Analisis minat warga negara Indonesia terhadap mobil listrik menggunakan metode bidirectional encoder representations from transformers (bert) dan metode named entity recognition (ner)

Chandra, Aldo (2025) Analisis minat warga negara Indonesia terhadap mobil listrik menggunakan metode bidirectional encoder representations from transformers (bert) dan metode named entity recognition (ner). Bachelor thesis, Universitas Pelita Harapan.

[thumbnail of Title] Text (Title)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (166kB)
[thumbnail of Abstract] Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (392kB)
[thumbnail of Chapter 1] Text (Chapter 1)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (708kB)
[thumbnail of Chapter 2] Text (Chapter 2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (3MB)
[thumbnail of Chapter 3] Text (Chapter 3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[thumbnail of Chapter 4] Text (Chapter 4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (3MB)
[thumbnail of Chapter 5] Text (Chapter 5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (432kB)
[thumbnail of Bibliography] Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (298kB)
[thumbnail of Appendices] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (3MB)

Abstract

Peralihan ke kendaraan listrik menjadi solusi yang menjanjikan untuk mengurangi emisi gas rumah kaca dan meningkatkan kualitas udara di kawasan perkotaan. Peningkatan signifikan penggunaan kendaraan listrik di Indonesia pada periode 2021-2023 menunjukkan minat masyarakat yang terus bertumbuh terhadap teknologi ini. Namun, adopsi kendaraan listrik di Indonesia masih menghadapi berbagai tantangan, termasuk persepsi masyarakat terhadap teknologi ini serta faktor ekonomi dan teknis. Oleh sebab itu, penelitian ini bertujuan untuk menganalisis minat masyarakat Indonesia terhadap mobil listrik dengan menggunakan metode Bidirectional Encoder Representations from Transformers (BERT) dan Named Entity Recognition (NER). BERT, sebagai metode pemrosesan bahasa alami berbasis deep learning, digunakan untuk menganalisis sentimen dari teks yang terkait dengan mobil listrik, sementara NER diterapkan untuk mengidentifikasi entitas penting dalam teks, seperti merek mobil, lokasi, dan faktorfaktor yang memengaruhi minat terhadap mobil listrik. Hasil penelitian menunjukkan bahwa kinerja metode BERT dalam analisis sentimen memiliki akurasi sebesar 71,71%, presisi 83,56%, dan recall 71,71%, dengan nilai missclassification error sebesar 28,29%. Analisis minat mengungkapkan bahwa mayoritas data menunjukkan sentimen negatif (48,45%), diikuti oleh sentimen netral (30,60%), dan sentimen positif (20,95%). Selanjutnya, metode NER menunjukkan bahwa faktor-faktor utama yang memengaruhi minat masyarakat terhadap mobil listrik meliputi pertimbangan lokasi penggunaan, harga, spesifikasi teknis, serta reputasi perusahaan dan kualitas produk. / The transition to electric vehicles offers a promising solution to reducing greenhouse gas emissions and improving air quality in urban areas. The significant increase in the use of electric vehicles in Indonesia during the 2021–2023 period indicates a growing public interest in this technology. However, the adoption of electric vehicles in Indonesia still faces various challenges, including public perceptions of this technology as well as economic and technical factors. Therefore, this study aims to analyze the interest of Indonesian society in electric cars using the Bidirectional Encoder Representations from Transformers (BERT) method and Named Entity Recognition (NER). BERT, as a deep learning-based natural language processing method, is used to analyze sentiment from texts related to electric cars, while NER is applied to identify key entities in the texts, such as car brands, locations, and factors influencing interest in electric cars. The study's results show that the performance of the BERT method in sentiment analysis achieved an accuracy of 71.71%, precision of 83.56%, and recall of 71.71%, with a misclassification error rate of 28.29%. The interest analysis revealed that the majority of the data indicated negative sentiment (48.45%), followed by neutral sentiment (30.60%), and positive sentiment (20.95%). Furthermore, the NER method showed that the main factors influencing public interest in electric cars include considerations of usage location, price, technical specifications, as well as company reputation and product quality.
Item Type: Thesis (Bachelor)
Creators:
Creators
NIM
Email
ORCID
Chandra, Aldo
NIM03082210022
aldchndra@gmail.com
UNSPECIFIED
Contributors:
Contribution
Contributors
NIDN/NIDK
Email
Thesis advisor
Belferik, Ronald
NIDN0105048702
ronald.belferik@uph.edu
Uncontrolled Keywords: Mobil listrik; analisis minat; metode bidirectional encoder representations from transformers (bert); metode named entity recognition (ner)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: University Subject > Current > Faculty/School - UPH Medan > School of Information Science and Technology > Informatics
Current > Faculty/School - UPH Medan > School of Information Science and Technology > Informatics
Depositing User: Aldo Chandra
Date Deposited: 25 Apr 2025 01:34
Last Modified: 25 Apr 2025 01:34
URI: http://repository.uph.edu/id/eprint/68201

Actions (login required)

View Item
View Item