SENTIMENT ANALYSIS OF TWITTER DATA ON REMOTE LEARNING USING NAÏVE BAYES ALGORITHM

Covid-19 is widespread, resulting in a global pandemic. Distance Learning System (DLS) is considered as a solution but, the reality of the implementation of DLS is not in accordance with the expectations of the community. Many Twitter users wrote their opinions on DLS. The tendency of public sentiment can be used as a way to improve the existing education system in Indonesia and can be an input for the government in improving the DLS method that is being implemented. Thus, this study produced a system that can analyze tweet sentiment towards DLS. The tweet was obtained using the Twitter API. The method used is Naïve Bayes for the process of classification of positive, negative, and neutral sentiments using 600 data. Then, data sharing is done 80% data training and 20% data testing that will be in the text preprocessing first. The accuracy of sentiment analysis of DLS using the Naïve Bayes method using 3-fold Cross-Validation produces an average of 93%.

Download Full-text

Analisis Sentimen Sistem E-Tilang Menggunakan Algoritma Naive Bayes Dengan Optimalisasi Information Gain

Journal of Informatic and Information Security ◽

10.31599/jiforty.v1i1.137 ◽

2020 ◽

Vol 1 (1) ◽

pp. 19-26

Author(s):

Rakhmi Khalida ◽

Siti Setiawati

Keyword(s):

Sentiment Analysis ◽

Opinion Mining ◽

Naive Bayes ◽

Information Gain ◽

Naïve Bayes ◽

Traffic Violations ◽

The Government ◽

Bayes Algorithm ◽

User Friendly

Abstract The Government of Indonesia took steps to change the system to improve public services in traffic violations by implementing the e-ticketing system. This system is a solution for disciplining motorized motorists from committing traffic violations. The existence of e-ticketing is also a solution to prevent the delinquency of law enforcers from illegal levies, peace terms in place, to accountability of fines. In this study, sentiment analysis of the e-ticketing system or opinion mining to classify the variety of public comments that give a positive, negative or neutral impression. Twitter social media is one of the objects to express opinions because it is user friendly, updated topics, and openly accesses tweets. Opinions on Twitter are collected, then the preprocessing stage is performed, then the selection of information gain features helps reduce noise caused by irrelevant labels, the next step is the classification of sentiments with the Naïve Bayes algorithm and finally polarity sentiments. This research resulted in an accuracy of 41.82%, a precision of 50.51% and a recall of 45.45%. Keywords: Sentiment analysis, E-ticketing, Information Gain, Naive Bayes Abstrak Pemerintah Indonesia melakukan langkah perubahan untuk memperbaiki sistem pelayanan publik dalam pelanggaran berlalu-lintas yaitu dengan menerapkan sistem e-Tilang. Sistem ini menjadi solusi mendisiplinkan para pengendara kendaraan bermotor dari banyaknya melakukan pelanggaran berlalu-lintas. Keberadaan e-Tilang juga menjadi solusi mencegah kenakalan penegak hukum dari pungutan liar, istilah damai ditempat, hingga akuntabilitas uang denda. Dalam penelitian ini melakukan analisis sentimen tentang sistem e-Tilang atau opinion mining untuk mengelompokan ragam komentar masyarakat yang memberikan kesan positif, negatif atau netral. Media sosial Twitter menjadi salah satu objek untuk menyampaikan opini karena user friendly, topik ter-update, dan terbuka mengakses tweet. Opini pada twitter dikumpulkan, lalu dilakukan tahapan preprocessing, selanjutnya dengan seleksi fitur information gain membantu mengurangi noise yang disebabkan oleh label-label yang tidak relevan, tahap selanjutnya adalah klasifikasi sentimen dengan algoritma Naïve Bayes dan terakhir sentimen polarity. Penelitian ini menghasilkan accuracy 41,82%, presisi 50,51% dan recall 45,45%. Kata kunci: Analisis sentimen, E-Tilang, Information Gain, Naive Bayes

Download Full-text

Community Opinion Sentiment Analysis on Social Media Using Naive Bayes Algorithm Methods

IJIIS: International Journal of Informatics and Information Systems ◽

10.47738/ijiis.v2i1.11 ◽

2019 ◽

Vol 2 (1) ◽

pp. 33-38 ◽

Cited By ~ 1

Author(s):

Taqwa Hariguna ◽

Vera Rachmawati

Keyword(s):

