Exploration of the best performance method of emotions classification for arabic tweets
Arab users of social media have significantly increased, thus increasing the opportunities for extracting knowledge from various areas of life such as trade, education, psychological health services, etc. The active Arab presence on Twitter motivates many researchers to classify and analysis Arabic...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | EJournal Article |
Published: |
Institute of Advanced Engineering and Science,
2020-08-01.
|
Subjects: | |
Online Access: | Get fulltext |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
LEADER | 02659 am a22003133u 4500 | ||
---|---|---|---|
001 | ijeecs20476_14021 | ||
042 | |a dc | ||
100 | 1 | 0 | |a Al-Hagery, Mohammed Abdullah |e author |
100 | 1 | 0 | |a None |e contributor |
700 | 1 | 0 | |a Al-assaf, Manar Abdullah |e author |
700 | 1 | 0 | |a Al-kharboush, Faiza Mohammad |e author |
245 | 0 | 0 | |a Exploration of the best performance method of emotions classification for arabic tweets |
260 | |b Institute of Advanced Engineering and Science, |c 2020-08-01. | ||
500 | |a https://ijeecs.iaescore.com/index.php/IJEECS/article/view/20476 | ||
520 | |a Arab users of social media have significantly increased, thus increasing the opportunities for extracting knowledge from various areas of life such as trade, education, psychological health services, etc. The active Arab presence on Twitter motivates many researchers to classify and analysis Arabic tweets from numerous aspects. This study aimed to explore the best performance scenarios in the classification of emotions conveyed through Arabic tweets. Hence, various experiments were conducted to investigate the effects of feature extraction techniques and the N-gram model on the performance of three supervised machine learning algorithms, which are support vector machine (SVM), naïve bayes (NB), and logistic regression (LR). The general method of the experiments was based on five steps; data collection, preprocessing, feature extraction, emotion classification, and evaluation of results. To implement these experiments, a real-world Twitter dataset was gathered. The best result achieved by the SVM classifier when using a bag of words (BoW) weighting schema (with unigrams and bigrams or with unigrams, bigrams, and trigrams) exceeded the best performance results of other algorithms. | ||
540 | |a Copyright (c) 2020 Institute of Advanced Engineering and Science | ||
540 | |a http://creativecommons.org/licenses/by-nc/4.0 | ||
546 | |a eng | ||
690 | |a Arabic Tweets, Emotion Analysis, Classification; Machine Learning; Feature Extraction; N-Gram | ||
690 | |a Arabic tweets; Emotion analysis classification; Machine learning; Feature extraction; N-gram | ||
655 | 7 | |a info:eu-repo/semantics/article |2 local | |
655 | 7 | |a info:eu-repo/semantics/publishedVersion |2 local | |
655 | 7 | |2 local | |
786 | 0 | |n Indonesian Journal of Electrical Engineering and Computer Science; Vol 19, No 2: August 2020; 1010-1020 | |
786 | 0 | |n 2502-4760 | |
786 | 0 | |n 2502-4752 | |
786 | 0 | |n 10.11591/ijeecs.v19.i2 | |
787 | 0 | |n https://ijeecs.iaescore.com/index.php/IJEECS/article/view/20476/14021 | |
856 | 4 | 1 | |u https://ijeecs.iaescore.com/index.php/IJEECS/article/view/20476/14021 |z Get fulltext |