Main Page
Deanship
The Dean
Dean's Word
Curriculum Vitae
Contact the Dean
Vision and Mission
Organizational Structure
Vice- Deanship
Vice- Dean
KAU Graduate Studies
Research Services & Courses
Research Services Unit
Important Research for Society
Deanship's Services
FAQs
Research
Staff Directory
Files
Favorite Websites
Deanship Access Map
Graduate Studies Awards
Deanship's Staff
Staff Directory
Files
Researches
Contact us
عربي
English
About
Admission
Academic
Research and Innovations
University Life
E-Services
Search
Deanship of Graduate Studies
Document Details
Document Type
:
Thesis
Document Title
:
EMOTION ANALYSIS HYBRID APPROACH TO DEFINE HUMAN FACTORS OF VIRTUAL REALITY WEARABLE DEVICES.
منهجية هجينة لتحليل العاطفة لتحديد العوامل البشرية لأَجهزة الواقع الإِفتراضي القابلة للإِرتداء.
Subject
:
Faculty of Computing and Information Technology
Document Language
:
Arabic
Abstract
:
Wearable devices manufacturing has been significantly grown nowadays, the performance and the quality have reached an incredible level of improvement. There is currently a global growing demand for these devices such as the head mounted displays (HMDs). Despite the fast improvement of HMDs which are the virtual reality (VR) wearables, most of those devices are being attached to the users’ body for a short time because it sometimes causes, pain, headaches or eye fatigue, which affect the user acceptability of the device. Accordingly, there is an increasing need to study human factors (HFs) which involve people and technology, in order to improve the users’ satisfaction level. Although measuring users’ emotions to define the HFs that affect the users’ acceptability toward a device considered a really challenging task, it accurately shows the users’ actual feelings about the HFs of these devices. This study proposed a novel multi-label hybrid emotion analysis and classification model (HF_EMA) using dictionary-based approach and machine learning approach, to define five human factors from users’ tweets which are wearability, usability, safety, satisfaction and aesthetics, and to analyze and classify users’ emotions regarding those factors into four emotions, happy, sad, anger and love. The experimental results proved the validity of the proposed model in detecting and classifying human factors and emotions, with an average of “ROC = 1” and an average of “accuracy = 98.2” for the five classification processes using a HF lexicon, two emotional lexicons, and the Naïve Base (NB) classifier. The results indicated that the usability factor is the most affected factor on VR wearables followed by satisfaction and then the wearability factor, it is also demonstrated that the aesthetics factor has less importance for the VR device’s users. Keywords—Ergonomics; Human Factors; Virtual Reality; Emotion Analysis; Social Media.
Supervisor
:
Prof. Wadee Saleh Alhalabi
Thesis Type
:
Master Thesis
Publishing Year
:
1441 AH
2020 AD
Added Date
:
Thursday, March 12, 2020
Researchers
Researcher Name (Arabic)
Researcher Name (English)
Researcher Type
Dr Grade
Email
إبتهال سيف الإسلام Makki
مكي, Ibtihal Saiful Islam
Researcher
Master
Files
File Name
Type
Description
46075.pdf
pdf
Back To Researches Page