ANALISIS SENTIMEN REVIEW CUSTOMER TERHADAP PERUSAHAAN EKSPEDISI JNE, J&T EXPRESS DAN POS INDONESIA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM)

N. Aula, Munirul Ula, Lidya Rosnita
{"title":"ANALISIS SENTIMEN REVIEW CUSTOMER TERHADAP PERUSAHAAN EKSPEDISI JNE, J&T EXPRESS DAN POS INDONESIA MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM)","authors":"N. Aula, Munirul Ula, Lidya Rosnita","doi":"10.33143/jics.v9i1.2947","DOIUrl":null,"url":null,"abstract":"Abstrak— Kepuasan customer adalah masalah yang harus diamati pada sebuah perusahaan, karena customer adalah alasan mengapa suatu perusahaan masih berdiri dan sukses. Perusahaan ekspedisi JNE, J&T, dan Pos Indonesia mempunyai akun twitter layanan customer yaitu @Jnecare, @J&texpressid dan @Posindonesia. Akun ini digunakan untuk layanan customer secara online yang disediakan untuk menyampaikan pendapat, kritik, saran atau keluhan pelanggan. Agar dapat mengolah komentar yang banyak tentu membutuhkan waktu yang lebih besar jika hanya dilakukan secara sederhana. Penelitian ini bertujuan untuk menganalisis sentimen perusahaan ekpedisi mana yang lebih unggul dari beberapa layanan jasa ekspedisi, metode yang akan digunakan yaitu metode Support Vector Machine (SVM). Berdasarkan hasil penelitian diperoleh performa tertinggi yaitu pada ekpedisi J&T Express menggunakan algoritma Support Vector Machine menghasikan accuracy sebesar 85%, precision sebesar 59.35%, recall sebesar 58.67%, dan f1-score sebesar 58.01% selanjutnya pada ekpedisi JNE menghasikan accuracy sebesar 82.29%, precision sebesar 54.54%, recall sebesar 55.83%, dan f1-score sebesar 54.97% sedangkan pada Pos Indonesia menghasikan accuracy sebesar 77.78%, precision sebesar 35.9%, recall sebesar 58.67%, dan f1-score sebesar 33.85%. Dari hasil perbandingan ketiga jasa ekspedisi tersebut terbukti bahwa algoritma SVM mampu menghasilkan performa yang tinggi karena tidak memiliki satupun nilai yang tidak wajar baik pada performa accuracy, precision, recall dan F1-Score.Kata kunci: Sentimen, customer, ekspedisi, SVMAbstract—Customer satisfaction is a problem that must be observed in a company, because customers are the reason why a company is still standing and successful. JNE, J&T and Pos Indonesia expedition companies have customer service twitter accounts, namely @Jnecare, @J&texpressid and @Posindonesia. This account is used for online customer service provided to convey opinions, criticisms, suggestions or customer complaints. In order to be able to process a lot of comments, of course it takes more time if it's only done in a simple way. This study aims to analyze which shipping company sentiment is superior to some courier services, the method to be used is the Support Vector Machine (SVM) method. Based on the results of the study, the highest performance was obtained on the J&T Express expedition using the Support Vector Machine algorithm resulting in an accuracy of 85%, a precision of 59.35%, a recall of 58.67%, and an f1-score of 58.01% then on a JNE expedition it produced an accuracy of 82.29%, a precision of 54.54%, recall of 55.83%, and f1-score of 54.97% while Pos Indonesia produced an accuracy of 77.78%, precision of 35.9%, recall of 58.67%, and f1-score of 33.85%. From the results of the comparison of the three shipping services it is proven that the SVM algorithm is capable of producing high performance because it does not have any unreasonable values in terms of accuracy, precision, recall and F1-Score performance. Keywords: Sentiment, customer, expedition, SVM","PeriodicalId":173281,"journal":{"name":"JOURNAL OF INFORMATICS AND COMPUTER SCIENCE","volume":"73 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"JOURNAL OF INFORMATICS AND COMPUTER SCIENCE","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.33143/jics.v9i1.2947","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Abstrak— Kepuasan customer adalah masalah yang harus diamati pada sebuah perusahaan, karena customer adalah alasan mengapa suatu perusahaan masih