A Systematic Mapping Study of Emotion Analysis in Arabic Language

Yousra Alhade Aljamel

المؤلفون

Yousra Alhade Aljamel Graduate School of Natural and Applied science, Atilim University Ankara. Turkey

الكلمات المفتاحية:

Emotion analysis، Arabic language، natural language processing

الملخص

In this study, we address the problem of emotion analysis in Arabic text by reviewing the current studies on the topic between the years 2013- 2023.

The standard systematic mapping study method has been employed collecting 62 studies on Arabic emotion text research, including 31 articles from SCOPUS, and 31 from Google Scholar.

The results of the review indicates that the largest number of research was conducted and published in 2023. 31 journals published articles in the area of Arabic Emotion Detection, and the journal that published the most articles is Applied Science (MDPI). The statistical approach using different supervised machine learning algorithms has been the most popular approach for Arabic Emotion Analysis for the past ten years, followed by the deep learning algorithms. There are only two studies that have used lexical-based techniques and the hybrid approach. The data sets collected from social media platforms (Twitter and Facebook) are the most widely used in the Arabic text emotion analysis, especially Twitter. Lastly, the number of type of emotions used in previous studies to detect Arabic emotion amounted to 26 emotions, where the most common emotion types recognized were: sadness, anger, fear, joy, surprise, disgust, and love.

المراجع

F. Acheampong, C. Wenyu, and H. Nunoo-Mensah, " Text-based emotion detection: Advances, challenges, and opportunities", Wily DOI: 10.1002/eng2.12189, Engineering Reports. 2020; 2:e12189.

J. Russell, and A. Mehrabia, “Evidence For A Three-Factor Theory Of EMOTIONS”, Journal Of Research In Personality 11, 273-294 (1977) .

H. Elfaik, and E. Nfaoui, "Combining Context-Aware Embeddings and Attentional Deep Learning Model", IEE Access; volume 9, 2021.

B. Al-onazi1, H. Alshamrani, F. Aldaajeh, A.S. Aziz, M. Rizwanullah, “Modified Seagull Optimization with Deep Learning for Affect Classification in Arabic Tweets”. Digital Object Identifier 10.1109/ACCESS.2017.Doi Number.

A. Daood, and I. Salman, "Comparison Study Of Automatic Classifiers Performance In Emotion Recognition Of Arabic Social Media Users", Journal of Theoretical and Applied Information Technology.95 (19), pp. 5172-5183, 2017.

S. Mohammad, " Sentiment analysis: Detecting valence, emotions, and other affectual states from text. In H. Meiselman (Ed.), Emotion measurement", Elsevier. To be published, 2016.

T. Kanan, O. Sadaqa, and A. Aldajeh. “A Review of Natural Language Processing and Machine Learning Tools Used to Analyze Arabic Social Media”, 2019 IEEE, Conference Paper, April 2019.

S. K. Tawalbehe, O. AlZoubi, and M. AL-Smadi, “Recent Advances of Affect Detection from Arabic Text”. Conference Paper · June 2019 DOI: 10.1109/IACS.2019.8809155.

M. J.Althobaiti, “Emotion Recognition In Arabic: A Bert-Based Transfer Learning Approach Leveraging Semantic Information Of Online Comments”. Journal of Theoretical and Applied Information Technology, Vol.101. No 9, ISSN: 1992-8645, May 2023.

I.M. Alwayle, B.B. Al-onazi, J.S. Alzahrani, K.M. Alalayah, K.M. Alaidarous, I.A.Ahmed, M.Othman, and A.Motwakel. “Parameter Tuned Machine Learning Based Emotion Recognition on Arabic Twitter Data”. CSSE, 2023, vol.46, no.3.

M. Alruily, “Classification of Arabic Tweets: A Review”. MDPI, Electronics 2021, 10, 1143.

Twitter Data set for Arabic Sentiment Analysis Data Set

https://archive.ics.uci.edu/ml/datasets/Twitter+Data+set+for+Arabic+Sentiment+Analysis

Twitter Data set for Arabic Sentiment Analysis. April, 2014. (a) Creator: N. A. Abdulla and N. Mahyoub (b) Donor: N. A. Abdulla (naabdulla11@cit.just.edu.jo) collection of 2000 labelled tweets (positive tweets and negative ones) These tweets written in both Modern Standard Arabic (MSA) and the Jordanian dialect”.

