Implementation Of K-Nearest Neighbor Algorithm With SMOTE For Hotel Reviews Sentiment Analysis

Mahmud, Firman Gazali; Hermanto, Teguh Iman; Nugroho, Imam Maruf

doi:10.33395/sinkron.v8i2.12214

Cited by 2 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results obtained are the k-NN method which is capable of classifying with an accuracy of 79%. Hotel reviews in e-commerce applications using k-NN produce an accuracy of 87% [11].…”

Section: Introductionmentioning

confidence: 99%

Unbalanced Multiclass Classification With Adaptive Synthetic Multinomial Naive Bayes Approach

Fauzi,

Ismatullah,

Manfaati Nur

2023

IAPGOS

View full text Add to dashboard Cite

Opinions related to rising fuel prices need to be seen and analysed. Public opinion is closely related to public policy in Indonesia in the future. Twitter is one of the media that people use to convey their opinions. This study uses sentiment analysis to look at this phenomenon. Sentiment is divided into three categories: positive, neutral, and negative. The methods used in this research are Adaptive Synthetic Multinomial Naive Bayes, Adaptive Synthetic k-nearest neighbours, and Adaptive Synthetic Random Forest. The Adaptive Synthetic method is used to handle unbalanced data. The data used in this study are public arguments per province in Indonesia. The results obtained in this study are negative sentiments that dominate all provinces in Indonesia. There is a relationship between negative sentiment and the level of education, internet use, and the human development index. Adaptive Synthetic Multinomial Naive Bayes performed better than other methods, with an accuracy of 0.882. The highest accuracy of the Adaptive Synthetic Multinomial Naive Bayes method is 0.990 in Papua Barat Province.

show abstract

“…The results obtained are the k-NN method which is capable of classifying with an accuracy of 79%. Hotel reviews in e-commerce applications using k-NN produce an accuracy of 87% [11].…”

Section: Introductionmentioning

confidence: 99%

Unbalanced Multiclass Classification With Adaptive Synthetic Multinomial Naive Bayes Approach

Fauzi,

Ismatullah,

Manfaati Nur

2023

IAPGOS

View full text Add to dashboard Cite

show abstract

Data oversampling and imbalanced datasets: an investigation of performance for machine learning and feature engineering

Mujahid,

Kına,

Rustam

et al. 2024

J Big Data

View full text Add to dashboard Cite

The classification of imbalanced datasets is a prominent task in text mining and machine learning. The number of samples in each class is not uniformly distributed; one class contains a large number of samples while the other has a small number. Overfitting of the model occurs as a result of imbalanced datasets, resulting in poor performance. In this study, we compare different oversampling techniques like synthetic minority oversampling technique (SMOTE), support vector machine SMOTE (SVM-SMOTE), Border-line SMOTE, K-means SMOTE, and adaptive synthetic (ADASYN) oversampling to address the issue of imbalanced datasets and enhance the performance of machine learning models. Preprocessing significantly enhances the quality of input data by reducing noise, redundant data, and unnecessary data. This enables the machines to identify crucial patterns that facilitate the extraction of significant and pertinent information from the preprocessed data. This study preprocesses the data using various top-level preprocessing steps. Furthermore, two imbalanced Twitter datasets are used to compare the performance of oversampling techniques with six machine learning models including random forest (RF), SVM, K-nearest neighbor (KNN), AdaBoost (ADA), logistic regression (LR), and decision tree (DT). In addition, the bag of words (BoW) and term frequency and inverse document frequency (TF-IDF) features extraction approaches are used to extract features from the tweets. The experiments indicate that SMOTE and ADASYN perform much better than other techniques thus providing higher accuracy. Additionally, overall results show that SVM with ’linear’ kernel tends to attain the highest accuracy and recall score of 99.67% and 1.00% on ADASYN oversampled datasets and 99.57% accuracy on SMOTE oversampled dataset with TF-IDF features. The SVM model using 10-fold cross-validation experiments achieved 97.40 mean accuracy with a 0.008 standard deviation. Our approach achieved 2.62% greater accuracy as compared to other current methods.

show abstract

Implementation Of K-Nearest Neighbor Algorithm With SMOTE For Hotel Reviews Sentiment Analysis

Cited by 2 publications

References 12 publications

Unbalanced Multiclass Classification With Adaptive Synthetic Multinomial Naive Bayes Approach

Unbalanced Multiclass Classification With Adaptive Synthetic Multinomial Naive Bayes Approach

Data oversampling and imbalanced datasets: an investigation of performance for machine learning and feature engineering

Contact Info

Product

Resources

About