Jurnal Teknik Informatika C.I.T. Medicom
Vol 16 No 1 (2024): March: Intelligent Decision Support System (IDSS)

Sentiment, toxicity, and social network analysis of virtual reality product content reviews

Singgalen, Yerik Afrianto (Unknown)



Article Info

Publish Date
30 Mar 2024

Abstract

Virtual Reality (VR) technology has garnered significant attention in recent years due to its potential to revolutionize various industries. This study aims to investigate consumer sentiments toward VR products, mainly focusing on Meta Quest 3 in the context of the AI era. The background section outlines the rising popularity of VR products and their impact on consumer behavior, emphasizing the need for a comprehensive understanding of consumer sentiments to inform marketing strategies effectively. Methodologically, the study adopts the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework to guide the analytical approach, which includes sentiment classification, toxicity scoring, and social network analysis (SNA). A dataset comprising 2,115 consumer interactions and evaluations was utilized, with 1,302 interactions for the ALINE tech video and 813 interactions for The Tech Chap video, to derive insights into sentiment patterns and interaction dynamics. The findings reveal a positive reception towards VR products, with Meta Quest 3 particularly well-received. The sentiment classification algorithm achieved an accuracy of 77.92% without SMOTE and 85.66% with SMOTE, demonstrating competency in sentiment prediction. The precision, recall, and f-measure for SVM without SMOTE were 85.78%, 99.83%, and 92.27%, respectively, while with SMOTE, they were 100%, 55.82%, and 71.50%, respectively. Toxicity scoring yielded an average toxicity score of 0.05. Social network analysis (SNA) identified a network diameter of 6, modularity of 0.6072, and a density of 0.002815, highlighting the intricate dynamics of consumer interaction within the VR domain.

Copyrights © 2024






Journal Info

Abbrev

JTI

Publisher

Subject

Computer Science & IT

Description

The Jurnal Teknik Informatika C.I.T a scientific journal of Decision support sistem , expert system and artificial inteligens which includes scholarly writings on pure research and applied research in the field of information systems and information technology as well as a review-general review of ...