Aspect-Based Sentiment Analysis for Arabic Government Reviews

  • Sufyan AreedEmail author
  • Omar Alqaryouti
  • Bilal Siyam
  • Khaled Shaalan
Part of the Studies in Computational Intelligence book series (SCI, volume 874)


Government services are available online and can be provided through multiple digital channels, clients’ feedback on these services can be submitted and obtained online. Enormous budgets are invested annually by governments to understand their clients and adapt services to meet their needs. In this paper, a unique dataset that consists of government smart apps Arabic reviews, domain aspects and opinion words is produced. It illustrates the approach that was carried out to manually annotate the reviews, measure the sentiment scores to opinion words and build the desired lexicons. Furthermore, this paper presents an Arabic Aspect-Based Sentiment Analysis (ABSA) that combines lexicon with rule-based models. The proposed model aims to extract aspects of smart government applications Arabic reviews, and classify all corresponding sentiments. This model examines mobile government app reviews from various perspectives to provide an insight into the needs and expectations of clients. In addition, it aims to develop techniques, rules and lexicons for language processing to address variety of SA challenge. The performance of the proposed approach confirmed that applying rules settings that can handle some challenges in ABSA improves the performance significantly. The results reported in the study have shown an increase in the accuracy and f-measure by 6%, and 17% respectively when compared with the baseline.


Aspect-Based Sentiment Analysis (ABSA) Government smart apps reviews Lexicon-based Rule-based Arabic reviews Dubai Government 


