Deep learning for Arabic subjective sentiment analysis: Challenges and research opportunities

Abstract The fields of machine learning and Web technologies have witnessed significant development in the last years. This caused a ceaseless and rapid growth in sharing of the views and experience regarding services or products over the Internet in different domains. Therefore, a torrential flow of online data is available for analytical studies. Sentiment Analysis (SA) is a subtask of Natural Language Processing (NLP) that aims to analyze huge data for detecting people opinions and emotions. This field has gained growing interest by public and private sectors that led to the occurrence of many challenges, especially that related to the Arabic language. The purpose of this study is to conduct a systematic review from year 2000 until June, 2020 to analyze the status of deep Learning for Arabic NLP (ANLP) task in Arabic Subjective Sentiment Analysis (ASSA) to highlight the challenges and propose research opportunities in this field. Extensive number of research studies were reviewed to investigate deep learning techniques applied in subjective sentiment analysis for the Arabic language. We observed that CNN and RNN (LSTM) models were the most common methods used for ASSA. The results of this review show that there is a need for more efforts to implement modernized deep learning methods for Arabic sentiment analysis systems.

[1]  Abed Allah Khamaiseh,et al.  A comprehensive survey of arabic sentiment analysis , 2019, Inf. Process. Manag..

[2]  Imane Guellil,et al.  Arabic sentiment analysis: studies, resources, and tools , 2019, Social Network Analysis and Mining.

[3]  Ammar Mohammed,et al.  Deep learning approaches for Arabic sentiment analysis , 2019, Social Network Analysis and Mining.

[4]  John G. Breslin,et al.  A Hierarchical Model of Reviews for Aspect-based Sentiment Analysis , 2016, EMNLP.

[5]  Abeer Alsadoon,et al.  Deep Learning for Aspect-Based Sentiment Analysis: A Comparative Review , 2019, Expert Syst. Appl..

[6]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[7]  Ahmed Z. Emam,et al.  Sentiment Analysis of Saudi Dialect Using Deep Learning Techniques , 2019, 2019 International Conference on Electronics, Information, and Communication (ICEIC).

[8]  Rdouan Faizi,et al.  Arabic Sentiment Analysis Using a Levenshtein Distance Based Representation Approach , 2018, 2018 IEEE 5th International Congress on Information Science and Technology (CiSt).

[9]  Marwan Al Omari,et al.  Hybrid CNNs-LSTM Deep Analyzer for Arabic Opinion Mining , 2019, 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS).

[10]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..

[11]  Tagwa Abd Elatif Mohammed.  Review of Sentiment Analysis for Classification Arabic Tweets , 2016 .

[12]  Yangqiu Song,et al.  Multilingual and Multi-Aspect Hate Speech Analysis , 2019, EMNLP.

[13]  Yahya AlMurtadha.  Mining Trending Hash Tags for Arabic Sentiment Analysis , 2018 .

[14]  Raddouane Chiheb,et al.  Sentiment analysis in Arabic: A review of the literature , 2017, Ain Shams Engineering Journal.

[15]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[16]  Nizar Habash,et al.  A Characterization Study of Arabic Twitter Data with a Benchmarking for State-of-the-Art Opinion Mining Models , 2017, WANLP@EACL.

[17]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[18]  José-Ángel González,et al.  ELiRF-UPV at SemEval-2017 Task 4: Sentiment Analysis using Deep Learning , 2017, SemEval@ACL.

[19]  Samira Shaikh,et al.  TeamUNCC at SemEval-2018 Task 1: Emotion Detection in English and Arabic Tweets using Deep Learning , 2018, *SEMEVAL.

[20]  Ismail Babaoglu,et al.  Modern Trends in Arabic Sentiment Analysis: A Survey , 2017, TAL.

[21]  Ashraf Elnagar,et al.  Comparative Study of Sentiment Classification for Automated Translated Latin Reviews Into Arabic , 2017, 2017 IEEE/ACS 14th International Conference on Computer Systems and Applications (AICCSA).

[22]  Areeb Alowisheq,et al.  Arabic Sentiment Analysis Resources: A Survey , 2016, HCI.

[23]  Seung-won Hwang,et al.  Translations as Additional Contexts for Sentence Classification , 2018, IJCAI.

[24]  Ram Gopal Raj,et al.  Sentiment Analysis for Arabic in Social Media Network: A Systematic Mapping Study , 2019, ArXiv.

