A lexicon-based approach for emotion analysis of Arabic social media content

Joint Authors

al-Ayyub, Mahmud
al-Abid, Muhammad

Source

International Computer Sciences and Informatics Conference, Amman, Jordan 12-13 January 2016.

Publisher

Amman Arab University

Publication Date

2016-01-31

Country of Publication

Jordan

No. of Pages

9

Main Subjects

Information Technology and Computer Science

English Abstract

Emotion Analysis (EA) is concerned with the determination of the emotions conveyed in a certain text.

With the global acceptance of social networks, EA has become both more useful and more feasible.

However, most of the current works target mainly the English language.

Important languages such as the Arabic language are largely understudied.

In this work, we develop a lexicon-based approach for EA of Arabic text.

To evaluate our approach, we collect a dataset of Arabic text excerpts from various sources such as Facebook and Twitter.

This is a necessary step since no such dataset is publicly available, to the best of our knowledge.

The emotion-bearing text excerpts of our in-house dataset are manually annotated by human experts.

We then test our approach on this dataset and the results show that our lexicon-based approach is effective with an accuracy of 89.7%.

Data Type

Conference Papers

Record ID

BIM-767319

• APA
• MLA
• AMA