Scholarlink

<p>Sarcasm detection is a subset of sentiment analysis and poses significant challenges due to its inherent linguistic complexity and the contextual subtleties required for accurate interpretation. In this paper, we present a comprehensive survey of the current state of sarcasm detection, covering models from traditional machine learning to large language models. Our review examines primary datasets and corpora used for training and evaluation, evaluates the effectiveness of existing sentiment analysis techniques, and highlights predominant methodologies. Additionally, we discuss the challenges and limitations facing sarcasm detection, including issues related to linguistic complexity and contextual interpretation. We compared all datasets, and how they impact the model performance and generalizability, assess the ability of sentiment analysis techniques to capture sarcasm and irony, and explore the strengths and limitations of leading methodologies. By exploring current limitations, including cross-cultural variances and the adaptability of deep learning models, this survey underscores ongoing challenges and highlights future directions in AI-driven sarcasm detection research.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Transformer-based advances in sarcasm detection: a study of contextual models and methodologies

  • 期刊论文

  • 发表日期：

    2025年5月28日

查看全文
  • Ramakrishna Bodige,
  • Rameshbabu Akarapu,
  • Pramod Kumar Poladi

摘要

Sarcasm detection is a subset of sentiment analysis and poses significant challenges due to its inherent linguistic complexity and the contextual subtleties required for accurate interpretation. In this paper, we present a comprehensive survey of the current state of sarcasm detection, covering models from traditional machine learning to large language models. Our review examines primary datasets and corpora used for training and evaluation, evaluates the effectiveness of existing sentiment analysis techniques, and highlights predominant methodologies. Additionally, we discuss the challenges and limitations facing sarcasm detection, including issues related to linguistic complexity and contextual interpretation. We compared all datasets, and how they impact the model performance and generalizability, assess the ability of sentiment analysis techniques to capture sarcasm and irony, and explore the strengths and limitations of leading methodologies. By exploring current limitations, including cross-cultural variances and the adaptability of deep learning models, this survey underscores ongoing challenges and highlights future directions in AI-driven sarcasm detection research.