20 Sentiment Analysis of Iraqi Arabic Dialect on Facebook Based on Distributed Representations of Documents ANWAR ALNAWAS, Department of Computer Engineering, Faculty of Technology, Gazi University, Turkey/Nasiriyah Technical Institute, Southern Technical University, Iraq NURSAL ARICI, Department of Computer Engineering, Faculty of Technology, Gazi University, Turkey Nowadays, social media is used by many people to express their opinions about a variety of topics. Opinion Mining or Sentiment Analysis techniques extract opinions from user generated contents. Over the years, a multitude of Sentiment Analysis studies has been done about the English language with defciencies of re- search in all other languages. Unfortunately, Arabic is one of the languages that seems to lack substantial research, despite the rapid growth of its use on social media outlets. Furthermore, specifc Arabic dialects should be studied, not just Modern Standard Arabic. In this paper, we experiment sentiments analysis of Iraqi Arabic dialect using word embedding. First, we made a large corpus from previous works to learn word representations. Second, we generated word embedding model by training corpus using Doc2Vec representa- tions based on Paragraph and Distributed Memory Model of Paragraph Vectors (DM-PV) architecture. Lastly, the represented feature used for training four binary classifers (Logistic Regression, Decision Tree, Support Vector Machine and Naive Bayes) to detect sentiment. We also experimented diferent values of parameters (window size, dimension and negative samples). In the light of the experiments, it can be concluded that our approach achieves a better performance for Logistic Regression and Support Vector Machine than the other classifers. CCS Concepts: • Information systems → Sentiment analysis; Additional Key Words and Phrases: Doc2Vec, Iraqi Arabic Dialect, word embedding, sentiments analysis, facebook ACM Reference format: Anwar Alnawas and Nursal Arici. 2019. Sentiment Analysis of Iraqi Arabic Dialect on Facebook Based on Distributed Representations of Documents. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 18, 3, Article 20 (January 2019), 17 pages. http://doi.org/10.1145/3278605 1 INTRODUCTION Nowadays, Social networking sites have generated a tremendous amount of data. These data con- tain a high level of opinions and user generated emotions on specifc topics [1]. Therefore it is necessary to analyze these feelings about specifc topics [2]. Thus, Sentiment Analysis (denoted Authors’ addresses: A. Alnawas, Department of Computer Engineering, Faculty of Technology, Gazi University, 06500 Ankara, Turkey/Nasiriyah Technical Institute, Southern Technical University, Iraq; emails: anwaradnanmzher.alnawas @gazi.edu.tr, anwar.alnawas@stu.edu.iq; N. Arici, Department of Computer Engineering, Faculty of Technology, Gazi Uni- versity, 06500 Ankara, Turkey; email: nursal@gazi.edu.tr. Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for proft or commercial advantage and that copies bear this notice and the full citation on the frst page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specifc permission and/or a fee. Request permissions from permissions@acm.org. © 2019 Association for Computing Machinery. 2375-4699/2019/01-ART20 $15.00 http://doi.org/10.1145/3278605 ACM Trans. Asian Low-Resour. Lang. Inf. Process., Vol. 18, No. 3, Article 20. Publication date: January 2019.