Review Sentiment Analysis of World Class Hotel Using Naive Bayes Classifier And Particle Swarm Optimization Method

Sentiment analysis is an area of approach that solves problems by using reviews from various relevant scientific perspectives. Reading a review before buying a product is very important to know the advantages and disadvantages of the products we will use, besides reading a cosmetic review can find out the quality of the cosmetic brand is feasible or not be used. Before consumers decide to buy cosmetics, consumers should know in detail the products to be purchased, this can be learned from the testimonials or the results of reviews from consumers who have bought and used the previous product. The number of reviews is certainly very much making consumers reluctant to read reviews. Eventually, the reviews become useless. For this reason, the authors classify based on positive and negative classes, so consumers can find product comparisons quickly and precisely. The implementation of Particle Swarm Optimization (PSO) optimization can improve the accuracy of the Support Vector Machine (SVM) and Naïve Bayes (NB) algorithm can improve accuracy and provide solutions to the review classification problem to be more accurate and optimal. Comparison of accuracy resulting from testing this data is an SVM algorithm of 89.20% and AUC of 0.973, then compared to SVM based on PSO with an accuracy of 94.60% and AUC of 0.985. The results of testing the data for the NB algorithm are 88.50% accuracy and AUC is 0.536, then the accuracy is compared with the PSO based NB for 0.692. In these calculations prove that the application of PSO optimization can improve accuracy and provide more accurate and optimal solutions

Download Full-text

Implemented PSO-NBC and PSO-SVM to Help Determine Status of Volcanoes

Jurnal Penelitian Pos dan informatika ◽

10.17933/jppi.2019.090202 ◽

2019 ◽

Vol 9 (2) ◽

pp. 97

Author(s):

Firman Tempola

Keyword(s):

Particle Swarm Optimization ◽

Naive Bayes ◽

Particle Swarm ◽

Naïve Bayes ◽

Bayes Classifier ◽

Naïve Bayes Classifier ◽

Swarm Optimization ◽

Attribute Weights ◽

The Status ◽

Bayes Algorithm

<p class="JGI-AbstractIsi">This research is a continuation of previous research that applied the Naive Bayes classifier algorithm to predict the status of volcanoes in Indonesia based on seismic factors. There are five attributes used in predicting the status of volcanoes, namely the status of the normal, standby and alerts. The results Showed the accuracy of the resulted prediction was only 79.31%, or fell into fair classification. To overcome these weaknesses and in order to increase accuracy, optimization is done by giving criteria or attribute weights using particle swarm optimization. This research compared the optimization of Naive Bayes algorithm to vector machine support using particle swarm optimization. The research found improvement on system after application of PSO-NBC to that of 91.3 % and 92.86% after applying PSO-SVM.</p>

Download Full-text

Marketplace Sentiment Analysis Using Naive Bayes And Support Vector Machine

PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic ◽

10.33558/piksel.v8i2.2272 ◽

2020 ◽

Vol 8 (2) ◽

pp. 91-100

Author(s):

Muhamad Azhar ◽

Noor Hafidz ◽

Biktra Rudianto ◽

Windu Gata

Keyword(s):

Support Vector Machine ◽

Feature Selection ◽

Particle Swarm Optimization ◽

Sentiment Analysis ◽

Cross Validation ◽

Naive Bayes ◽

Particle Swarm ◽

Naïve Bayes ◽

Support Vector ◽

Swarm Optimization

Abstract Technology implementation in the marketplace world has attracted the attention of researchers to analyze the reviews from customers. The Klik Indomaret application page on GooglePlay is one application that can be used to get information on review data collection. However, getting information on consumer’s opinion or review is not an easy task and need a specific method in categorizing or grouping these reviews into certain groups, i.e. positive or negative reviews. The sentiment analysis study of a review application in GooglePlay is still rare. Therefore, this paper analysis the customer’s sentiment from klikindomaret app using Naive Bayes Classifier (NB) algorithm that is compared to Support Vector Machine (SVM) as well as optimizing the Feature Selection (FS) using the Particle Swarm Optimization method. The results for NB without using FS optimization were 69.74% for accuracy and 0.518 for Area Under Curve (AUC) and for SVM without using FS optimization were 81.21% for accuracy and 0.896 for AUC. While the results of cross-validation NB with FS are 75.21% for accuracy and 0.598 for AUC and cross-validation of SVM with FS is 81.84% for accuracy and 0.898 for AUC, while there is an increase when using the Feature Selection (FS) Particle Swarm Optimization and also the modeling algorithm SVM has a higher value compared to NB for the dataset used in this study. Keywords: Naive Bayes, Particle Swarm Optimization, Support Vector Machine, Feature Selection, Consumer Review.

