|
Title:
|
MINING SOCIAL NETWORKS ARABIC SLANG COMMENTS |
|
Author(s):
|
Taysir Hassan A. Soliman, Mostafa A. Elmasry, Abdel Rahman Hedar, M. M. Doss |
|
ISBN:
|
978-972-8939-93-9 |
|
Editors:
|
António Palma dos Reis and Ajith P. Abraham |
|
Year:
|
2013 |
|
Edition:
|
Single |
|
Keywords:
|
Opinion mining, Social Network, sentiment analysis, support vector machines, Arabic Classification. |
|
Type:
|
Full Paper |
|
First Page:
|
29 |
|
Last Page:
|
36 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
Social networks have affected the way the new generation think all over the world, specifically in the Middle East. Their effectiveness appears in the revolutions of Tunisia, Egypt, and Syria. Therefore, social networks opinion mining for Arabic slang language has become an essential since it is widely used between the youth generation. Arabic slang language suffers from two main problems, which are the new expressive (opinion) words and idioms as well as the unstructured format. Mining Arabic slang language requires efficient techniques to extract youth opinions on various issues, such as news websites. In this paper, we propose a SVM-based classifier for Arabic slang language, applying sentiment analysis, to classify youth news comments on Facebook. This classifier consists of three main phases: 1) Arabic comments data preparation, 2) Data preprocessing, and 3) data classification. In addition, a Slang Sentimental Words and Idioms Lexicon (SSWIL) of opinion words is built, used by Arab youth in their comments on news topics, Facebook1 posts and comments, twits in Twitter2 and reviews. This paper works on users comments and SSWIL enhances the classification task to be 86.86% of classified comments instead of 75.35% when using classical opinion words lexicon with precision 88.63 and recall 78 instead of 82.4 and 59.33 respectively. |
|
|
|
|
|
|
