Analisis Sentimen Nasabah pada Layanan Perbankan Menggunakan Metode Regresi Logistik Biner, Naïve Bayes Classifier (NBC), dan Support Vector Machine (SVM)

Sari, Erna Dwi Nurindah; Irhamah, Irhamah

doi:10.12962/j23373520.v8i2.44565

Cited by 7 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In addition, there are also several studies that compare several classification algorithms to get the most superior. Some of them are in research [20], [21] compared the Support Vector Machine and Naïve Bayes algorithms to conclude that the Naïve Bayes algorithm is superior because it produces a higher accuracy value. Another study compared the NBC, KNN and Decision Tree algorithms, the analysis resulted in the NBC algorithm producing the highest accuracy value compared to other methods, namely 100% [22].…”

Section: Literature Studymentioning

confidence: 99%

Sentiment Analysis of the Use of Digital Banking Service Applications On Google Play Store Reviews Using Naïve Bayes Method

Amalia Nur Soliha,

Tb Ai Munandar,

Muhammad Yasir

2023

IJITCSA

View full text Add to dashboard Cite

The development of the financial system is characterized by the emergence of digital banking service applications that are widely circulated and can be accessed for free. With so many applications, users often feel confused in choosing which applications are safe to use. Before downloading an application on the Google Play Store, users will usually look at ratings and reviews first. However, the title of the best application cannot be pinned if only seen from the rating and number of downloads. This research was conducted to analyze sentiment on user reviews of digital banking service applications on the Google Play Store using the NBC (Naïve Bayes Classifier) method. Research using the NBC algorithm produced an accuracy value of 81% on the classification of Allo Bank reviews and 78% on the classification of Line Bank reviews

show abstract

Section: Literature Studymentioning

confidence: 99%

Sentiment Analysis of the Use of Digital Banking Service Applications On Google Play Store Reviews Using Naïve Bayes Method

Amalia Nur Soliha,

Tb Ai Munandar,

Muhammad Yasir

2023

IJITCSA

View full text Add to dashboard Cite

show abstract

“…Metode ini akan mentransformasi bentuk teks menjadi bentuk numerik agar dapat digunakan untuk pemodelan. Hasil pembobotan dengan TF-IDF akan diketahui tingkat kepentingan suatu kata terhadap kumpulan twit berdasarkan frekuensi kemunculannya (Sari & Irhamah, 2020). Term Frequency (TF) adalah frekuensi munculnya kata dalam suatu dokumen sedangkan Document Frequency (DF) adalah banyaknya dokumen yang mengandung kata tertentu.…”

Section: Term Frequency-inverse Document Frequency (Tf-idf)unclassified

Sentiment Analysis of Twitter Users’ Opinion Towards Face-to-Face Learning

Manaf,

Alamudi,

Fitrianto

2023

IJSA

View full text Add to dashboard Cite

In early 2022, the government allowed face-to-face learning again after approximately one year of online learning. When face-to-face learning will be held again in several areas, the number of Covid-19 has increased and the government has imposed the enforcement of restrictions on community activities. The pros and cons of face-to-face learning also occur on social media, one of them is on Twitter. This study used twitter data for January 30th – February 7th 2022. Opinions on twitter regarding face-to-face learning were studied by sentiment analysis using the binary logistic regression method with sentiment classes being positive and negative. Labeling uses based on the final score of the difference between the number of positive and negative words. The purpose of this study is to determine the public’s perception of the policy of implementing face-to-face learning in the era of the Covid-19 on social media especially Twitter. From this study, public’s perception tends to be in a negative direction which indicates that they have not agreed enough with the existence of face-to-face learning in the period of February 2022 with the accuracy was 85%, sensitivity was 77%, specificity was 88%, and AUC was 91%.

show abstract

“…Penelitian ini menjelaskan bagimana metode SVM dan KNN digunakan untuk menganalisis suatu topik berupa "Investasi dimasa pandemic". Metode SVM digunakan untuk pengklasifikasian suatu prediksi dengan memisahkan dua fungsi kelas yang berbeda secara optimal [9]. Sedangkan metode KNN digunakan unurk mencari objek pada data train yang dekat atau mirip dengan data testing [10].…”

Section: Pendahuluanunclassified

“…Pembobotan TF -IDF dilakukan untuk melakukan pembobotan pada model vektor , pembobotan dilakukan untuk mencari frekuensi kemunculannya kata pada kumpulan dataset. TF (Term Frequency) menunjukan frekuensi kata yang muncul, sedangkan IDF(Inverse Document Frequency) menghitung frekuensi kemunculan kata , dengan cara mengalikan TF dengan IDF [9]. Rumus :…”

Section: Pembobotan Tf-idfunclassified

Analisis Sentimen Kepuasan Investasi Pada Masa Pandemi dengan Metode Support Vector Machine dan K-Nearest Neighbors

Fauziah

2022

STRING

View full text Add to dashboard Cite

Investasi merupakan kegiatan untuk menanamkan asset kepada orang atau lembaga tertentu agar mendapakan keuntungan dengan jangka waktu tertentu. Investasi tak hanya dilakukan untuk jangka pendek, investasi juga bisa untuk menabung yang digunakan untuk masa depan. Investasi kini menjadi trend semenjak pandemi melanda. Banyak sekali orang ikut terjun kedalam dunia ini dengan harapan mendapatkan keuntungan yang sangat menjanjikan, baik dari usia remaja maupun dewasa, mereka sudah mencoba terjun kedalam dunia investasi. Namun sebagian orang masih kurang paham tentang cara berinvestasi yang benar, sehingga resiko yang dihadapi juga cukup tinggi karena akan berdampak pada keuntungan yang didapat. Terlebih lagi pada masa pandemi saat ini inflasi terhadap nilai Indeks Harga Saham Gabungan bisa mengalami fluktuasi seiring dengan terjadinya berbagai hal. Penelitian ini bertujuan untuk meninjau bagaimana respon masyarakat dalam melakukan investasi dimasa pandemi saat ini. Penelitian menggunakan metode Support Vector Machine dan K-Nearest Neighbors. Dengan menggunakan metode Support Vector Machine dan K-Nearest Neighbors dapat dilihat SVM lebih baik dibandingkan KNN. Dengan nilai akurasi SVM sebanyak 96.84% dan KNN sebanyak 95.74% dengan selisih akurasi kedua metode 1.10%.

show abstract

Analisis Sentimen Nasabah pada Layanan Perbankan Menggunakan Metode Regresi Logistik Biner, Naïve Bayes Classifier (NBC), dan Support Vector Machine (SVM)

Cited by 7 publications

References 0 publications

Sentiment Analysis of the Use of Digital Banking Service Applications On Google Play Store Reviews Using Naïve Bayes Method

Sentiment Analysis of the Use of Digital Banking Service Applications On Google Play Store Reviews Using Naïve Bayes Method

Sentiment Analysis of Twitter Users’ Opinion Towards Face-to-Face Learning

Analisis Sentimen Kepuasan Investasi Pada Masa Pandemi dengan Metode Support Vector Machine dan K-Nearest Neighbors

Contact Info

Product

Resources

About