Download Full-text

Sentiment Analysis Using Naive Bayes Algorithm with Feature Selection Particle Swarm Optimization (PSO) and Genetic Algorithm

International Journal of Advances in Data and Information Systems ◽

10.25008/ijadis.v2i2.1224 ◽

2021 ◽

Vol 2 (2) ◽

Author(s):

Abi Rafdi ◽

Herman Mawengkang Herman ◽

Syahril Efendi

Keyword(s):

Genetic Algorithm ◽

Feature Selection ◽

Particle Swarm Optimization ◽

Sentiment Analysis ◽

Naive Bayes ◽

Confusion Matrix ◽

Particle Swarm ◽

Naïve Bayes ◽

Swarm Optimization ◽

Bayes Algorithm

This study analyzes Sentiment to see opinions, points of view, judgments, attitudes, and emotions towards creatures and aspects expressed through texts. One of Social Media is like Twitter is one of the most widely used means of communication as a research topic. The main problem with sentiment analysis is voting and using the best feature options for maximum results. Either, the most widely known classification method is Naive Bayes. However, Naive Bayes is very sensitive to significant features. That way, in this test, a comparison of feature selection is carried out using Particle Swarm Optimization and Genetic Algorithm to improve the accuracy performance of the Naive Bayes algorithm. Analyses are performed by comparing before and after testing using feature selection. Validation uses a cross-validation technique, while the confusion matrix ??is appealed to measure accuracy. The results showed the highest increase for Naïve Bayes algorithm accuracy when using the feature selection of the Particle Swarm Optimization Algorithm from 60.26% to 77.50%, while the genetic algorithm from 60.26% to 70.71%. Therefore, the choice of the best characteristics is Particle Swarm Optimization which is superior with an increase in accuracy of 17.24%.

Download Full-text

Naive Bayes classifier algorithm and Particle Swarm Optimization for classification of cross selling (Case study: PT TELKOM Jakarta)

2016 4th International Conference on Cyber and IT Service Management ◽

10.1109/citsm.2016.7577589 ◽

2016 ◽

Author(s):

Sfenrianto ◽

Indah Purnamasari ◽

Rizal Broer Bahaweres

Keyword(s):

Particle Swarm Optimization ◽

Naive Bayes ◽

Particle Swarm ◽

Naïve Bayes ◽

Naive Bayes Classifier ◽

Bayes Classifier ◽

Naïve Bayes Classifier ◽

Swarm Optimization

Download Full-text

Analisis Sentiment pada Sosial Media Twitter Menggunakan Naїve Bayes Classifier dengan Feature Selection Particle Swarm Optimization dan Term Frequency

Jurnal Informatika Universitas Pamulang ◽

10.32493/informatika.v2i1.1500 ◽

2017 ◽

Vol 2 (1) ◽

pp. 14

Author(s):

Yono Cahyono

Keyword(s):

Feature Selection ◽

Particle Swarm Optimization ◽

Naive Bayes ◽

Particle Swarm ◽

Naïve Bayes ◽

Naive Bayes Classifier ◽

Bayes Classifier ◽

Naïve Bayes Classifier ◽

Swarm Optimization ◽

Term Frequency

Pengguna media sosial saat ini sangat besar; dimana setiap orang mengungkapkan pendapat; komentar; kritik dan lain-lain. Data tersebut memberikan informasi yang berharga untuk dapat membantu orang atau organisasi dalam pengambilan keputusan. Jumlah data yang sangat besar tidak mungkin bagi manusia untuk membaca dan menganalisis secara manual. Ansalisis Sentiment merupakan proses dalam menganalisis; memahami; dan mengklasifikasi pendapat; evaluasi; penilaian; sikap; dan emosi terhadap suatu entitas tertentu seperti produk; jasa; organisasi; individu; peristiwa; topik; guna mendapatkan informasi. Penelitian ini bertujuan untuk memisahkan tweets berbahasa Indonesia pada media sosial twitter kedalam kategori positif; negatif dan netral. Metode naїve bayes Classifier (NBC) dengan feature selection Particle Swarm Optimization (PSO) diterapkan pada dataset untuk mengurangi atribut yang kurang relevan pada saat proses klasifikasi. Hasil pengujian menunjukan bahwa algoritma Naïve Bayes Classifier dengan feature selection Particle Swarm Optimization (PSO) menggunakan parameter term frequency (TF) dengan akurasi 97;48%.