  1. 1.
    M.Z. Asghar, A. Khan, S. Ahmad, F.M. Kundi, A review of feature extraction in sentiment analysis 4(3), 181–186 (2014)Google Scholar
  2. 2.
    S.Y. Ganeshbhai, Feature Based Opinion Mining : A Survey (2015), pp. 919–923Google Scholar
  3. 3.
    B. Liu, L. Zhang, A Survey of Opinion Mining and Sentiment Analysis (2012)Google Scholar
  4. 4.
    M. Hu, B. Liu, Mining and Summarizing Customer Reviews (2004)Google Scholar
  5. 5.
    G. Carenini, R. Ng, A. Pauls, Multi-document summarization of evaluative text. Comput. Intell., 305–312 (2013)Google Scholar
  6. 6.
    S. Poria, E. Cambria, A. Gelbukh, Aspect extraction for opinion mining with a deep convolutional neural network. Knowl.-Based Syst. 108, 42–49 (2016)CrossRefGoogle Scholar
  7. 7.
    S. Poria, E. Cambria, L.-W. Ku, C. Gui, A. Gelbukh, A rule-based approach to aspect extraction from product reviews, in Proceedings of the Second Workshop on Natural Language Processing for Social Media (SocialNLP) (2014), pp. 28–37Google Scholar
  8. 8.
    M. Tubishat, N. Idris, M.A.M. Abushariah, Implicit aspect extraction in sentiment analysis: review, taxonomy, oppportunities, and open challenges. Inf. Process. Manage. 54(4), 545–563 (2018)CrossRefGoogle Scholar
  9. 9.
    O. Alqaryouti, N. Siyam, K. Shaalan, A Sentiment Analysis Lexical Resource and Dataset for Government Smart Apps Domain, vol 639 (Springer International Publishing, 2018)Google Scholar
  10. 10.
    J. Moreno-Garcia, J. Rosado, Using syntactic analysis to enhance aspect based sentiment analysis, in International Conference on Information Processing and Management of Uncertainty in Knowledge-Based Systems (2018), pp. 671–682Google Scholar
  11. 11.
    C.C. Aggarwal, C. Zhai, Mining Text Data, vol 101, no 23 (2012)Google Scholar
  12. 12.
    M. Rushdi-Saleh, M.T. Martín-Valdivia, L.A. Ureña-López, J.M. Perea-Ortega, OCA: Opinion Corpus for Arabic, In vivo (Athens, Greece), vol 30, no 2 (2011), pp. 155–157Google Scholar
  13. 13.
    M. Abdul-Mageed, M.T. Diab, M. Korayem, Subjectivity and sentiment analysis of modern standard Arabic. Assoc. Comput. Linguist. 29(3), 587–591 (2011)Google Scholar
  14. 14.
    M. Abdul-Mageed, M.M. Diab, AWATIF: a multi-genre corpus for modern standard arabic subjectivity and sentiment analysis, in Language Resources and Evaluation Conference (LREC’12), Istanbul (2012), pp. 3907–3914Google Scholar
  15. 15.
    S.R. El-beltagy, A. Ali, Open Issues in the Sentiment Analysis of Arabic Social Media : A Case Study, no. June, 2013Google Scholar
  16. 16.
    A. Assiri, A. Emam, H. Al-Dossari, Towards enhancement of a lexicon-based approach for Saudi dialect sentiment analysis. J. Inf. Sci. 44(2), 184–202 (2018)CrossRefGoogle Scholar
  17. 17.
    G. Badaro, R. Baly, H. Hajj, A large scale Arabic sentiment lexicon for Arabic opinion mining, in Arabic Natural Language Processing Workshop Co-located with EMNLP 2014 (2014), pp. 165–173Google Scholar
  18. 18.
    H. Abdellaoui, M. Zrigui, Using Tweets and Emojis to Build TEAD : an Arabic Dataset for Sentiment Analysis, vol 22, no 3 (2018), pp. 777–786Google Scholar
  19. 19.
    M. AL-Smadi, O. Qawasmeh, B. Talafha, M. Quwaider, Human Annotated Arabic Dataset of Book Reviews for Aspect Based Sentiment Analysis (2015), pp. 726–730Google Scholar
  20. 20.
    M. AL-Smadi, M. Al-Ayyoub, H. Al-Sarhan, Y. Jararweh, Using Aspect-Based Sentiment Analysis to Evaluate Arabic News Affect on Readers (2015)Google Scholar
  21. 21.
    M. Al-smadi, O. Qwasmeh, B. Talafha, M. Al-ayyoub, Y. Jararweh, E. Benkhelifa, An Enhanced Framework for Aspect-Based Sentiment Analysis of Hotels’ Reviews : Arabic Reviews Case Study (2016), pp. 98–103Google Scholar
  22. 22.
    M. Al-smadi, O. Qawasmeh, M. Al-ayyoub, Y. Jararweh, B. Gupta, Deep recurrent neural network vs. support vector machine for aspect-based sentiment analysis of Arabic Hotels’ reviews. J. Comput. Sci. (2017)Google Scholar
  23. 23.
    M. Al-smadi, M. Al-ayyoub, Y. Jararweh, O. Qawasmeh, Enhancing aspect-based sentiment analysis of Arabic Hotels’ reviews using morphological, syntactic and semantic features, in Information Processing and Management, no. October 2016 (2018), pp. 0–1Google Scholar
  24. 24.
    B. Liu, Sentiment Analysis and Opinion Mining Morgan & Claypool Publishers, in Language Arts & Disciplines, no. May (2012), p. 167Google Scholar
  25. 25.
    G. Badaro, R. Baly, R. Akel, L. Fayad, J. Khairallah, A Light Lexicon-based Mobile Application for Sentiment Mining of Arabic Tweets (2015), pp. 18–25Google Scholar
  26. 26.
    P. Takala, P. Malo, A. Sinha, O. Ahlgren, Gold-standard for topic-specific sentiment analysis of economic texts, in Proceedings of the Language Resources and Evaluation Conference (2010), pp. 2152–2157Google Scholar
  27. 27.
    K. Shaalan, Rule-based Approach in Arabic Natural Language Processing, no. May, 2010Google Scholar
  28. 28.
    D. Vilares, C. Gómez-Rodríguez, M.A. Alonso, Universal, Unsupervised (Rule-Based), Uncovered Sentiment Analysis ∗. Knowl.-Based Syst. 118, 45–55 (2017)CrossRefGoogle Scholar
  29. 29.
    M. Taboada, J. Brooke, M. Tofiloski, K. Voll, M. Stede, Lexicon-based methods for sentiment analysis. Assoc. Comput. Linguist. (2011)Google Scholar
  30. 30.
    F.M. Kundi, A. Khan, S. Ahmad, M.Z. Asghar, Lexicon-based sentiment analysis in the social web. J. Basic Appl. Sci. Res., 238–248 (2014)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Sufyan Areed
    • 1
    Email author
  • Omar Alqaryouti
    • 1
  • Bilal Siyam
    • 1
  • Khaled Shaalan
    • 2
  1. 1.The British University in DubaiDubaiUAE
  2. 2.School of InformaticsUniversity of EdinburghEdinburghUK

Personalised recommendations