M. Abdullah., I. Makki, M. Almasawa, and M. Alsulmi, “Emotions extraction from Arabic tweets". International Journal of Computers and Applications; 42(7), pp. 661-675.

AraSenti Lexicon

https://github.com/nora-twairesh/AraSenti

AraSenti Lexicon. May, 2016 (a) Nour AlTwairesh (Twairesh@ksu.edu.sa) (b) Hend Alkhaifa (hendk@ksu.edu.sa) (c) abdulMalik Alsalman (salman@ksu.edu.sa)

M. Balli, and N. Ghneim, “Emotion analysis of Arabic tweets using deep learning approach". Journal of Big Date; 6(1), 89.

N. Al-wairesh, “The evolution of language models applied to emotion analysis of arabic tweets". Information (Switzerland); (2), 84, pp. 1-15.

O. Badarneh, M. Al-ayyoub, N. Alhindawi, and L. Tawalbeh, “Fine-Grained Emotion Analysis of Arabic Tweets: A Multi-target Multi-label Approach". 2018 IEEE 12th International Conference on Semantic Computing (ICSC).

S. Alzu'bi, O. Badarneh, B. Hawashin, M. Al-ayyoub, N. Alhindawi, Y. Jararweh, "Multi-Label Emotion Classification for Arabic Tweets". 2019 Sixth International Conference on Social Networks Analysis; Management and Security (SNAMS).

A. Al-Mahdawi, and W.J.Teahan. “A new Arabic dataset for emotion recognition”. Chapter · July 2019 DOI: 10.1007/978-3-030-22868-2_16.

A. Al-Khatib, and S.R. El-Beltagy, “Emotional tone detection in arabic tweets”. Conference Paper · April 2017.

H. Alhuzali, M.Abdul-Mageed, and L. Ungar, “Enabling Deep Learning of Emotion With First-Person Seed Expressions”, New Orleans, Louisiana, June 6, 2018.c 2018 Association for Computational Linguistics.

K. Shakil, K. Tabassum, F. S. Alqahtani, and M. A. Wani, “Analyzing user digital emotions from a holy versus non-pilgrimage city in Saudi Arabia on twitter platform”. Appl. Sci. 2021, 11, 684.

A. Al-Laith, and M. Alenezi, “Monitoring people’s emotions and symptoms from arabic tweets during the covid-19 pandemic”. Information 2021, 12, 86.

A. Nasir, E. Nee, C. Choong, A. Ghani. A. Majeed, A. Adam, and M. Furqan, "Text-based emotion prediction system using machine learning approach", IOP Conf. Series: Materials Science and Engineering, 10.1088/1757-899X/769/1/012022.

https://blog.knoldus.com/text-data-vectorization-techniques-in-natural-language-processing/

M. M,Abuteir, and E.S.Elsamani, “Automatic Sarcasm Detection in Arabic Text: A Supervised Classification Approach”. International Journal of New Technology and Research (IJNTR) ISSN: 2454-4116, Volume-7, Issue-8, August 2021 Pages 32-42.

A. Mohammad, " Arabic Text Classification: A Review". Modern Applied Science, Vol. 13, No. 5; 2019. ISSN 1913-1844 E-ISSN 1913-1852.

M. Al-hagery, M. Al-saaf, and F. Alkharbush, " Exploration of the best performance method of emotions classification for arabic tweets", Indonesian Journal of Electrical Engineering and Computer Science,19(2), pp. 1010-1020.

S. Mohammad, and P. Turney, "NRC Emotion Lexicon".November 15, 2013.

H. Çakar, and A. Şengür, "Machine Learning Based Emotion Classification Using the Covid-19 Real World Worry Dataset". Anatolian Journal of Computer Sciences, Volume/6, No/1, pp: 24-31.

Kai. P, and V. Kuzniarz, " Guidelines for conducting systematic mapping studies in software engineering: An update", Information and Software Technology 64 (2015) 1–18, 2015.

B. Kitchenham, O. Pearl Brereton, D. Budgen, M. Turner, and J. Bailey, "Systematic literature reviews in software engineering – A systematic -literature review" ,Information and Software Technology 51 (2009) 7–15,2009.

W. Alshehri, N.Al-Twairesh, and A. Alothaim, “Affect Analysis in Arabic Text: Further Pre-Training Language Models for Sentiment and Emotion”. Appl. Sci. 2023, 13, 5609.