Emotion Classification in Arabic Poetry using Machine Learning

In recent years, work on sentiment analysis and automatic text classification in Arabic has seen some progress. However, the problem of emotion classification remains widely under-researched. This work attempts to remedy the situation by considering the problem of classifying documents by their over...

Full description

Saved in:
Bibliographic Details
Published in:International journal of computer applications 2013-01, Vol.65 (16)
Main Authors: Alsharif, Ouais, Alshamaa, Deema, Ghneim, Nada
Format: Article
Language:English
Subjects:
Classification
Emotions
Machine learning
Mathematical analysis
Preprocessing
Remedies
Tasks
Texts
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, work on sentiment analysis and automatic text classification in Arabic has seen some progress. However, the problem of emotion classification remains widely under-researched. This work attempts to remedy the situation by considering the problem of classifying documents by their overall sentiment into four affect categories that are present in Arabic poetry- Retha, Ghazal, Fakhr and Heja. This work begins by building an emotional annotated Arabic poetry corpus. The impact of different levels of language preprocessing settings, feature vector dimensions and machine learning algorithms is, then, investigated and evaluated on the emotion classi?cation task.
ISSN:0975-8887
0975-8887
DOI:10.5120/11006-6300