Analisis Sentimen Twitter Kuliah Online Pasca Covid-19  Menggunakan Algoritma Support Vector Machine dan Naive Bayes

Setiawan, Hendrik; Utami, Ema; Sudarmawan, Sudarmawan

doi:10.31603/komtika.v5i1.5189

Cited by 11 publications

(11 citation statements)

References 1 publication

(1 reference statement)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Dampak opini terhadap independensi setiap kondisi adalah salah satu ciri utama metode ini [20]. Teknologi pembelajaran terawasi bernama Support Vector Machine (SVM) berupaya mengidentifikasi pola dan mengatur informasi [21]. Pada Decision Tree, output mudah dibaca dan diinterpretasikan tanpa adanya pengetahuan statistic, namun kurang stabil karena adanya perubahan data skala kecil akan menyebabkan perubahan hasil yang cukup signifikan [22].…”

Section: Penerapan Metode Dan Pengujian Akurasiunclassified

Analisis Sentimen Pengguna Sosial Media Twitter Terhadap Perokok Di Indonesia

Cahyono¹,

Setiyawati²

2023

ijcs

View full text Add to dashboard Cite

One of the tools web users use to access, share, and discuss subjects of interest is social media. One social networking site, Twitter, is often used in real time to communicate this. Due to its significant negative impacts on both health and the economy, smoking is still a topic of regular debate and debate in Indonesia. This research was conducted to assess sentiment towards smokers and differentiate between positive and negative emotions. The data used in this study were obtained by crawling the Twitter social media network. Three Bayes techniques (NB), Support Vector Machine (SVM), and Logistic Regression are used in this study. In this study, 40.25% of Twitter users agreed with the existence of smokers in Indonesia, while 59.74% disagreed. The Naive Bayes method was used in this study, giving the highest accuracy value = 62.1% using 60% training data and 40% test data.

show abstract

Section: Penerapan Metode Dan Pengujian Akurasiunclassified

Analisis Sentimen Pengguna Sosial Media Twitter Terhadap Perokok Di Indonesia

Cahyono¹,

Setiyawati²

2023

ijcs

View full text Add to dashboard Cite

show abstract

“…Melihat postingan opini dan pendapat masyarakat pada Twitter sebagai instrumen untuk pengukuran tingkat kepuasan masyarakat mengenai belajar online, maka dilakukan sentimen analisis menggunakan algoritma Naive Bayes dan SVM. Hasil dari penelitian menunjukkan performa dari algoritma Naive Bayes sebesar akurasi 81,20%, waktu 9,00 detik, recall 79,60%, presisi 79,40%, sedangkan performa dari algoritma SVM sebesar akurasi 85%, waktu 31,60 detik, recall 84%, presisi 83,60% [8]. Hasil tersebut menunjukkan bahwa algoritma SVM memiliki tingkat akurasi lebih tinggi dari Naive Bayes namun membutuhkan waktu yang lebih lama.…”

Section: Pendahuluanunclassified

Analisis Sentimen Masyarakat Indonesia Terhadap Dampak Penurunan Global Sebagai Akibat Resesi di Twitter

Sutresno

2023

bits

View full text Add to dashboard Cite

A recession is a significant reduction in economic activity and is spread across the economy at its greatest for more than a few months, but it can also be seen in Real GDP, Real Income, Employment, Industrial Production, and Wholesale-Retail Sales. Recently, there has been a lot of public opinion regarding the recession that will occur in 2023, especially in Indonesia, on various social media such as Twitter. Based on these problems, sentiment analysis was carried out on tweets to obtain information on the positive or negative polarity of these opinions using the Naive Bayes and Support Vector Machine (SVM) methods to choose a more effective way in case studies to determine sentiment predictions. The steps are taken consist of data collection, processing data, weighting data, classification process, evaluation, validation, and results and discussion. The web scraping technique was used, and after going through the data cleaning stages, a total of 780 tweet data was obtained. The results of the classification test show that the SVM method has a greater accuracy rate with a proportion of 79.5% compared to the Naive Bayes method with a proportion of 72.5%. The SVM method's prediction results also show several 144 positive and 636 negative sentiments. Judging from the Wordcloud that was formed, it can be assumed that people are worried about their economic conditions, one of which is the unstable oil price which can trigger a recession.

show abstract

“…seconds. 84% and 83.60% accuracy, performance results were obtained for his 1st iteration of Naive Bayes and the 423rd iteration of his SVM algorithm [13].…”

Section: Literature Reviewmentioning

confidence: 99%

Analysis of Twitter Sentiments About the Russian-Ukraine War Using Naive Bayes Based on Particle Swarm Optimization

Sasi¹,

Utami²,

Pramono³

2023

Int.J.Res.Publ.Rev.

View full text Add to dashboard Cite

The Russia-Ukraine crisis has not found a solution until now, at least until November 2022. Many Indonesians have expressed their opinions on this matter via social media Twitter. This study uses the Naïve Bayes (NB) Algorithm based on Particle Swarm Optimization (PSO) to analyze opinions regarding the RussiaUkraine war. Data was taken from Twitter using the keywords "Russia Ukraine", "Russia vs Ukraine", "Russia-Ukraine", and "Perang Russia". The number of data sets taken is 5000 data. The results showed that the accuracy of the Naïve Bayes (NB) algorithm without Particle Swarm Optimization (PSO) was 67.72%, the precision value was 58.33%, the recall value was 79.75%, and the error rate of 57.14% while Naïve Bayes (NB) with Particle Swarm Optimization (PSO) the accuracy obtained is 73.48%, the precision value is 65.62%, the recall value is 76.36% and error rate of 50.36%. Thus it can be said that the Particle Swarm Optimization (PSO) applied to the Naïve Bayes algorithm for objects in research can increase the accuracy of results.

show abstract

Analisis Sentimen Twitter Kuliah Online Pasca Covid-19 Menggunakan Algoritma Support Vector Machine dan Naive Bayes

Cited by 11 publications

References 1 publication

Analisis Sentimen Pengguna Sosial Media Twitter Terhadap Perokok Di Indonesia

Analisis Sentimen Pengguna Sosial Media Twitter Terhadap Perokok Di Indonesia

Analisis Sentimen Masyarakat Indonesia Terhadap Dampak Penurunan Global Sebagai Akibat Resesi di Twitter

Analysis of Twitter Sentiments About the Russian-Ukraine War Using Naive Bayes Based on Particle Swarm Optimization

Contact Info

Product

Resources

About