Sarcasm Detection in Persian

Abstract

Sarcasm is a form of communication where the individual states the opposite of what is implied. Therefore, detecting a sarcastic tone is somewhat complicated due to its ambiguous nature. On the other hand, identification of sarcasm is vital to various natural language processing tasks such as sentiment analysis and text summarisation. However, research on sarcasm detection in Persian is very limited. This paper investigated the sarcasm detection technique on Persian tweets by combining deep learning-based and machine learning-based approaches. Four sets of features that cover different types of sarcasm were proposed, namely deep polarity, sentiment, part of speech, and punctuation features. These features were utilised to classify the tweets as sarcastic and nonsarcastic. In this study, the deep polarity feature was proposed by conducting a sentiment analysis using deep neural network architecture. In addition, to extract the sentiment feature, a Persian sentiment dictionary was developed, which consisted of four sentiment categories. The study also used a new Persian proverb dictionary in the preparation step to enhance the accuracy of the proposed model. The performance of the model is analysed using several standard machine learning algorithms. The results of the experiment showed that the method outperformed the baseline method and reached an accuracy of 80.82%. The study also examined the importance of each proposed feature set and evaluated its added value to the classification.

Humor Detection in Persian: A Transformers-Based Approach

“…For Irony and sarcasm Detection in Persian, we review two works. Bekainejad et al [26] presented a model on a dataset of 2500 tweets. After pre-processing and preparing the data, they extracted the features of the text, like polarity and the use of punctuation marks.…”

“…We could not find any previous dataset for Persian humor detection. The two most similar Persian datasets are suitable for sarcasm [26] and irony [27] detection. Those datasets were manually-labeled tweets.…”

Recent Trends of Machine Learning Predictions Using Open Data: A Systematic Review

“…A combination of DL and ML prediction has also been carried out on the Persian sentiment analysis by using Tweet OD for the first time; however, future research should include new features to the classification to boost the performance (Nezhad & Deihimi, 2020).…”

Toward Hate Speech Analysis: Sentiment Analysis for Food Brands Review on Twitter

“…Sentiment analysis is particularly beneficial for social media tracking because it enables one to develop a better understanding of the broader public opinion around such issues. Sentiment analysis has become a discipline of study for locating opinionated data on the Web and categorizing it based on its polarity (Nezhad & Deihimi, 2021). Knowing the sentiment behind everything from forum posts and news stories enables us to develop more effective tactics and plans.…”