Comparing Sentiment Analysis of Indonesian Presidential Election 2019 with Support Vector Machine and K-Nearest Neighbor Algorithm

Firmansyah, Fiki; Zulfikar, Wildan Budiawan; Maylawati, Dian Sa’adillah; Arianti, Nunik Destria; Muliawaty, Lia; Septiadi, Muhammad Andi; Ramdhani, Muhammad Ali

doi:10.1109/icced51276.2020.9415767

Cited by 13 publications

(13 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Stemming technique [1], [5]- [7], [9]- [12] has the advantage of being able to change words into basic forms (removing affixes). This step can reduce the analysis process on unnecessary text.…”

Section: Introductionmentioning

confidence: 99%

“…Several classification algorithms show good results in classifying sentiment analysis. These algorithms include NB [17], kNN [9], [12], [17], SVM [4], [6], [9]- [16], [18], and DL [19]- [21]. Research by Shaban et al [22] in his study yielded an accuracy of 98% with a classification using NB.…”

Section: Introductionmentioning

confidence: 99%

“…SVM has been used in research on several system areas, such as: presidential election [12], health record data [18], customer satisfaction [16], fake consumer reviews [6], restaurant review [9], flood disaster news [14], Vietnamese [15], product reviews [4], [11]. The accuracy is quite high in research using the SVM algorithm.…”

Section: Introductionmentioning

confidence: 99%

“…In the presidential election system, the accuracy is 76.5% [12], customer satisfaction system 84.85% [18], and product reviews with accuracy 88.13% [11]. Various datasets are used, including Twitter [10], [12], [14], [16], [18], Cornell University, trip advisor [6], restaurant review [9], Vietnamese [15], product reviews [4], application comments, financial market news [10], and product review Amazon [11]. SVM already has the advantages of support vector and a dividing line (hyperplane) so it takes a little time to classify [12].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Improving sentiment reviews classification performance using support vector machine-fuzzy matching algorithm

Nurcahyawati¹,

Mustaffa

2023

Bulletin EEI

View full text Add to dashboard Cite

High dimensionality in data sets is one of the challenges faced in classification, data mining, and sentiment analysis. In the data set, many dimensionalities require effort to simplify. Many of these dimensionalities have a major impact on the complexity and performance of the algorithms used for classification. Various challenges were encountered, including how to determine the optimal combination of pre-processing techniques, how to clean the dataset, and determine the best classification algorithm. This study uses a new approach based on the combination of three powerful techniques which are: tokenizing-lowercasing-stemming (for series of preprocessing), support vector machine (SVM) for supervised classification, and fuzzy matching (FM) for dimensionality reduction. The proposed model was realized using 3 different datasets, namely Amazon product review, movie review, and airline review from Twitter. This study provides better findings than the previous results. Improved performance is generated by SVM combined with FM, resulting in 96% accuracy. So that the SVM-FM combination can be said to be the best combination for sentiment analysis on the given data set.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving sentiment reviews classification performance using support vector machine-fuzzy matching algorithm

Nurcahyawati¹,

Mustaffa

2023

Bulletin EEI

View full text Add to dashboard Cite

show abstract

“…Kemudian Gambar 6 menunjukkan literatur Naive K-NN yang diteliti adalah literatur terbitan tahun 2015-2021 [14], [16], [22], [24]- [28]. Berikutnya, Gambar 7 menunjukkan literatur SVM yang diteliti adalah literatur terbitan tahun 2015-2020 [16], [21]- [23], [27], [29]- [34].…”

Section: B Conductingunclassified

Text Mining Literature Review on Indonesian Social Media

Thenata

2021

JEPIN

View full text Add to dashboard Cite

Era sekarang jumlah berita dari berbagai media sosial yang tersebar dalam waktu singkat dan kebutuhan masyarakat untuk mengkonsumsi berita dalam berbagai referensi dapat mempengaruhi kehidupan masyarakat. Hal ini menyebabkan data yang tersebar dapat dikumpulkan dan dimanfaatkan oleh pemerintah, pengusaha, analisis, ataupun peneliti untuk mengidentifikasi tren, mengembangkan bisnis, memprediksi perilaku pelanggan dan lain sebagainya. Pengumpulan data berita dari media sosial tersebut dapat menggunakan text mining yang melibatkan algoritma yakni Naive Bayes, K-NN, dan SVM. Namun, penggunaan algoritma pada studi kasus yang tidak sesuai dapat memberikan hasil yang tidak optimal. Oleh karena itu, penelitian ini akan menganalisis algoritma text mining yang diimplementasikan pada media sosial berbahasa Indonesia dengan memakai metode systematic literature review. Metode ini dimulai dengan melakukan tahap planning yang menetapkan pertanyaan penelitian, kata pencarian, sumber literatur digital, dan standard literatur. Dilanjutkan dengan tahap conducting yang memilih dan mencocokan standard literatur, serta ekstraksi data. Kemudian tahap reporting yang melakukan analisis hasil ekstraksi data sehingga bisa menemumkan informasi dan pengetahuan. Tolak ukur yang menjadi acuan untuk perbandingan yakni pengujian confusion matrix berupa accuracy, precision, dan recall. Adapun hasil dari penelitian ini ditemukan algoritma Naive Bayes memberikan hasil yang stabil tapi kurang optimal jika diterapkan pada studi kasus media sosial berbahasa Indonesia. Sedangkan algortima K-NN dan SVM ditemukan memberikan hasil yang optimal jika diterapkan pada studi kasus media sosial berbahasa Indonesia yang dibuktikan dengan accuracy (50%-98.13%), precision (58.22%-98.48%), dan recall (21.05%-98%).

show abstract

A Novel Deep Learning-based Sentiment Analysis Method Enhanced with Emojis in Microblog Social Networks

Zhang

et al. 2022

Enterprise Information Systems

View full text Add to dashboard Cite

Comparing Sentiment Analysis of Indonesian Presidential Election 2019 with Support Vector Machine and K-Nearest Neighbor Algorithm

Cited by 13 publications

References 10 publications

Improving sentiment reviews classification performance using support vector machine-fuzzy matching algorithm

Improving sentiment reviews classification performance using support vector machine-fuzzy matching algorithm

Text Mining Literature Review on Indonesian Social Media

A Novel Deep Learning-based Sentiment Analysis Method Enhanced with Emojis in Microblog Social Networks

Contact Info

Product

Resources

About