Sentiment Analysis on Movie Reviews: A Deep Dive into Modern Techniques and Open Challenges

2026-01-12

AI Summary

This study addresses the persistent challenges in sentiment analysis of movie reviews—such as sarcasm, negation, contextual ambiguity, and domain shift—by offering a systematic, challenge-driven review that bridges critical gaps in existing literature. Moving beyond fragmented accounts, it traces the methodological evolution from lexicon-based approaches and traditional machine learning to deep learning and large language models. For the first time, it integrates emerging frontiers including multimodal fusion, zero- and few-shot learning, and neuro-symbolic hybrid architectures, thereby transcending the limitations of unimodal surveys. Through comprehensive benchmarking across mainstream datasets, the work delineates the performance boundaries of diverse modeling paradigms, constructs a domain-focused research roadmap, identifies key open problems, and provides a theoretical foundation for developing more accurate, generalizable, and interpretable sentiment analysis systems.

Technology Category

Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument MiningMachine Learning: Transfer, Domain Adaptation, Multi-Task LearningCognitive Modeling & Cognitive Systems: Affective Computing

Application Category

Web Mining and Content Analysis: Sentiment analysis and opinion miningSearch and Retrieval-Augmented AI: Web evaluation methodologies and metricsSocial Networks and Social Media: Fairness and bias in social network and social media analysis

Abstract

This paper presents a comprehensive survey of sentiment analysis methods for movie reviews, a benchmark task that has played a central role in advancing natural language processing. We review the evolution of techniques from early lexicon-based and classical machine learning approaches to modern deep learning architectures and large language models, covering widely used datasets such as IMDb, Rotten Tomatoes, and SST-2, and models ranging from Naive Bayes and support vector machines to LSTM networks, BERT, and attention-based transformers. Beyond summarizing prior work, this survey differentiates itself by offering a comparative, challenge-driven analysis of how these modeling paradigms address domain-specific issues such as sarcasm, negation, contextual ambiguity, and domain shift, which remain open problems in existing literature. Unlike earlier reviews that focus primarily on text-only pipelines, we also synthesize recent advances in multimodal sentiment analysis that integrate textual, audio, and visual cues from movie trailers and clips. In addition, we examine emerging concerns related to interpretability, fairness, and robustness that are often underexplored in prior surveys, and we outline future research directions including zero-shot and few-shot learning, hybrid symbolic--neural models, and real-time deployment considerations. Overall, this abstract provides a domain-focused roadmap that highlights both established solutions and unresolved challenges toward building more accurate, generalizable, and explainable sentiment analysis systems for movie review data.

Problem

• sentiment analysis
• sarcasm
• domain shift
• multimodal fusion
• interpretability

Innovation

• multimodal sentiment analysis
• challenge-driven evaluation
• interpretability
• domain shift
• hybrid symbolic-neural models