Deep Learning Framework for Classification of Emoji Based Sentiments

Recent patterns of human sentiments are highly influenced by emoji based sentiments (EBS). Social media users are widely using emoji based sentiments (EBS) in between text messages, tweets and posts. Although tiny pictures of emoji contains sufficient information to be considered for construction of...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Computers, materials & continua Jg. 72; H. 2; S. 3145 - 3158
Hauptverfasser: Parveen Shaikh, Nighat, Hussain Mahar, Mumtaz
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Henderson Tech Science Press 2022
Schlagworte:
Algorithms
Artificial neural networks
Classification
Cleaning
Deep learning
Digital media
Emotional icons
Image classification
Machine learning
Machine vision
Object recognition
Short message service
Social networks
ISSN:1546-2226, 1546-2218, 1546-2226
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Recent patterns of human sentiments are highly influenced by emoji based sentiments (EBS). Social media users are widely using emoji based sentiments (EBS) in between text messages, tweets and posts. Although tiny pictures of emoji contains sufficient information to be considered for construction of classification model; but due to the wide range of dissimilar, heterogynous and complex patterns of emoji with similar meanings (SM) have become one of the significant research areas of machine vision. This paper proposes an approach to provide meticulous assistance to social media application (SMA) users to classify the EBS sentiments. Proposed methodology consists upon three layers where first layer deals with data cleaning and feature selection techniques to detect dissimilar emoji patterns (DEP) with similar meanings (SM). In first sub step we input set of emoji, in second sub step every emoji has to qualify user defined threshold, in third sub step algorithm detects every emoji by considering as objects and in fourth step emoji images are cropped, after data cleaning these tiny images are saved as emoji images. In second step we build classification model by using convolutional neural networks (CNN) to explore hidden knowledge of emoji datasets. In third step we present results visualization by using confusion matrix and other estimations. This paper contributes (1) data cleaning method to detect EBS; (2) highest classification accuracy for emoji classification measured as 97.63%.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1546-2226
1546-2218
1546-2226
DOI:10.32604/cmc.2022.024843