP), Movie Reviews, LSTM, Graph Convolutional Networks (GCN), BERT, Sarcasm Detection, Opinion Mining, Artificial Intelligence (AI), Text Analytics.},
        keywords = {component, formatting, style, styling, insert},
        month = {April},
        }