Download Full-text

Analisis Sentimen Vaksinasi Covid-19 Pada Twitter Menggunakan Naive Bayes Classifier Dengan Feature Selection Chi-Squared Statistic dan Particle Swarm Optimization

Jurnal SISKOM-KB (Sistem Komputer dan Kecerdasan Buatan) ◽

10.47970/siskom-kb.v5i1.228 ◽

2021 ◽

Vol 5 (1) ◽

pp. 49-56

Author(s):

Ristasari Dwi Septiana ◽

Agung Budi Susanto ◽

Tukiyat Tukiyat

Keyword(s):

Feature Selection ◽

Particle Swarm Optimization ◽

Naive Bayes ◽

Particle Swarm ◽

Naïve Bayes ◽

Naive Bayes Classifier ◽

Bayes Classifier ◽

Naïve Bayes Classifier ◽

Swarm Optimization ◽

Chi Squared

Tingginya penyebaran Covid-19 semakin berdampak pada bidang kesehatan, ekonomi, bahkan bidang pendidikan di Indonesia, sehingga pemerintah Indonesia melakukan tindakan vaksinasi Covid-19 guna menekan tingkat penyebaran Covid-19 di Indonesia. Namun hal tersebut dinilai kotroversial sehingga menarik perhatian masyarakat untuk memberikan opini di berbagai media seperti media sosial twitter. Sehingga membutuhkan analisa sentimen masyarakat terhadap upaya pemerintah pada tindakan vaksinasi Covid-19 untuk mencapai hasil prediksi dengan nilai akurasi paling optimal. Proses crawling secara otomatis menggunakan tools Rapidminer akan mengambil data tweets yang mengandung 5 (lima) kata kunci, yaitu “Vaksin Sinovac”, “Vaksin Astrazeneca”, “Vaksin Moderna”, “Vaksin Merah Putih”, dan “Vaksinasi Covid-19”. Dataset tweets didapatkan dari tanggal 4 Agustus 2021 sampai 12 Agustus 2021. Dataset diperoleh sejumlah 2060 tweets dan diberi label secara manual didapatkan jumlah tweet sebanyak 1193 sentimen positif, 73 negatif, dan 794 netral. Data tersebut dianalisa dengan menggunakan Metode Feature Selection Chi-Squared Statistic dan Particle Swarm Optimization (PSO) untuk mengurangi atribut yang kurang relevan pada saat proses klasifikasi dengan algoritma Naive Bayes Classifier (NBC). Hasil pengujian menunjukan bahwa Algoritma Naive Bayes Classifier (NBC) tanpa Feature Selection mendapatkan nilai akurasi 63,69%. Hasil penelitian menunjukkan bahwa Algoritma Naive Bayes Classifier (NBC) dengan Feature Selection Chi-Squared Statistic mempunyai tingkat akurasi 69,13%. Sedangkan hasil pengujian algoritma Naive Bayes Classifier (NBC) dengan Particle Swarm Optimization mempunyai tingkat akurasi 66,02%. Dengan demikian hasil seleksi fitur Chi-Squared Statistic mendapatkan nilai akurasi yang lebih baik jika dibandingkan dengan Particle Swarm Optimization untuk proses klasifikasi algoritma Naive Bayes Classifier (NBC) dengan selisih akurasi 3,11%.

Download Full-text

SENTIMENT ANALYSIS OF DIGITAL WALLET SERVICE USERS USING NAÏVE BAYES CLASSIFIER AND PARTICLE SWARM OPTIMIZATION

Jurnal Riset Informatika ◽

10.34288/jri.v2i4.160 ◽

2020 ◽

Vol 2 (4) ◽

pp. 241-250

Author(s):

Alvie Delia Cahyani ◽

Tati Mardiana

Keyword(s):

Particle Swarm Optimization ◽

Sentiment Analysis ◽

Naive Bayes ◽

Naïve Bayes ◽

Service Users ◽

Naive Bayes Classifier ◽

Bayes Classifier ◽

Naïve Bayes Classifier ◽

Swarm Optimization ◽

Digital Wallet

Digital wallet services provide many conveniences and benefits to its users. However, not all digital wallet service users have a positive opinion of the service. Sentiment analysis in this study aims to determine the opinions given by Dana and Isaku digital wallet service users whether they contain positive or negative opinions and apply the Naïve Bayes Classifier and Particle Swarm Optimization (PSO) method to the sentiment analysis of digital wallet service users. The Naïve Bayes Classifier method is used because it is simple, fast, high accuracy, and has good enough performance to classify data, but the Naïve Bayes Classifier has the disadvantage that each independent variable is assumed to cause a decrease in the accuracy value. Therefore, this research added an attribute weighting method, namely Particle Swarm Optimization (PSO) to increase the accuracy of the classification of the Naïve Bayes Classifier. This study uses data taken from Twitter as many as 490 tweet data. The test results using the confusion matrix and ROC curve show an increase in accuracy of the Naïve Bayes Classifier Dana digital wallet from 60.00% to 91.67% and I.Saku digital wallet from 53.23% to 85.00%. T-Test and Anova test results show that the two classification methods tested have significant (significant) differences in Accuracy values.

Download Full-text