Penerapan Support Vector Machine (SVM) untuk  Pengkategorian Penelitian

Jumeilah, Fithri Selva

doi:10.29207/resti.v1i1.11

Cited by 45 publications

(47 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Terdapat beberapa penelitian terkait analisis sentimen sebuah opini. Pada penelitian pengkategorian penelitian menggunakan metode SVM, dapat menghasilkan tingkat akurasi sebesar 90% dengan menggunakan 390 abstrak dan 4 kategori [6]. Metode classifier juga dapat digunakan pada algoritma Naive Bayes, dimana metode tersebut akan mampu melihat peluang dari setiap kondisi [7].…”

Section: Pendahuluanunclassified

Algorithm Comparation of Naive Bayes and Support Vector Machine based on Particle Swarm Optimization in Sentiment Analysis of Freight Forwarding Services

Anggita

Ikmah

2020

RESTI

View full text Add to dashboard Cite

The needs of the community for freight forwarding are now starting to increase with the marketplace. User opinion about freight forwarding services is currently carried out by the public through many things one of them is social media Twitter. By sentiment analysis, the tendency of an opinion will be able to be seen whether it has a positive or negative tendency. The methods that can be applied to sentiment analysis are the Naive Bayes Algorithm and Support Vector Machine (SVM). This research will implement the two algorithms that are optimized using the PSO algorithms in sentiment analysis. Testing will be done by setting parameters on the PSO in each classifier algorithm. The results of the research that have been done can produce an increase in the accreditation of 15.11% on the optimization of the PSO-based Naive Bayes algorithm. Improved accuracy on the PSO-based SVM algorithm worth 1.74% in the sigmoid kernel.

show abstract

Section: Pendahuluanunclassified

Algorithm Comparation of Naive Bayes and Support Vector Machine based on Particle Swarm Optimization in Sentiment Analysis of Freight Forwarding Services

Anggita

Ikmah

2020

RESTI

View full text Add to dashboard Cite

show abstract

“…In writing tweets, there are usually different letterforms, case folding is a process in text preprocessing that is carried out to uniform the characters in the data. (Jumeilah, 2017) This is a case of case collapsing, input "PSBB effect feels direct lockdown trillions loss", becomes output "psbb effect feeling lockdown direct trillions loss".…”

Section: Case Foldingmentioning

confidence: 99%

Sentiment Analysis on Twitter of PSBB Effect Using Machine Learning

Saputra

Halomoan

Raharjo

et al. 2020

techno

View full text Add to dashboard Cite

A collection of tweets from Twitter users about PSBB can be used as sentiment analysis. The data obtained is processed using data mining techniques (data mining), in which there is a process of mining the text, tokenize, transformation, classification, stem, etc. Then calculated into three different algorithms to be compared, the algorithm used is the Decision Tree, K-NN, and Naïve Bayes Classifier to find the best accuracy. Rapidminer application is also used to facilitate writers in processing data. The highest results from this study were the Decision Tree algorithm with an accuracy of 83.3%, precision 79%, and recall 87.17%.

show abstract

“…Penelitian terkait klasifikasi teks sudah banyak dilakukan diantaranya: analisis data twitter "Make-In-India" dengan menggunakan R yang lakukan oleh Rani dan Rani (2016) untuk memvisualisasikan pendapat dari pengguna Twitter, klasifikasi analisis sentimen terhadap tokoh publik dengan menggunakan metode klasfikikasi Naïve Bayes dan Support Vector Machine (SVM) (Hidayatullah dan Azhari, 2014), pengklasifikasian penelitian dengan SVM untuk memudahkan pencarian penelitian yang memiliki kategori yang sama (Jumeilah, 2017) dan analisis sentimen masyarakat berdasarkan emoticon pada data tweets tentang film (Kiruthika et al, 2016).…”

Section: Pendahuluanunclassified

Klasifikasi Opini Masyarakat Terhadap Jasa Ekspedisi JNE dengan Naïve Bayes

Jumeilah¹

2018

J. Sistem Info. Bisnis

Self Cite

View full text Add to dashboard Cite

The large number of online sales transactions has increased the number of service users. One of the companies engaged in the delivery service in Indonesia is Tiki Nugraha Ekakurir or more known JNE. Currently, JNE service users reach 14.000.000 per month. JNE has used many media communications with its customers one of them with Twitter. The number of followers of JNECare is 108,000 and the number of tweets is 375,000. The number of comments for people who can be used to see what they think of JNE is an inseparable comment is a negative, positive or neutral category. To simplify the grouping of comments, the data will be classified using the Naïve Bayes method present in Rstudio. that is changing all the letters into lowercase and other letters other than letters and spaces (case folding), tokenizing words, and the removal of the word common (stopword remove). After the data is cleared the data will be labeled manually one by one and new data can be used for the training process to get the probability model for each category. Probailitas obtained by using Naïve bayes algorithm. Models obtained from the training will be used using data testing. The categories obtained from the test will be used to process the data used by using the confusion matrix and will calculate the accuracy, precision and recall. From the results of the classification of JNE comments obtained that Naïve Bayes was able to classify the data well. This is evidenced by the average percentage accuracy of 85%, 78% precision and 67% recall. AbstrakBanyaknya jumlah transaksi penjualan online membuat bertambahnya pengguna jasa pengiriman. Salah satu perusahaan yang bergerak di bidang jasa pengiriman di Indonesia adalah Tiki Jalur Nugraha Ekakurir atau lebih dikenal JNE. Saat ini, pengguna jasa JNE mencapai 14.000.000 perbulan. JNE telah memanfaatkan banyak media komunikasi dengan pelanggannya salah satunya dengan Twitter. Jumlah followers dari JNECare adalah 108.000 dan jumlah tweets sebanyak 375.000. Banyaknya komentar pelanggan dapat dimanfaatkan untuk melihat gambaran opini mereka tentang JNE apakah komentar dominan adalah kategori negatif, positif atau netral. Untuk mempermudah pengelompokan komentar, data akan diklasifikasi menggunakan metode Naïve Bayes yang ada pada Rstudio. Jumlah data yang digunakan dalam penelitian berjumlah 1725 tweets. Data akan dibagi duga 70% data training sebanyak 1208 data dan 30% data testing atau sebanyak 517 data. Sebelum data diklasifikasi data sebelumnya harus melalui proses preprocessing yaitu mengubah semua karakter huruf menjadi lowercase dan membuang karakter selain huruf dan spasi (case folding), pemotongan kata (tokenizing), dan penghapusan kata umum (stopword removing). Setelah data dibersihkan data akan dilabeli secara manual satu persatu dan baru data dapat digunakan untuk proses training untuk mendapatkan model probabilitas untuk setiap kategori. Probailitas diperoleh dengan menggunakan algoritma Naïve bayes. Model yang diperoleh dari tahap training akan diuji dengan menggunakan data testing. Kategori y...

show abstract

Penerapan Support Vector Machine (SVM) untuk Pengkategorian Penelitian

Cited by 45 publications

References 3 publications

Algorithm Comparation of Naive Bayes and Support Vector Machine based on Particle Swarm Optimization in Sentiment Analysis of Freight Forwarding Services

Algorithm Comparation of Naive Bayes and Support Vector Machine based on Particle Swarm Optimization in Sentiment Analysis of Freight Forwarding Services

Sentiment Analysis on Twitter of PSBB Effect Using Machine Learning

Klasifikasi Opini Masyarakat Terhadap Jasa Ekspedisi JNE dengan Naïve Bayes

Contact Info

Product

Resources

About