Detecting Irony in Arabic Microblogs using Deep Convolutional Neural Networks

A considerable amount of research has been de-veloped lately to analyze social media with the intention of understanding and exploiting the available information. Recently, irony has took a significant role in human communication as it has been increasingly used in many social media platforms. In Natural Language Processing (NLP), irony recognition is an important yet difficult problem to solve. It is considered to be a complex linguistic phenomenon in which people means the opposite of what they literally say. Due to its significance, it becomes essential to analyze and detect irony in subjective texts to improve the analysis tools to classify people opinion automatically. This paper explores how deep learning methods can be employed to the detection of irony in Arabic language with the help of Word2vec term representations that converts words to vectors. We applied two different deep learning models; Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM). We tested our frameworks with a manually annotated datasets that was collected using Tweet Scraper. The best result was achieved by the CNN model with an F1 score of 0.87.

@article{Alhaidari2022,
  title     = {Detecting Irony in Arabic Microblogs using Deep Convolutional Neural Networks},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {13},
  number    = {1},
  year      = {2022},
  publisher = {The Science and Information Organization},
  author    = {Linah Alhaidari and Khaled Alyoubi and Fahd Alotaibi},
  doi       = {10.14569/IJACSA.2022.0130187},
  url       = {https://doi.org/10.14569/IJACSA.2022.0130187}
}