berdiri dan sukses. Perusahaan ekspedisi JNE, J&T, dan Pos Indonesia mempunyai akun twitter layanan customer yaitu @Jnecare, @J&texpressid dan @Posindonesia. Akun ini digunakan untuk layanan customer secara online yang disediakan untuk menyampaikan pendapat, kritik, saran atau keluhan pelanggan. Agar dapat mengolah komentar yang banyak tentu membutuhkan waktu yang lebih besar jika hanya dilakukan secara sederhana. Penelitian ini bertujuan untuk menganalisis sentimen perusahaan ekpedisi mana yang lebih unggul dari beberapa layanan jasa ekspedisi, metode yang akan digunakan yaitu metode Support Vector Machine (SVM). Berdasarkan hasil penelitian diperoleh performa tertinggi yaitu pada ekpedisi J&T Express menggunakan algoritma Support Vector Machine menghasikan accuracy sebesar 85%, precision sebesar 59.35%, recall sebesar 58.67%, dan f1-score sebesar 58.01% selanjutnya pada ekpedisi JNE menghasikan accuracy sebesar 82.29%, precision sebesar 54.54%, recall sebesar 55.83%, dan f1-score sebesar 54.97% sedangkan pada Pos Indonesia menghasikan accuracy sebesar 77.78%, precision sebesar 35.9%, recall sebesar 58.67%, dan f1-score sebesar 33.85%. Dari hasil perbandingan ketiga jasa ekspedisi tersebut terbukti bahwa algoritma SVM mampu menghasilkan performa yang tinggi karena tidak memiliki satupun nilai yang tidak wajar baik pada performa accuracy, precision, recall dan F1-Score.Kata kunci: Sentimen, customer, ekspedisi, SVMAbstract—Customer satisfaction is a problem that must be observed in a company, because customers are the reason why a company is still standing and successful. JNE, J&T and Pos Indonesia expedition companies have customer service twitter accounts, namely @Jnecare, @J&texpressid and @Posindonesia. This account is used for online customer service provided to convey opinions, criticisms, suggestions or customer complaints. In order to be able to process a lot of comments, of course it takes more time if it's only done in a simple way. This study aims to analyze which shipping company sentiment is superior to some courier services, the method to be used is the Support Vector Machine (SVM) method. Based on the results of the study, the highest performance was obtained on the J&T Express expedition using the Support Vector Machine algorithm resulting in an accuracy of 85%, a precision of 59.35%, a recall of 58.67%, and an f1-score of 58.01% then on a JNE expedition it produced an accuracy of 82.29%, a precision of 54.54%, recall of 55.83%, and f1-score of 54.97% while Pos Indonesia produced an accuracy of 77.78%, precision of 35.9%, recall of 58.67%, and f1-score of 33.85%. From the results of the comparison of the three shipping services it is proven that the SVM algorithm is capable of producing high performance because it does not have any unreasonable values in terms of accuracy, precision, recall and F1-Score performance. Keywords: Sentiment, customer, expedition, SVM
抽象地说——客户满意度是一个必须在企业中观察到的问题,因为客户端是一个企业仍然保持着成功的原因。探险公司JNE, J&T和post Indonesia有客户服务twitter账号@Jnecare, @J&texpressid和@Posindonesia。该帐户用于在线客户服务,提供给客户的意见、批评、建议或抱怨。要处理大量的评论,当然需要更多的时间,如果你只是简单地做。本研究旨在分析哪些远届企业的情绪,即支持向量机(SVM)。获得最高性能的研究成果,即根据探险队J&T快车使用支持向量机算法精确赚评比高达85%,高达35%,召回共计58 59。67%,f1-score 58 . 01%接下来在下一次的JNE大赚评比82万,29%的精确,54万。54%的召回,55万。83%,97% f1-score 54万。而在印尼明信片赚77大评比78%,高级35美元。9%,记得58.67%,f1分数33.85%。三次探险比较结果证明,SVM算法在准确、精确、记忆和F1-Score性能上没有任何不自然值,因此能够产生高性能性能。关键词:情感、客户、探险、SVMAbstract——客户满意度是一个必须在公司观察的问题,因为客户是公司仍然成功的原因。JNE, J&T和post Indonesia快递公司有客户服务twitter帐号,namely @Jnecare, @J&texpressid和@Posindonesia。该账户用于在线客户服务,提供意见、基于短信、建议或客户投诉。如果只是用简单的方法来做,就需要更多的时间。这一研究表明,该公司的声誉比一些信使服务更优越,使用的方法是支撑向量机器(SVM)方法。results》改编自《最高演出是获得on the study, J&T快车expedition用的支持向量机算法精确resulting in an 85%的评比,a的35%,a的召回58 59。67%,and an f1-score of 58 . 01%然后on a JNE expedition它由精确的82。29%的评比,a 54 54%的,召回的55。83%的97%,54和f1-score》。当邮递员印尼由77的评比的78%,高级的35。9%,召回的58。67%和f1-score 33年的85%。从三船服务的结果来看,SVM算法能够生产出高产量数据,因为它在准确、精确、记忆和F1-Score表现方面没有任何不可靠的价值。口语:情感,客户,奉献,SVM
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信