[25]  Mahmoud Al-Ayyoub,et al.  Deep learning for Arabic NLP: A survey , 2017, J. Comput. Sci..

[26]  Nagwa M. El-Makky,et al.  Sentiment Analysis of Arabic Tweets using Deep Learning , 2018, ACLING.

[27]  Mirsad Hadzikadic,et al.  SEDAT: Sentiment and Emotion Detection in Arabic Text Using CNN-LSTM Deep Learning , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[28]  Nada Almani,et al.  Deep Attention-Based Review Level Sentiment Analysis for Arabic Reviews , 2020, 2020 6th Conference on Data Science and Machine Learning Applications (CDMA).

[29]  Yousef Ali,et al.  Arabic Sentiment Analysis: A Systematic Literature Review , 2020, Appl. Comput. Intell. Soft Comput..

[30]  Nizar Habash,et al.  A Sentiment Treebank and Morphologically Enriched Recursive Deep Models for Effective Sentiment Analysis in Arabic , 2017, ACM Trans. Asian Low Resour. Lang. Inf. Process..

[31]  Xiuzhen Zhang,et al.  Language-Independent Twitter Classification Using Character-Based Convolutional Networks , 2017, ADMA.

[32]  Nizar Habash,et al.  A Survey of Opinion Mining in Arabic , 2019, ACM Trans. Asian Low Resour. Lang. Inf. Process..

[33]  Amal Abdullah AlMansour,et al.  State-of-the-art review on Twitter Sentiment Analysis , 2019, 2019 2nd International Conference on Computer Applications & Information Security (ICCAIS).

[34]  Ahmed Guessoum,et al.  Sentiment Analysis of Users on Social Networks: Overcoming the challenge of the Loose Usages of the Algerian Dialect , 2018, ACLING.

[35]  Faouzia Benabbou,et al.  A comparative study of sentiment analysis approaches , 2019, SCA.

[36]  Chafik Aloulou,et al.  An Empirical Evaluation of Arabic-Specific Embeddings for Sentiment Analysis , 2019, ICALP.

[37]  Tao Yu,et al.  Cross-lingual sentiment transfer with limited resources , 2018, Machine Translation.

[38]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[39]  Abdelmajid Ben Hamadou,et al.  A New Emotional Vector Representation for Sentiment Analysis , 2016, CICLing.

[40]  Fethi Bougares,et al.  Sentiment Analysis of Tunisian Dialects: Linguistic Ressources and Experiments , 2017, WANLP@EACL.

[41]  Ahmed Sabah Al-Araji,et al.  Arabic Sentiment Analysis (ASA) Using Deep Learning Approach , 2020 .

[42]  Hosny M. Ibrahim,et al.  Detecting Twitter Users' Opinions of Arabic Comments During Various Time Episodes via Deep Neural Network , 2017, AISI.

[43]  H. Chandler.  Practical , 1982, Digital Transformation of the Laboratory.

[44]  Tao Yu,et al.  Leveraging Sparse and Dense Feature Combinations for Sentiment Classification , 2017, ArXiv.

[45]  Walaa Medhat,et al.  Sentiment analysis algorithms and applications: A survey , 2014 .

[46]  Pearl Brereton,et al.  Performing systematic literature reviews in software engineering , 2006, ICSE.

[47]  Chen Wenyu,et al.  Text‐based emotion detection: Advances, challenges, and opportunities , 2020, Engineering Reports.

[48]  Haytham H. Elmousalami,et al.  Subword Attentive Model for Arabic Sentiment Analysis , 2020, ACM Trans. Asian Low Resour. Lang. Inf. Process..

[49]  Janyce Wiebe,et al.  Tracking Point of View in Narrative , 1994, Comput. Linguistics.

[50]  Mohamed Abd Elaziz,et al.  Multi-Channel Embedding Convolutional Neural Network Model for Arabic Sentiment Classification , 2019, ACM Trans. Asian Low Resour. Lang. Inf. Process..

[51]  El-Sayed M. El-Alfy,et al.  Emojis-Based Sentiment Classification of Arabic Microblogs Using Deep Recurrent Neural Networks , 2018, 2018 International Conference on Computing Sciences and Engineering (ICCSE).

[52]  Shuai Wang,et al.  Deep learning for sentiment analysis: A survey , 2018, WIREs Data Mining Knowl. Discov..