Social Media ◽

Sentiment Analysis ◽

Naive Bayes ◽

Naïve Bayes ◽

Central Java ◽

Public Sentiment ◽

Positive Class ◽

Negative Class ◽

Bayes Algorithm ◽

F Measure

The election of Governor is an election event for the Regional Head for the future of the region and the country. The Central Java Governor election in 2018 was held jointly on 27 June 2018, which was followed by 2 candidate pairs of the governor. Its many responses from people through twitter's social media to bring up opinions from the public. Sentiment analysis of 2 research objects of Central Java Governor 2018 candidates with a total of 400 tweets with each candidate being 200 tweets. The used of tweets are divided into 3 classes: positive class, neutral class and negative class. In this study the classification process used the Naive Bayes Classifier (NBC) method, while for data preprocessing is using Cleansing, Punctuation Removal, Stopword Removal, and Tokenisation, to determine the sentiment class with the Lexicon Based method produces the highest accuracy in the Ganjar Pranowo dataset with an accuracy of 87,9545%, Precision value is 0.891%, Recall value is 0.88% and F-Measure is 0.851% while Sudirman Said dataset has an accuracy rate of 84.322%, Precision value of 0.867%, Recall value of 0.843% and F-Measure of 0.815%. From these results, we can conclude that the Ganjar Pranowo dataset was higher compared to Sudirman Said's dataset.

Download Full-text

Algorithm Comparation of Naive Bayes and Support Vector Machine based on Particle Swarm Optimization in Sentiment Analysis of Freight Forwarding Services

Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) ◽

10.29207/resti.v4i2.1840 ◽

2020 ◽

Vol 4 (2) ◽

pp. 362-369

Author(s):

Sharazita Dyah Anggita ◽

Ikmah

Keyword(s):

Support Vector Machine ◽

Sentiment Analysis ◽

Naive Bayes ◽

Naïve Bayes ◽

Support Vector ◽

The Public ◽

Svm Algorithm ◽

Bayes Algorithm ◽

Freight Forwarding ◽

Improved Accuracy

The needs of the community for freight forwarding are now starting to increase with the marketplace. User opinion about freight forwarding services is currently carried out by the public through many things one of them is social media Twitter. By sentiment analysis, the tendency of an opinion will be able to be seen whether it has a positive or negative tendency. The methods that can be applied to sentiment analysis are the Naive Bayes Algorithm and Support Vector Machine (SVM). This research will implement the two algorithms that are optimized using the PSO algorithms in sentiment analysis. Testing will be done by setting parameters on the PSO in each classifier algorithm. The results of the research that have been done can produce an increase in the accreditation of 15.11% on the optimization of the PSO-based Naive Bayes algorithm. Improved accuracy on the PSO-based SVM algorithm worth 1.74% in the sigmoid kernel.

Download Full-text

Twitter Sentiment Analysis towards COVID-19 Vaccines in the Philippines Using Naïve Bayes

Information ◽

10.3390/info12050204 ◽

2021 ◽

Vol 12 (5) ◽

pp. 204

Author(s):

Charlyn Villavicencio ◽

Julio Jerison Macrohon ◽

X. Alphonse Inbaraj ◽

Jyh-Horng Jeng ◽

Jer-Guang Hsieh

Keyword(s):

Sentiment Analysis ◽

Language Processing ◽

Data Science ◽

Naive Bayes ◽

The Philippines ◽

Naïve Bayes ◽

Social Networking Site ◽

Bayes Model ◽

The Government ◽

Processing Techniques

A year into the COVID-19 pandemic and one of the longest recorded lockdowns in the world, the Philippines received its first delivery of COVID-19 vaccines on 1 March 2021 through WHO’s COVAX initiative. A month into inoculation of all frontline health professionals and other priority groups, the authors of this study gathered data on the sentiment of Filipinos regarding the Philippine government’s efforts using the social networking site Twitter. Natural language processing techniques were applied to understand the general sentiment, which can help the government in analyzing their response. The sentiments were annotated and trained using the Naïve Bayes model to classify English and Filipino language tweets into positive, neutral, and negative polarities through the RapidMiner data science software. The results yielded an 81.77% accuracy, which outweighs the accuracy of recent sentiment analysis studies using Twitter data from the Philippines.

Download Full-text

The Sentiment Analysis Reviewing Indosat Services from Twitter Using the Naive Bayes Classifier

Journal of Applied Computer Science and Technology ◽

10.52158/jacost.v1i2.79 ◽

2020 ◽

Vol 1 (2) ◽

pp. 61-66

Author(s):

Febri Astiko ◽

Achmad Khodar

Keyword(s):

Machine Learning ◽

Social Media ◽

Sentiment Analysis ◽

Naive Bayes ◽

Learning Model ◽

Naïve Bayes ◽

Bayes Classifier ◽

Naïve Bayes Classifier ◽

Machine Learning Model ◽

Bayes Algorithm

This study aims to design a machine learning model of sentiment analysis on Indosat Ooredoo service reviews on social media twitter using the Naive Bayes algorithm as a classifier of positive and negative labels. This sentiment analysis uses machine learning to get patterns an model that can be used again to predict new data.

Download Full-text