A Survey of Sarcasm Detection Techniques in Natural Language Processing

Singh, Bhuvanesh; Sharma, Dilip Kumar

doi:10.1109/iscon57294.2023.10112176

Cited by 2 publications

(1 citation statement)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, comparing the results of deep learning and machine learning, it can be found that the deep learning-based model is better at detecting sarcasm in the data set. This is because by learning different levels of abstraction, a deep learning model can simulate higher-level features and capture more complex relationships between modeling inputs and outputs [19]. Moreover, from the difference between the two mentioned above, with the expansion of the amount of data in the future, deep learning will be more adaptable, so deep learning models will be more favored by researchers.…”

Section: The Difference Between the Machine Learning And The Deep Lea...mentioning

confidence: 99%

Sarcasm detection methods based on machine learning and deep learning

Zhang

2024

ACE

View full text Add to dashboard Cite

Sarcasm is an expression of emotion, which often expresses criticism and disgust in a positive tone, and we see it everywhere on social networking platforms. Because of this nature, sarcasm can be challenging to process in Natural Language Processing (NLP) Systems. Failing to detect sarcasm correctly can negatively affect the results of natural language processing tasks such as text correct and sentiment analysis. In recent years, there are more and more studies on sarcasm detection, and the research methods are diverse. According to the survey, the methods based on machine learning (ML) and deep learning (DL) account for the majority. Therefore, this paper mainly summarizes the literature on sarcasm detection based on ML and DL methods in recent years. This paper first introduces the application of sarcasm, then expounds the general architecture of sarcasm detection and makes a distinction between machine learning and deep learning. Then the author investigates the relevant literature and compares the results. Finally, the challenges and research directions in this field are summarized. The purpose of this paper is to facilitate the follow-up research of sarcasm detection.

show abstract

Section: The Difference Between the Machine Learning And The Deep Lea...mentioning

confidence: 99%