Sarcasm detection of tweets without #sarcasm: data science approach

Abstract

Identifying sarcasm present in the text could be a challenging work. In sarcasm, a negative word can flip the polarity of a positive sentence. Sentences can be classified as sarcastic or non-sarcastic. It is easier to identify sarcasm using facial expression or tonal weight rather detecting from plain text. Thus, sarcasm detection using natural language processing is major challenge without giving away any specific context or clue such as #sarcasm present in a tweet. Therefore, research tries to solve this classification problem using various optimized models. Proposed model, analyzes whether a given tweet, is sarcastic or not without the presnece of hashtag sarcasm or any kind of specific context present in text. To achieve better results, we used different machine learning classification methodology along with deep learning embedding techniques. Our optimized model uses a stacking technique which combines the result of logistic regression and long short-term memory (LSTM) recurrent neural net feed to light gradient boosting technique which generates better result as compare to existing machine learning and neural network algorithm. The key difference of our research work is sarcasm detection done without #sarcasm which has not been much explored earlier by any researcher. The metrics used for evolutionis F1-score and confusion matrix.

Sarcasm Text Detection on News Headlines Using Novel Hybrid Machine Learning Techniques

“…It is a method of implementing gradient-boosting engines. Other gradient-boosting methods cannot match XGBoost's speed or accuracy (Bagate & Suguna, 2021). It is one of the ensemble strategies that makes use of the second partial differential equation of the error function, which provides more details about the gradient's direction and how to minimize it.…”

Evaluation of Different Stemming Techniques on Arabic Customer Reviews

“…Globally, there are approximately 4 billion internet users and applications; in the Middle East, the number of users has grown from 147 million to 164 million during the previous few years [2]. With the increasing number of social media users sharing their opinions or leaving reviews or feedback about particular services or products [3], it is no secret to anyone today the role played by reviews, opinions or feedback on various things, whether they are comments on social media or user-written reviews about a particular service or product [4,5]. Since the Arabic language is an official language in 22 countries around the world [6][7][8], it is also the 4th most used language on the Internet.…”

Masked Statement Classification in Conversational Text

“…In the early days of detecting sarcasm, rule-based techniques were used, in which Lexicon-based, Subjective incongruity-based features and pragmatic features were used [1] [2]. But in recent times the research on sentiment analysis has been shifted to deep learning methods and among them, CNN and LSTM are the dominating ones [3][4][5].…”