Sentiment Analysis of School Zoning System On Youtube Social Media Using The K-Nearest Neighbor With Levenshtein Distance Algorithm

Anggraini, Nenny; Tursina, Muhammad Jabal

doi:10.1109/citsm47753.2019.8965407

Cited by 16 publications

(9 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In previous studies, using word embedding combining with CNN achieve the accuracy of 76.2% [5], while use SVM with a classification accuracy of 84% [6], 79.412% [7] and 62.76% [8]. Model in our study also better than research that was using K-Nearest Neighbor and Levenshtein Distance (65,625%) [10], and using Naive Bayes (81%) [13]. Now, if we observed in Tables 3 and 4, using TF or TF-IDF as feature extraction does not show a significant difference in the accuracy results.…”

Section: Resultsmentioning

confidence: 52%

See 1 more Smart Citation

Comparison of the Effects of Feature Selection and Tree-Based Ensemble Machine Learning for Sentiment Analysis on Indonesian YouTube Comments

Khomsah¹,

Hidayatullah

Aribowo

2021

Proceedings of the 1st International Conference on Electronics, Biomedical Engineering, and Health Informatics

View full text Add to dashboard Cite

The main problems in sentiment analysis models on Indonesian YouTube comments are unstructured data and low classification accuracy. Sentiment analysis for Indonesian, which is different from English, requires proper preprocessing and classification methods. Previous research usually using Linear Support Vector Machine (SVM), Naïve Bayes and Decision Tree. Although the accuracy of SVM is better than other algorithms, it still needs to be improved. This study aims to compare the performance of the tree-based ensemble method and feature selection to improve the sentiment analysis model for Indonesian YouTube comments. This research crawled Indonesian YouTube comments from different domains and produce ten datasets. The preprocessing's method in this research was removed stopword, convert slang words, and stemming. For feature selection, we tested two vectorizer method, i.e. Term Frequency (TF) or Term Frequency/Inverse Document Frequency (TF-IDF). The model build using six machine learning, consist of four tree-based ensemble machine learning to raise better accuracy, Linear SVM and Decision Tree. We use tree-based ensemble machine learning, they are Random Forest, and Extra Tree represents bagging ensemble. AdaBoost and Gradient Boosting represent boosting ensemble. SVM and Decision tree as a comparison. Based on experiments by combining feature selection and ensemble machine learning, it can be concluded that the type of vectorizer has little effect on

show abstract

Section: Resultsmentioning

confidence: 52%

“…Another study developed a combination of K-Nearest Neighbor and Levenshtein Distance. This combination only gets an accuracy of 65,625% [10]. Another study that combines several machine learning methods is the combination of the Naive Bayes and Decision Tree Classifier but does not report its accuracy [11].…”

Section: Literature Reviewmentioning

confidence: 99%

Comparison of the Effects of Feature Selection and Tree-Based Ensemble Machine Learning for Sentiment Analysis on Indonesian YouTube Comments

Khomsah¹,

Hidayatullah

Aribowo

2021

Proceedings of the 1st International Conference on Electronics, Biomedical Engineering, and Health Informatics

View full text Add to dashboard Cite

show abstract

“…This research shows the result of accuracy of 79.412% [9]. Other studies using SVM using the linear kernel function, show an accuracy of 62.76% [10], sentiment analysis using a combination of K-Nearest Neighbor and Levenshtein Distance, show the accuracy of 65.625% [11]. Other research on sentiment analysis uses Naive Bayes Classifier and Decision Tree Classifier and preprocessing using emoji deletion of punctuation removal, number correction of non-standard words, and POS-Tagging [12].…”

Section: Literature Reviewmentioning

confidence: 53%

An Evaluation of Preprocessing Steps and Tree-based Ensemble Machine Learning for Analysing Sentiment on Indonesian YouTube Comments

Aribowo

Basiron

Suryana

et al. 2020

IJATCSE

View full text Add to dashboard Cite

This study aims to find the best model for the sentiment analysis of Indonesian YouTube video comments. Datasets crawled from YouTube video comments about government services related to COVID-19 pandemic in Indonesia. There are two opinion datasets obtained from two different domains, different characteristics, and errors. The problem is that comments from YouTube videos are very unstructured, containing spelling, diction, and slang word errors. The scenario for the solution of the problem is to test several preprocessing techniques, including standard preprocessing such as stop word removal, slang word, emoticon conversion, and stemming. Feature extraction using count vectorizer and TF-IDF method. For the development of the model, five types of models were tested, namely Naive Bayes (NB), Support Vector Machine (SVM), Decision Tree, Random Forest, and Extra Tree classifier. The result is a model with a maximum accuracy of 89.68% using a combination of standard preprocessing (converting emoticons and handling unstructured words), the count vectorizer feature extraction, and Extra Tree model classifier.

show abstract

“…The KNN algorithm saves all existing data and classifies fresh data points according to their similarity. This implies that new data present can be quickly sorted into a well-suited category using the KNN algorithm as it arises [22]- [23]. The KNN algorithm is a non-parametric algorithm, which means it makes no assumptions about the data [24], [25].…”

Section: K-nearest Neighbors (Knn) Techniquementioning

confidence: 99%

The significance of artificial intelligent technique in classifying various grades of agarwood oil

Amidon

Huzir

Yusoff

et al. 2022

IJEECS

View full text Add to dashboard Cite

Agarwood oil quality is often separated into two or three categories. This makes classifying agarwood oil quality using current methods difficult. Current approaches rely solely on human perception to determine the quality of agarwood, whether in raw material or oil. This technique has other undesirable implications. It can affect the human sensory system, particularly the eyes and nose. Categorization takes time, which is a considerable expense to succeed in this method. As a result, a new classification system should be devised. The chemical components in agarwood oil are used to classify it in this study. In this study, samples with preprocessing data from two to five quality levels were used. The purpose is to categorize this data based on its qualities and analyze whether this new quality group is acceptable. The K-nearest neighbours (KNN) approach was used to classify all samples and their properties for this dataset. All samples may be correctly classified by grade without any errors. This shows the chemical compound-based classification of agarwood oil can be retained. With these findings, future agarwood oil research may focus on building a new classification.

show abstract

Sentiment Analysis of School Zoning System On Youtube Social Media Using The K-Nearest Neighbor With Levenshtein Distance Algorithm

Cited by 16 publications

References 1 publication

Comparison of the Effects of Feature Selection and Tree-Based Ensemble Machine Learning for Sentiment Analysis on Indonesian YouTube Comments

Comparison of the Effects of Feature Selection and Tree-Based Ensemble Machine Learning for Sentiment Analysis on Indonesian YouTube Comments

An Evaluation of Preprocessing Steps and Tree-based Ensemble Machine Learning for Analysing Sentiment on Indonesian YouTube Comments

The significance of artificial intelligent technique in classifying various grades of agarwood oil

Contact Info

Product

Resources

About