[53]  John G. Breslin,et al.  INSIGHT-1 at SemEval-2016 Task 5: Deep Learning for Multilingual Aspect-based Sentiment Analysis , 2016, *SEMEVAL.

[54]  Lina Maria Rojas-Barahona,et al.  Deep learning for sentiment analysis , 2016, Lang. Linguistics Compass.

[55]  Hanady Mansour,et al.  Successes and challenges of Arabic sentiment analysis research: a literature review , 2017, Social Network Analysis and Mining.

[56]  Eslam Omara,et al.  Deep Convolutional Network for Arabic Sentiment Analysis , 2018, 2018 International Japan-Africa Conference on Electronics, Communications and Computations (JAC-ECC).

[57]  Mohammad Azzeh,et al.  Comparative analysis of soft computing techniques for predicting software effort based use case points , 2017, IET Softw..

[58]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[59]  Samhaa R. El-Beltagy,et al.  A Context Integrated Model for Multi-label Emotion Detection , 2018, ACLING.

[60]  Kaushik Roy,et al.  Comparison of Pre-Trained Word Vectors for Arabic Text Classification Using Deep Learning Approach , 2018, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA).

[61]  Nursal Arici,et al.  The Corpus Based Approach to Sentiment Analysis in Modern Standard Arabic and Arabic Dialects: A Literature Review , 2018 .

[62]  Okba Tibermacine,et al.  Sentiment Analysis of Arabic Algerian Dialect Using a Supervised Method , 2019, 2019 International Conference on Intelligent Systems and Advanced Computing Sciences (ISACS).

[63]  Junwei Zhou,et al.  Arabic Sentiment Classification Using Convolutional Neural Network and Differential Evolution Algorithm , 2019, Comput. Intell. Neurosci..

[64]  Alain Abran,et al.  On the value of parameter tuning in heterogeneous ensembles effort estimation , 2017, Soft Computing.

[65]  Cagatay CATAL,et al.  A sentiment classification model based on multiple classifiers , 2017, Appl. Soft Comput..

[66]  Feiran Huang,et al.  Sentiment analysis of social images via hierarchical deep fusion of content and links , 2019, Appl. Soft Comput..

[67]  Mahmoud Al-Ayyoub,et al.  Using long short-term memory deep neural networks for aspect-based sentiment analysis of Arabic reviews , 2018, International Journal of Machine Learning and Cybernetics.

[68]  Erik Cambria,et al.  A review of sentiment analysis research in Arabic language , 2020, Future Gener. Comput. Syst..

[69]  Raymond Chiong,et al.  Multilingual sentiment analysis: from formal to informal and scarce resource languages , 2016, Artificial Intelligence Review.

[70]  Altyeb Altaher,et al.  Hybrid approach for sentiment analysis of Arabic tweets based on deep learning model and features weighting , 2017 .

[71]  Ashraf Elnagar,et al.  An Annotated Huge Dataset for Standard and Colloquial Arabic Reviews for Subjective Sentiment Analysis , 2018, ACLING.

[72]  Adel Said Elmaghraby,et al.  Annotation Technique for Health-Related Tweets Sentiment Analysis , 2018, 2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT).

[73]  Khaled Shaalan,et al.  Speech Recognition Using Deep Neural Networks: A Systematic Review , 2019, IEEE Access.

[74]  Faouzia Benabbou,et al.  Machine Learning for Sentiment Analysis: A Survey , 2019 .

[75]  Hazem M. Hajj,et al.  Comparative Evaluation of Sentiment Analysis Methods Across Arabic Dialects , 2017, ACLING.

[76]  Mohamed Lazaar,et al.  Impact of Neural Network Architectures on Arabic Sentiment Analysis , 2019, BDIoT'19.

[77]  Tomas Mikolov,et al.  Bag of Tricks for Efficient Text Classification , 2016, EACL.

[78]  Ashraf Elnagar,et al.  Investigation on sentiment analysis for Arabic reviews , 2016, 2016 IEEE/ACS 13th International Conference of Computer Systems and Applications (AICCSA).

[79]  K. Shaalan,et al.  A sentiment reporting framework for major city events: Case study on the China-United States trade war , 2020 .

[80]  Amir Hussain,et al.  A Semi-supervised Corpus Annotation for Saudi Sentiment Analysis Using Twitter , 2018, BICS.

