A study of the performance of embedding methods for Arabic short-text sentiment analysis using deep learning approaches
Sentiment analysis aims to classify a text according to sentimental polarities of people’s opinions, such as positive, negative, or neutral. While most of the studies focus on eliciting features from English text, the research on Arabic is limited due to the morphological and grammatical complexity...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-09-01
|
| Series: | Journal of King Saud University: Computer and Information Sciences |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1319157821001786 |
| _version_ | 1817999454859427840 |
|---|---|
| author | Ali Alwehaibi Marwan Bikdash Mohammad Albogmi Kaushik Roy |
| author_facet | Ali Alwehaibi Marwan Bikdash Mohammad Albogmi Kaushik Roy |
| author_sort | Ali Alwehaibi |
| collection | DOAJ |
| description | Sentiment analysis aims to classify a text according to sentimental polarities of people’s opinions, such as positive, negative, or neutral. While most of the studies focus on eliciting features from English text, the research on Arabic is limited due to the morphological and grammatical complexity of Arabic language. In this paper, we proposed an optimized sentiment classification for dialectal Arabic short text at the document level using deep learning (DL). The contributions of this paper are in three areas. First, we extracted semantic features for Arabic short text at the word level and character level. Second, we used three DL topologies for classification models: a long short-term memory recurrent neural network (LSTM); a convolutional neural network (CNN); and an ensemble model combining both models’ advantages to improve the prediction performance. Third, we used a hyperparameter tuning estimation method to optimize the neural network performance. We trained and tested our proposed models on a dataset that consists of Modern Standard Arabic and dialectal Arabic corpus collected from Twitter. The results showed significant improvement in Arabic text classification in term of classification accuracy that ranges between 88% and 69.7%. The ensemble model scored the highest accuracy of 96.7% on the test set. |
| first_indexed | 2024-04-14T03:09:13Z |
| format | Article |
| id | doaj.art-3c1374b08d9546e4b6edf9a771b5fbab |
| institution | Directory Open Access Journal |
| issn | 1319-1578 |
| language | English |
| last_indexed | 2024-04-14T03:09:13Z |
| publishDate | 2022-09-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of King Saud University: Computer and Information Sciences |
| spelling | doaj.art-3c1374b08d9546e4b6edf9a771b5fbab2022-12-22T02:15:39ZengElsevierJournal of King Saud University: Computer and Information Sciences1319-15782022-09-0134861406149A study of the performance of embedding methods for Arabic short-text sentiment analysis using deep learning approachesAli Alwehaibi0Marwan Bikdash1Mohammad Albogmi2Kaushik Roy3Department of Computational Data Science & Engineering, North Carolina A&T State University, Greensboro, NC 27411, USADepartment of Computational Data Science & Engineering, North Carolina A&T State University, Greensboro, NC 27411, USADepartment Of Arabic Language, Taif University, Taif 26571, Saudi ArabiaDepartment of Computer Science, North Carolina A&T State University, Greensboro, NC 27411, USA; Corresponding author.Sentiment analysis aims to classify a text according to sentimental polarities of people’s opinions, such as positive, negative, or neutral. While most of the studies focus on eliciting features from English text, the research on Arabic is limited due to the morphological and grammatical complexity of Arabic language. In this paper, we proposed an optimized sentiment classification for dialectal Arabic short text at the document level using deep learning (DL). The contributions of this paper are in three areas. First, we extracted semantic features for Arabic short text at the word level and character level. Second, we used three DL topologies for classification models: a long short-term memory recurrent neural network (LSTM); a convolutional neural network (CNN); and an ensemble model combining both models’ advantages to improve the prediction performance. Third, we used a hyperparameter tuning estimation method to optimize the neural network performance. We trained and tested our proposed models on a dataset that consists of Modern Standard Arabic and dialectal Arabic corpus collected from Twitter. The results showed significant improvement in Arabic text classification in term of classification accuracy that ranges between 88% and 69.7%. The ensemble model scored the highest accuracy of 96.7% on the test set.http://www.sciencedirect.com/science/article/pii/S1319157821001786Arabic short-textSentiment analysisDeep learningEmbeddingEnsemble |
| spellingShingle | Ali Alwehaibi Marwan Bikdash Mohammad Albogmi Kaushik Roy A study of the performance of embedding methods for Arabic short-text sentiment analysis using deep learning approaches Journal of King Saud University: Computer and Information Sciences Arabic short-text Sentiment analysis Deep learning Embedding Ensemble |
| title | A study of the performance of embedding methods for Arabic short-text sentiment analysis using deep learning approaches |
| title_full | A study of the performance of embedding methods for Arabic short-text sentiment analysis using deep learning approaches |
| title_fullStr | A study of the performance of embedding methods for Arabic short-text sentiment analysis using deep learning approaches |
| title_full_unstemmed | A study of the performance of embedding methods for Arabic short-text sentiment analysis using deep learning approaches |
| title_short | A study of the performance of embedding methods for Arabic short-text sentiment analysis using deep learning approaches |
| title_sort | study of the performance of embedding methods for arabic short text sentiment analysis using deep learning approaches |
| topic | Arabic short-text Sentiment analysis Deep learning Embedding Ensemble |
| url | http://www.sciencedirect.com/science/article/pii/S1319157821001786 |
| work_keys_str_mv | AT alialwehaibi astudyoftheperformanceofembeddingmethodsforarabicshorttextsentimentanalysisusingdeeplearningapproaches AT marwanbikdash astudyoftheperformanceofembeddingmethodsforarabicshorttextsentimentanalysisusingdeeplearningapproaches AT mohammadalbogmi astudyoftheperformanceofembeddingmethodsforarabicshorttextsentimentanalysisusingdeeplearningapproaches AT kaushikroy astudyoftheperformanceofembeddingmethodsforarabicshorttextsentimentanalysisusingdeeplearningapproaches AT alialwehaibi studyoftheperformanceofembeddingmethodsforarabicshorttextsentimentanalysisusingdeeplearningapproaches AT marwanbikdash studyoftheperformanceofembeddingmethodsforarabicshorttextsentimentanalysisusingdeeplearningapproaches AT mohammadalbogmi studyoftheperformanceofembeddingmethodsforarabicshorttextsentimentanalysisusingdeeplearningapproaches AT kaushikroy studyoftheperformanceofembeddingmethodsforarabicshorttextsentimentanalysisusingdeeplearningapproaches |