Class Imbalanced Learning Menggunakan Algoritma Synthetic Minority Over-sampling Technique – Nominal (SMOTE-N) pada Dataset Tuberculosis Anak

Kurniawati, Yulia Ery

doi:10.24002/jbi.v10i2.2441

Cited by 12 publications

(10 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This indicates that using SMOTE can increase the accuracy value of k-NN performance in classifying datasets based on negative and positive sentiments. [15] shows that SMOTE utilizes nearest neighbors and an adjustable Figure 5 shows that the AUC value of k-NN using SMOTE obtained a better accuracy value compared to not using SMOTE. [16] argues that data imbalances can occur when the objects of one data class are more numerous in quantity compared to other courses.…”

Section: Resultsmentioning

confidence: 99%

Sentiment Analysis on Customer Perception towards Products and Services of Restaurant in Labuan Bajo

Singgalen

2022

Journal-ISI

View full text Add to dashboard Cite

Analysis of consumer sentiment towards restaurant products and services in the form of reviews on various digital platforms such as Tripadvisor determines business sustainability and the image of tourist destinations. This study aims to classify visitor sentiments as Tripadvisor users towards Happy Banana Komodo, MadeInItaly, Mediterraneo, and La Cucina restaurants in Labuan Bajo. The research stages are divided into three parts, namely the stages of data collection, data processing, classification and evaluation of model performance, and interpretation of data and information. At the data collection stage, Tripadvisor user reviews of products and services at each restaurant are mined using the Webharvy application based on the configuration of the customer name, date of examination, rating, review title, and review. The data mining results are cleaned and prepared to be managed using the RapidMiner application at the data processing stage. The classification and evaluation stage of model performance is the implementation and testing of classification algorithms that are relevant to the dataset, namely Decision Tree (DT), Naïve Bayes (NB), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN). The findings of this study indicate the implementation of the positive and negative sentiment classification method for the comprehensive review data from the Tripadvisor website for the products and services of restaurants Happy Banana Komodo, MadeInITaly, Mediterraneo, and La Cucina Restaurants are relevant with k-Nearest Neighbor (k-NN) with accuracy value of 99.27% , a precision value of 100%, and a recall of 98.53%.

show abstract

Section: Resultsmentioning

confidence: 99%

Sentiment Analysis on Customer Perception towards Products and Services of Restaurant in Labuan Bajo

Singgalen

2022

Journal-ISI

View full text Add to dashboard Cite

show abstract

“…Barro et al berpendapat bahwa ketidakseimbangan data akan terjadi apabila jumlah objek di suatu kelas data memiliki kuantitas yang lebih tinggi dibandingkan dengan kelas lain, dimana kelas data yang objeknya lebih banyak disebut kelas mayor sedangkan yang lain disebut minor [20]. Disisi lain, Kurniawati menekankan bahwa pengolahan algoritma yang tidak mempertimbangkan ketidakseimbangan data cenderung menitikberatkan kelas mayor dan bukan kelas minor, oleh sebab itu diperlukan teknik SMOTE yang menggunakan metode oversampling untuk memperbanyak pengamatan secara acak dengan menambah jumlah data kelas minor (data buatan) agar setara dengan kelas mayor [21]. Adapun, data buatan atau sintesis tersebut dibuat berdasarkan k-tetangga terdekat (k-Nearest Neighbor).…”

Section: Synthetic Minority Oversampling Technique (Smote)unclassified

Analisis Sentimen Wisatawan terhadap Taman Nasional Bunaken dan Top 10 Hotel Rekomendasi Tripadvisor Menggunakan Algoritma SVM dan DT berbasis CRISP-DM

