Arabic Language Sentiment Analysis using Bidirectional Long Short Term Memory | ||||
| IJCI. International Journal of Computers and Information | ||||
| Article 6, Volume 10, Issue 1, January 2023, Page 65-77 PDF (714.52 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/ijci.2022.157244.1084 | ||||
 View on SCiNiTO | ||||
| Authors | ||||
osama mohamed Elsamadony  1; Arabi Elsayed Keshk2; amira abdelatey3
| ||||
| 1computer science,Cairo Higher Institute for Engineering, Computer Science,cairo,egypt | ||||
| 2Computer Science, Faculty of Computers and Information, Menoufia University | ||||
| 3Information Systems Department, Faculty of Computers and Information, Menoufia University | ||||
| Abstract | ||||
| The amount of data generated in the digital era is huge since the super growth of social networks. Sentiment analysis (SA) seeks to extract opinions from a text and determine the polarity (positive, negative, or neutral). SA is widely used to refer to English. The topic of this study is SA in Arabic language. There is an amalgamation between Word2Vec and Bidirectional Long-Short Time Memory) BLSTM) used in this paper. Firstly, words in reviews are transferred into its corresponding vectors with word representation models. Secondly, sequence of words in the sentences passes as input to BLSTM. BLSTM not only captures long-range information and solves the gradient attenuation problem, but also it better represents the future semantics of the word sequence. The polarity was calculated using Word2Vec representation models, which relies on meaning and context. A BLSTM-based deep learning (DL) architecture is proposed. The result shows that BLSTM Model Architecture surpasses CNN and LSTM Architectures with the maximum accuracy of 94.88 | ||||
| Keywords | ||||
| BLSTM; Sentiment Analysis; Word2Vec; CNN; DL | ||||
|
Statistics Article View: 360 PDF Download: 387 |
||||
