Proceedings of the 3rd International Conference on Business and Management of Technology (ICONBMT 2021)

Sentiment Analysis Based on Quality Aspects in Effort to Improve Quality of Indhome Product and Services PT Telkom Indonesia Tbk

Authors
Reza Hermansyah1, *, Riyanarto Sarno1, *
1Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia
*Corresponding author. Email: rezahrmnsyh@gmail.com, riyanarto@if.its.ac.id
Corresponding Authors
Reza Hermansyah, Riyanarto Sarno
Available Online 31 December 2021.
DOI
10.2991/aebmr.k.211226.005How to use a DOI?
Keywords
Online Review; Sentiment Analysis; Dimension of Quality; Indihome
Abstract

The fierce competition for product quality in the telecommunications industry makes every company compete to provide products that are acceptable and liked by the public, including PT Telkom Indonesia Tbk with one of its superior products, Indihome. To find out the advantages of a product or service, it is necessary to evaluate the opinion of the online review. One method that is often used to analyze online reviews is sentiment analysis. This study conducted a sentiment analysis on the product or service Indihome PT. Telkom Indonesia Tbk is based on a review written in tweet on Twitter. First, Each tweet related to Indihome is collected into data and then categorized based on eight aspects of the dimension of quality (Performance, Reliability, Features, Fit & Finish, Serviceability, Durability, Conformance dan Aesthetics) with several stages. First, the keyword term aspect of the product quality dimensions are expanded with the help of the Term Frequency Inverse Cluster Frequency method or better known as TF-ICF. Then, Lantent Dirichelet Allocation (LDA) to find hidden topics from tweets and calculate Sematic Similarity to categorize each hidden topic. Furthermore, the comparison of the combination of classification algorithm types: SentiWordNet, SentiCircle, SVM and Random Forest was tested using an evaluation factor, this was done to get a sentiment model with the best performance. The results show that the categorization of aspects using LDA+Semantic Similarity model and combining it with TF-ICF 100% to expand the terms gave 70.1% results. The sentiment classification shows that the combined SentiWordNet+SVM model assisted by SentiCircle produces a performance of 96.3%. Finally, the researchers used these two methods to obtain an evaluation based on eight aspects of the dimension of quality towards improving the quality of Indihome’s products and services. The researcher found that the ease of service aspect (Serviceability) had a review with the highest negative sentiment reaching 20.82% compared to other dimensions (Performance: 12.86%, Reliability: 2.53%, Features: 13.28%, Fit & Finish: 0.99%, Durability 4.44%, Suitability: 2.29% and Aesthetics: 5.86%).

Copyright
© 2021 The Authors. Published by Atlantis Press International B.V.
Open Access
This is an open access article under the CC BY-NC license.

Download article (PDF)

Volume Title
Proceedings of the 3rd International Conference on Business and Management of Technology (ICONBMT 2021)
Series
Advances in Economics, Business and Management Research
Publication Date
31 December 2021
ISBN
10.2991/aebmr.k.211226.005
ISSN
2352-5428
DOI
10.2991/aebmr.k.211226.005How to use a DOI?
Copyright
© 2021 The Authors. Published by Atlantis Press International B.V.
Open Access
This is an open access article under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Reza Hermansyah
AU  - Riyanarto Sarno
PY  - 2021
DA  - 2021/12/31
TI  - Sentiment Analysis Based on Quality Aspects in Effort to Improve Quality of Indhome Product and Services PT Telkom Indonesia Tbk
BT  - Proceedings of the 3rd International Conference on Business and Management of Technology (ICONBMT 2021)
PB  - Atlantis Press
SP  - 30
EP  - 39
SN  - 2352-5428
UR  - https://doi.org/10.2991/aebmr.k.211226.005
DO  - 10.2991/aebmr.k.211226.005
ID  - Hermansyah2021
ER  -