test

Feature extraction has transformed the field of Natural Language Processing (NLP) by providing an effective way to represent linguistic features. Various techniques are utilised for feature extraction, such as word embedding. This latter has emerged as a powerful technique for semantic feature extraction in Arabic Natural Language Processing (ANLP). Notably, research on feature extraction in the Arabic language remains relatively limited compared to English. In this paper, we present a review of recent studies focusing on word embedding as a semantic feature extraction technique applied in Arabic NLP. The review primarily includes studies on word embedding techniques applied to the Arabic corpus. We collected and analysed a selection of journal papers published between 2018 and 2023 in this field. Through our analysis, we categorised the different feature extraction techniques, identified the Machine Learning (ML) and/or Deep Learning (DL) algorithms employed, and assessed the performance metrics utilised in these studies. We demonstrate the superiority of word embeddings as a semantic feature representation in ANLP. We compare their performance with other feature extraction techniques, highlighting the ability of word embeddings to capture semantic similarities, detect contextual associations, and facilitate a better understanding of Arabic text. Consequently, this article provides valuable insights into the current state of research in word embedding for Arabic NLP.