[81]  Ismail Shahin,et al.  Emotion Recognition Using Hybrid Gaussian Mixture Model and Deep Neural Network , 2019, IEEE Access.

[82]  Mika V. Mäntylä,et al.  The evolution of sentiment analysis - A review of research topics, venues, and top cited papers , 2016, Comput. Sci. Rev..

[83]  Eslam Omara,et al.  Emotion Analysis in Arabic Language Applying Transfer Learning , 2019, 2019 15th International Computer Engineering Conference (ICENCO).

[84]  Ge Yu,et al.  Sentiment analysis using deep learning approaches: an overview , 2019, Science China Information Sciences.

[85]  Mirsad Hadzikadic,et al.  Sentiment Analysis on Arabic Tweets: Challenges to Dissecting the Language , 2017, HCI.

[86]  Allan Ramsay,et al.  Explorations in Sentiment Mining for Arabic and English Tweets , 2018, AIMSA.

[87]  Ali Yahyaouy,et al.  Applications of Deep Learning in Arabic Sentiment Analysis: Research Perspective , 2020, 2020 1st International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET).

[88]  Bing Liu,et al.  Sentiment Analysis and Opinion Mining , 2012, Synthesis Lectures on Human Language Technologies.

[89]  Ahmed Alsayat,et al.  A comprehensive study for Arabic Sentiment Analysis (Challenges and Applications) , 2020 .

[90]  Mario Cannataro,et al.  Sentiment analysis for mining texts and social networks data: Methods and tools , 2019, WIREs Data Mining Knowl. Discov..

[91]  Shivakant Mishra,et al.  Investigating the effect of combining GRU neural networks with handcrafted features for religious hatred detection on Arabic Twitter space , 2019, Social Network Analysis and Mining.

[92]  Florentin Smarandache,et al.  Word-level neutrosophic sentiment similarity , 2019, Appl. Soft Comput..

[93]  Basemah Alshemali,et al.  Adversarial Examples in Arabic , 2019, 2019 International Conference on Computational Science and Computational Intelligence (CSCI).

[94]  Juan Manuel Cueva Lovelle,et al.  An approach to improve the accuracy of probabilistic classifiers for decision support systems in sentiment analysis , 2017, Appl. Soft Comput..

[95]  Claire Cardie,et al.  Adversarial Deep Averaging Networks for Cross-Lingual Sentiment Classification , 2016, TACL.

[96]  Mohammad Karim Sohrabi,et al.  A survey on classification techniques for opinion mining and sentiment analysis , 2017, Artificial Intelligence Review.

[97]  Nora Al-Twairesh,et al.  Surface and Deep Features Ensemble for Sentiment Analysis of Arabic Tweets , 2019, IEEE Access.

[98]  Ridi Ferdiana,et al.  A Review of Sentiment Analysis for Non-English Language , 2019, 2019 International Conference of Artificial Intelligence and Information Technology (ICAIIT).

[99]  Rabeeh Ayaz Abbasi,et al.  ArWordVec: efficient word embedding models for Arabic tweets , 2020, Soft Comput..

[100]  Dinesh Kumar Vishwakarma,et al.  Sentiment analysis using deep learning architectures: a review , 2019, Artificial Intelligence Review.

[101]  Patricia Conde Céspedes,et al.  Detection of Suspicious Accounts on Twitter Using Word2Vec and Sentiment Analysis , 2018, MISSI.

[102]  Sara Tedmori,et al.  Sentiment Analysis for Arabic Language using Attention-Based Simple Recurrent Unit , 2019, 2019 2nd International Conference on new Trends in Computing Sciences (ICTCS).

[103]  María I. Viedma-del Jesús,et al.  A survey of multilingual human-tagged short message datasets for sentiment analysis tasks , 2017, Soft Computing.

[104]  Rachid Oulad Haj Thami,et al.  Exploring the Use of Word Embedding and Deep Learning in Arabic Sentiment Analysis , 2019 .

[105]  Arjun Mukherjee,et al.  Aspect Extraction with Automated Prior Knowledge Learning , 2014, ACL.

[106]  Nizar Habash,et al.  OMAM at SemEval-2017 Task 4: Evaluation of English State-of-the-Art Sentiment Analysis Models for Arabic and a New Topic-based Model , 2017, *SEMEVAL.

