Emotions extraction from Arabic tweets

ABSTRACT

Twitter is one of the most used microblogs in social media communication channels. Emotion detection has recently raised as an important research field. Extracting emotions in Twitter microblogs has many benefits and applications. Such applications include e-commerce, e-marketing, and others. Knowing the perception about relevant products, services, events or personalities, as well as monitoring their online reputation are some of the objectives that companies have marked in short term. Most of studies focus on sentiments analysis as positive and negative but few of them go deeper to analyze and classify the emotions behind tweets, especially in Arabic tweets. Arabic language becomes a hard challenge for emotions classification on twitter and it involves more preprocessing before classification than other languages. This paper presents a model for extracting and classifying emotions in Arabic tweets based on four emotions: sad, joy, disgust, and anger. The experimental results demonstrate the validity of the proposed model, which improves the state of the art in the classification of Arabic tweets using support vector machine (SVM) and Naïve Bayes (NB) that give the best results. SVM outperforms the other used classifiers with 80.6% accuracy, and the NB outperforms the other classifiers with 0.95 ROC area.

KEYWORDS:

• Text mining
• NLP
• Arabic tweets
• emotions
• sentiment analysis

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1. The official version of this package will be available in Jan 2017 on WEKA website.

 

Additional information

Notes on contributors

Manal Abdullah

Dr Manal Abdullah received her PhD at computers and systems engineering, Faculty of engineering, Ain Shams University, Cairo, Egypt, 2002. She has experience in industrial computer networks and embedded systems. Her research interests include computer networks, performance evaluation, WSN, network management, Artificial Intelligence, Big Data analysis, and pattern recognition. Dr Abdullah published more than 75 research papers in various international journals and conferences. Currently she is assistant professor, Faculty of Computing and Information Technology FCIT, King Abdulaziz University, KAU, Saudi Arabia.

Muna AlMasawa

Muna AlMasawa is currently a master student in the Computer Science department at King Abdulaziz University. Her research interests include image processing, computer vision, pattern recognition and big data analysis.

Ibtihal Makki

Ibtihal Makki is a postgraduate student working on her M.S. degree at the Department of Computer Science from King Abdulaziz University. Her current research interests focus on human factors engineering, virtual reality, augmented reality, mixed reality, computer networks, text mining and big data analysis.

Maha Alsolmi

Maha Alsolmi is a postgraduate student working on her M.S. degree at the Department of Computer Science from King Abdulaziz University. Her current research interests focus on networks, security, big data, text mining, sentiment analysis.

Samar Mahrous

Samar Mahrous is currently a master student in the Computer Science department at King Abdulaziz University. Her research interests include artificial intelligence, computer vision, e-learning, human-computer interaction.