Singgalen

2023

JoSYC

View full text Add to dashboard Cite

It is necessary to analyze traveler sentiment towards Bunaken National Park and Tripadvisor's Top 10 Recommended Hotels to identify traveler satisfaction with the attractions, accommodation services, and transportation used. Considering this, this study uses the Cross-Industry Standard Process for Data Mining (CRISP-DM) framework by testing the performance of the Decision Tree (DT) algorithm and the Support Vector Machine (SVM). CRISP-DM has six stages: business understanding, data understanding, data preparation, modeling, evaluation, and deployment. Based on the processing of 398 Bunaken National Park destination data and 1793 review data on the top 10 hotels recommended by Tripadvisor, the SVM algorithm performed better. In the context of Bunaken National Park destination data, the performance of the SVM algorithm using the SMOTE operator can produce 100% accuracy, precision, recall, f-measure, AUC, and t-Test values. In addition, in processing the top 10 hotel datasets recommended by Tripadvisor, the SVM algorithm using the SMOTE operator provides an accuracy value of 96.42%, a precision value of 100%, a recall value of 92.83%, an f-measure value of 96.27%, an AUC value of 100%, and a t-Test value of 96.4%. The results of identifying the five words that most often appear in tourist reviews for Bunaken Marine Park tourist destinations are 164 words fish, 165 words island, 193-word dive, 230 diving, and 280 words Bunaken. This indicates the driving factor for tourist visits to Bunaken Marine Park is the beauty of underwater nature, including the diversity of marine animal species, the natural beauty of the archipelago, and diving activities. In addition, the results of identifying the five words that most often appear in traveler reviews for Tripadvisor's top 10 recommended hotels are 1170 great words, 1222 bunaken words, 1550 resort words, 1613 diving words, and 1711 dive words. This indicates that the characteristics of tourists who have the motive of traveling to Bunaken National Tourism Park have the intention to use resort accommodations around Bunaken and have mobility and facilities to support diving activities. Thus, the output of this study can be used as a recommendation for accommodation service managers to prepare supporting facilities for tourists who want to visit Bunaken National Park.

show abstract

“…SMOTE menghasilkan contoh sintetis dari kelas minoritas yang dioperasikan di dalam ruang fitur daripada di dalam ruang data [3]. Teknik ini menambahkan contoh dari kelas minoritas dengan cara mengekstrak sampel data minoritas yang ada dengan menggunakan sampel acak yang diambil dari nilai k tetangga terdekat [17]. Dengan demikian, SMOTE menghasilkan contoh sintetis baru yang dapat memperluas area keputusan dari kelas minoritas.…”

Section: Gambar 1 Skema Penelitianunclassified

Penerapan Metode Oversampling SMOTE Pada Algoritma Random Forest Untuk Prediksi Kebangkrutan Perusahaan

Nugroho

Rilvani²

2023

View full text Add to dashboard Cite

Kemajuan teknologi informasi berkembang kearah finansial dalam melakukan prediski. Banyak model algoritma prediksi data keuangan telah dikembangkan. Prediksi kebangkrutan merupakan sesuatu yang sangat penting bagi organisasi atau perusahaan dalam mengambil keputusan yang diperlukan oleh pemodal dan investor. Prediksi kebangkrutan termasuk dalam permasalahan ketidakseimbangan kelas dalam model kalsifikasi karena jumlah data yang termasuk dalam kelas bangkrut jauh lebih sedikit dibandingkan dengan data yang termasuk dalam kelas tidak bangkrut. Tujuan dari penelitian ini adalah untuk menghasilkan model klasifikasi yang baik untuk prediksi risiko kebangkrutan pada perusahaan. preprocessing data dilakukan untuk melakukan optimasi algoritma klasifikasi dengan metode oversampling SMOTE agar menghasilkan model kalsifikasi yang optimal. Algoritma klasifikasi yang digunakan adalah Random Forest Classification untuk mendapatkan hasil prediksi kebangkrutan yang optimal. Berdasarkan hasil pengujian yang telah dilakukan didapatkan bahwa performa klasifikasi meningkat sebesar 7,40% setelah dilakukan preprocessing data dengan menggunakan teknik oversampling SMOTE pada algoritma Random Forest Classifier.

show abstract

Class Imbalanced Learning Menggunakan Algoritma Synthetic Minority Over-sampling Technique – Nominal (SMOTE-N) pada Dataset Tuberculosis Anak

Cited by 12 publications

References 0 publications

Sentiment Analysis on Customer Perception towards Products and Services of Restaurant in Labuan Bajo

Sentiment Analysis on Customer Perception towards Products and Services of Restaurant in Labuan Bajo

Analisis Sentimen Wisatawan terhadap Taman Nasional Bunaken dan Top 10 Hotel Rekomendasi Tripadvisor Menggunakan Algoritma SVM dan DT berbasis CRISP-DM

Penerapan Metode Oversampling SMOTE Pada Algoritma Random Forest Untuk Prediksi Kebangkrutan Perusahaan

Contact Info

Product

Resources

About