Text Mining Untuk Analisis Sentimen Pelanggan Terhadap Layanan Uang Elektronik Menggunakan Algoritma Support Vector Machine
Electronic money is a cashless payment instrument whose money is stored in media server or chip that can be moved for the benefit of payment transactions or fund transfers. In Indonesia, there are already many electronic money products, one of which is OVO. OVO is very popular with the people of Ind...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
LPPM ISB Atma Luhur
2020-07-01
|
| Series: | Jurnal Sisfokom |
| Subjects: | |
| Online Access: | http://jurnal.atmaluhur.ac.id/index.php/sisfokom/article/view/903 |
| _version_ | 1827333641959636992 |
|---|---|
| author | Fajar Romadoni Yuyun Umaidah Betha Nurina Sari |
| author_facet | Fajar Romadoni Yuyun Umaidah Betha Nurina Sari |
| author_sort | Fajar Romadoni |
| collection | DOAJ |
| description | Electronic money is a cashless payment instrument whose money is stored in media server or chip that can be moved for the benefit of payment transactions or fund transfers. In Indonesia, there are already many electronic money products, one of which is OVO. OVO is very popular with the people of Indonesia because it offers many promos such as discounts and cashback. But over time, that much promotion is detrimental to OVO shareholders, so the portion of promo given by OVO to its customers is finally reduced. That incident caused many pros and cons opinions about OVO, one of them is on social media Twitter. Sentiment analysis can be used as a solution to process the opinions of OVO customers on Twitter. This study aims to classify the customer opinions on OVO services into positive and negative classes. This study uses the Support Vector Machine algorithm with 3852 data taken from Twitter with keyword @ovo_id using web scraping techniques. The dataset divided into two classes, 2034 positive and 1818 negative sentiment data. The classification process is carried out with four splitting data scenarios, with 60:40, 70:30, 80:20, 90:10 data ratio and with four kernel such as linear, rbf, sigomid, and polynomial. The final results show that the greatest accuracy value obtained by linear kernel with 90:10 data ratio which gets an accuracy value of 98.7%. |
| first_indexed | 2024-03-07T17:30:22Z |
| format | Article |
| id | doaj.art-ae7f1f47e354457e9809fd127603c425 |
| institution | Directory Open Access Journal |
| issn | 2301-7988 2581-0588 |
| language | English |
| last_indexed | 2024-03-07T17:30:22Z |
| publishDate | 2020-07-01 |
| publisher | LPPM ISB Atma Luhur |
| record_format | Article |
| series | Jurnal Sisfokom |
| spelling | doaj.art-ae7f1f47e354457e9809fd127603c4252024-03-02T18:13:21ZengLPPM ISB Atma LuhurJurnal Sisfokom2301-79882581-05882020-07-019224725310.32736/sisfokom.v9i2.903555Text Mining Untuk Analisis Sentimen Pelanggan Terhadap Layanan Uang Elektronik Menggunakan Algoritma Support Vector MachineFajar Romadoni0Yuyun Umaidah1Betha Nurina Sari2Universitas Singaperbangsa KarawangUniversitas Singaperbangsa KarawangUniversitas Singaperbangsa KarawangElectronic money is a cashless payment instrument whose money is stored in media server or chip that can be moved for the benefit of payment transactions or fund transfers. In Indonesia, there are already many electronic money products, one of which is OVO. OVO is very popular with the people of Indonesia because it offers many promos such as discounts and cashback. But over time, that much promotion is detrimental to OVO shareholders, so the portion of promo given by OVO to its customers is finally reduced. That incident caused many pros and cons opinions about OVO, one of them is on social media Twitter. Sentiment analysis can be used as a solution to process the opinions of OVO customers on Twitter. This study aims to classify the customer opinions on OVO services into positive and negative classes. This study uses the Support Vector Machine algorithm with 3852 data taken from Twitter with keyword @ovo_id using web scraping techniques. The dataset divided into two classes, 2034 positive and 1818 negative sentiment data. The classification process is carried out with four splitting data scenarios, with 60:40, 70:30, 80:20, 90:10 data ratio and with four kernel such as linear, rbf, sigomid, and polynomial. The final results show that the greatest accuracy value obtained by linear kernel with 90:10 data ratio which gets an accuracy value of 98.7%.http://jurnal.atmaluhur.ac.id/index.php/sisfokom/article/view/903classificationelectronic moneykernelsentiment analysissupport vector machine |
| spellingShingle | Fajar Romadoni Yuyun Umaidah Betha Nurina Sari Text Mining Untuk Analisis Sentimen Pelanggan Terhadap Layanan Uang Elektronik Menggunakan Algoritma Support Vector Machine Jurnal Sisfokom classification electronic money kernel sentiment analysis support vector machine |
| title | Text Mining Untuk Analisis Sentimen Pelanggan Terhadap Layanan Uang Elektronik Menggunakan Algoritma Support Vector Machine |
| title_full | Text Mining Untuk Analisis Sentimen Pelanggan Terhadap Layanan Uang Elektronik Menggunakan Algoritma Support Vector Machine |
| title_fullStr | Text Mining Untuk Analisis Sentimen Pelanggan Terhadap Layanan Uang Elektronik Menggunakan Algoritma Support Vector Machine |
| title_full_unstemmed | Text Mining Untuk Analisis Sentimen Pelanggan Terhadap Layanan Uang Elektronik Menggunakan Algoritma Support Vector Machine |
| title_short | Text Mining Untuk Analisis Sentimen Pelanggan Terhadap Layanan Uang Elektronik Menggunakan Algoritma Support Vector Machine |
| title_sort | text mining untuk analisis sentimen pelanggan terhadap layanan uang elektronik menggunakan algoritma support vector machine |
| topic | classification electronic money kernel sentiment analysis support vector machine |
| url | http://jurnal.atmaluhur.ac.id/index.php/sisfokom/article/view/903 |
| work_keys_str_mv | AT fajarromadoni textmininguntukanalisissentimenpelangganterhadaplayananuangelektronikmenggunakanalgoritmasupportvectormachine AT yuyunumaidah textmininguntukanalisissentimenpelangganterhadaplayananuangelektronikmenggunakanalgoritmasupportvectormachine AT bethanurinasari textmininguntukanalisissentimenpelangganterhadaplayananuangelektronikmenggunakanalgoritmasupportvectormachine |