[107]  Nizar Habash,et al.  Morphological Analysis and Generation for Arabic Dialects , 2005, SEMITIC@ACL.

[108]  Javier M. Moguerza,et al.  A multi-stage method for content classification and opinion mining on weblog comments , 2013, Annals of Operations Research.

[109]  Eslam Omara,et al.  Deep Convolutional Arabic Sentiment Analysis with Imbalanced Data , 2019, 2019 15th International Computer Engineering Conference (ICENCO).

[110]  Hazlina Hamdan,et al.  Narrow Convolutional Neural Network for Arabic Dialects Polarity Classification , 2019, IEEE Access.

[111]  Pengfei Duan,et al.  Word Embeddings and Convolutional Neural Network for Arabic Sentiment Classification , 2016, COLING.

[112]  Ambreen Nazir,et al.  Issues and Challenges of Aspect-based Sentiment Analysis: A Comprehensive Survey , 2020, IEEE Transactions on Affective Computing.

[113]  Anazida Zainal,et al.  A Review on Challenging Issues in Arabic Sentiment Analysis , 2016, J. Comput. Sci..

[114]  Ismail Shahin,et al.  Novel cascaded Gaussian mixture model-deep neural network classifier for speaker identification in emotional talking environments , 2018, Neural Computing and Applications.

[115]  Imane Guellil,et al.  English vs Arabic Sentiment Analysis: A Survey Presenting 100 Work Studies, Resources and Tools , 2019, 2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA).

[116]  Mahmoud Al-Ayyoub,et al.  Deep Recurrent neural network vs. support vector machine for aspect-based sentiment analysis of Arabic hotels' reviews , 2017, J. Comput. Sci..

[117]  El-Sayed M. El-Alfy,et al.  Hybrid Deep Learning for Sentiment Polarity Determination of Arabic Microblogs , 2017, ICONIP.

[118]  A. Elnagar,et al.  Hotel Arabic-Reviews Dataset Construction for Sentiment Analysis Applications , 2018 .

[119]  Allan Ramsay,et al.  Detecting Emotions in English and Arabic Tweets , 2019, Inf..

[120]  Fadi Almasalha,et al.  Pareto efficient multi-objective optimization for local tuning of analogy-based estimation , 2016, Neural Computing and Applications.

[121]  Muhammad Abdul-Mageed,et al.  AraNet: A Deep Learning Toolkit for Arabic Social Media , 2020, OSACT.

[122]  Stergios Chatzikyriakidis,et al.  LSTM-CNN Deep Learning Model for Sentiment Analysis of Dialectal Arabic , 2019, ICALP.

[123]  Shahid Shayaa,et al.  Sentiment Analysis of Big Data: Methods, Applications, and Open Challenges , 2018, IEEE Access.

[124]  Matthew England,et al.  Improving Sentiment Analysis in Arabic Using Word Representation , 2018, 2018 IEEE 2nd International Workshop on Arabic and Derived Script Analysis and Recognition (ASAR).

[125]  Nursal Arici,et al.  Sentiment Analysis of Iraqi Arabic Dialect on Facebook Based on Distributed Representations of Documents , 2019, ACM Trans. Asian Low Resour. Lang. Inf. Process..

[126]  Farah Benamara,et al.  An Algerian Corpus and an Annotation Platform for Opinion and Emotion Analysis , 2020, LREC.

[127]  Arafat Awajan,et al.  A Survey of Textual Emotion Detection , 2018, 2018 8th International Conference on Computer Science and Information Technology (CSIT).

[128]  Mounir Zrigui,et al.  Using Tweets and Emojis to Build TEAD: an Arabic Dataset for Sentiment Analysis , 2018, Computación y Sistemas.

[129]  Timothy D. Solberg,et al.  Deep nets vs expert designed features in medical physics: An IMRT QA case study , 2018, Medical physics.

[130]  Ashraf Elnagar,et al.  Improving Arabic sentiment analysis with sentiment-specific embeddings , 2017, 2017 IEEE International Conference on Big Data (Big Data).

[131]  Naomie Salim,et al.  Opinion analysis for twitter and arabic tweets: a systematic literature review , 2013 .

[132]  Dipanjan Sarkar,et al.  Practical Machine Learning with Python , 2018, Apress.

[133]  Ann Banfield,et al.  Unspeakable Sentences : Narration and Representation in the Language of Fiction , 1982 .