An Ensemble of Traditional Supervised and Deep Learning Models for Arabic Text-Based Emotion Detection and Analysis


Authors : Dr. MuneerAbduallh Saeed Hazaa; Waleed Abdulqawi Mohammed Al-Homedy

Volume/Issue : Volume 7 - 2022, Issue 10 - October

Google Scholar : https://bit.ly/3IIfn9N

Scribd : https://bit.ly/3TkuQCo

DOI : https://doi.org/10.5281/zenodo.7212652

The dramaticgrowth of usersgenerated contents describing their feelings and emotion aboutproducts, services and events played a special role to bring attention to text based emotion analysis.Emotion analysis from unstructured textual data is an active area of research with numerous practical applications.Text based Emotion detection is one of the challenging tasks in Natural Language Processing. To overcome these challenges, this paper proposesanensemble of feature-based supervised learning and feature-less deep learning models for emotion recognition and analysis in Arabic short text.This paperalso evaluatesthree machine learning algorithms namely Naive-Bayes (NB), K-nearest neighbor (KNN) and meta-ensemble method of NB and KNN for Arabic text-based emotion detection and analysisProposed models are evaluated on theSemEval2018 and compared with the performances of baseline models. Experimental results clearly show that theenhanced methods outperform other baseline models for Arabic emotion detection and analysis. Results shows that proposed models had a superficial impact on the general quality of Text based Arabic emotion detection and analysis. Results show proposed models outperformed baseline models in terms of weightedaverage F-score

Keywords : Emotion analysis, deep learning, machine learning, Arabic language.

CALL FOR PAPERS


Paper Submission Last Date
31 - March - 2024

Paper Review Notification
In 1-2 Days

Paper Publishing
In 2-3 Days

Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe