A Survey on Detection of Deepfake Text and Sentiment Analysis using Machine Learning Models

Citations Over TimeTop 1% of 2025 papers

Abstract

With its rapid evolution, deepfake technology also raises the risk of manipulating content written, especially in journalism, social media, and cyber security. This review chapter pivots and concentrated on detecting deepfake text using machine learning-based models, and specifically on sentiment analysis for detecting emotional manipulation and intent from contrived content. We dig into the ways of deepfake text generation as well as sentiment driven detection techniques, notably how neural language models trained on such vast datasets generate something to provoke targeted emotional reactions. Several methodologies, namely sentiment driven statistical analysis, sentiment aware linguistics evaluation and machine learning algorithms that are trained to identify deepfake text and emotion manipulation content are also discussed. Emotional bias found in synthetic text is investigated through existing sentiment analysis methodologies to determine emotional tone, polarity, and subjective intent in content targeted to elicit emotional, rather than logical, responses from consumers and promote fraudulent behavior. The study surfaces challenges in constructing a robust detection system to analyze both textual accuracy and sentiment in the underlay, highlighting the lack of labeled datasets and the adversaries’ ability to adapt emotionally charged content to evade detection. The combination of sentiment analysis and deepfake detection in the domains of natural language processing (NLP), cyber security, and ethics are highlighted through this review, as both textual and emotional manipulations need to be detected in fighting misinformation.

Related Papers

• → Physician-Friendly Machine Learning: A Case Study with Cardiovascular Disease Risk Prediction(2019)71 cited
• → Application of Machine Learning in Animal Disease Analysis and Prediction(2020)26 cited
• → Interpretable machine learning assessment(2023)24 cited
• → Breakdown of Machine Learning Algorithms(2022)1 cited
• → Machine Learning Techniques for the Management of Diseases: A Paper Review(2024)