Claim Missing Document
Check
Articles

Found 6 Documents
Search
Journal : The Indonesian Journal of Computer Science

Analisis Sentimen Pengguna Sosial Media Twitter Terhadap Perokok Di Indonesia Dewi Setiyawati; Cahyono, Nuri
The Indonesian Journal of Computer Science Vol. 12 No. 1 (2023): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i1.3154

Abstract

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.
Analisis Topic Modelling Persepsi Pengguna Internet Menggunakan Metode Latent Dirichlet Allocation Angga Reni Dwi Astuti; Cahyono, Nuri
The Indonesian Journal of Computer Science Vol. 12 No. 1 (2023): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i1.3155

Abstract

Technological advances have undoubtedly had a major impact on information media. One impact of technological progress is the existence of news media as a source of publik information. There is also regional information, both domestic and foreign, and of course there are various discussions. News data from online news portals can be used as a source of information as a source of research and analysis. Of course, newa portals cover all types of news on various topics. Indentifying frequently discussed topics on news portal will denfinitely take a lot of time. Therefore, this research focuses on applying a topic modelling system to implement a news topic decision system using the Latent Dirichlet Allocation (LDA) method. This research successfully applies the Latent Dirichlet Allocation (LDA) method in determining news topics, of which there are three topic categories that are often discussed on the online news portal detik.com. topic 1 contains natural disaster event, topik 2 contins political figures and issues, topik 3 conttains news about the world cup.
Analisis Sentimen Terhadap Cyberbullying Pada Komentar Di Instagram Menggunakan Algoritma Naïve Bayes Fauzan Baehaqi; Cahyono, Nuri
The Indonesian Journal of Computer Science Vol. 13 No. 1 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i1.3301

Abstract

Cyberbullying, penggunaan teknologi digital yang disengaja untuk menyakiti, mempermalukan, atau menggertak orang lain secara online, telah menjadi isu penting dalam masyarakat saat ini. Dampak dari cyberbullying bisa sangat parah, menyebabkan masalah kesehatan mental, rendah diri, dan, dalam beberapa kasus tragis, hilangnya nyawa. Memahami fenomena ini secara mendalam dan menemukan solusi efektif untuk mengatasinya sangatlah penting. Analisis sentimen menggunakan algoritma Naïve Bayes sebagai pendekatan yang layak untuk mengatasi cyberbullying di Instagram. Tujuan utama dari penelitian ini adalah untuk mempelajari dan menganalisis sentimen terkait cyberbullying pada komentar Instagram menggunakan algoritma Naïve Bayes. Dengan menganalisis konten yang terkait dengan cyberbullying, penelitian ini bertujuan untuk memberikan wawasan yang lebih baik tentang masalah tersebut dan mengidentifikasi pola dan karakteristik khusus yang dapat membantu upaya pencegahan dan intervensi. Temuan ini dapat berkontribusi untuk menciptakan lingkungan online yang lebih aman dan melindungi kesejahteraan pengguna media sosial.
Analisis Sentimen Ulasan Aplikasi TikTok Shop Seller Center di Google Playstore Menggunakan Algoritma Naive Bayes Anggista Oktavia Praneswara; Cahyono, Nuri
The Indonesian Journal of Computer Science Vol. 12 No. 6 (2023): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v12i6.3473

Abstract

In the rapidly developing digital era, users' views on mobile applications are a key factor in the success of an application. Understanding user sentiment can help application developers and management to improve service quality and user satisfaction. One of the social media that is experiencing a revolution is TikTok, a short video sharing platform that presents e-commerce innovations through the TikTok Shop Seller Center. Therefore, sentiment analysis was carried out to find out whether user reviews of the TikTok Shop Seller Center application tended to be positive or negative based on the Naïve Bayes algorithm. The research methodology involves data scrapping, data cleaning, preprocessing (case folding, stopword removing, tokenization, stemming), labeling, TF-IDF, data testing using confusion matrix and visualization using wordcloud. The results of research regarding sentiment analysis of reviews of the TikTok Shop Seller Center application on Google Playstore totaling 5000 data, it was concluded that user reviews were classified as negative with a percentage of 86.3% accuracy value, 83.7% precision value, 94.6% recall value and 88.7% % F1-Score value.
Pengembangan Aplikasi Chat Multi Bahasa Berbasis NLP Translation API Sugiharto, M Iqbal Novananda; Cahyono, Nuri
The Indonesian Journal of Computer Science Vol. 11 No. 3 (2022): The Indonesian Journal of Computer Science
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v11i3.3128

Abstract

Interacting with others is an essential part of human life.. Sometimes users experience problems using chat applications, namely language differences when communicating with foreigners. Based on these problems, the author aims to build a chat application with a mobile-based automatic translator. In this application, the user can choose the language that will be used as needed. This application development uses the React Native framework for mobile applications and uses the NLP translation API for translators. This chat application automatically translates messages into the language used by the user. After doing some testing on the application, it can be concluded that it is according to the design and can make it easier for users to communicate with different languages
Analisis Topic Modelling Pariwisata Yogyakarta Menggunakan Latent Dirichlet Allocation (LDA) Uray Nur Khadijah; Nuri Cahyono
The Indonesian Journal of Computer Science Vol. 13 No. 4 (2024): The Indonesian Journal of Computer Science (IJCS)
Publisher : AI Society & STMIK Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33022/ijcs.v13i4.3816

Abstract

Pariwisata Yogyakarta sebagai destinasi yang kaya akan budaya dan sejarah, sering menjadi fokus diskusi di media sosial. Tujuan dari Penelitian ini adalah menelaah topik pariwisata Yogyakarta dari Twitter. Dataset yang diperoleh dalam penelitian ini dari crawling data menggunakan API key Twitter. Penelitian ini menggunakan tahapan dari pengumpulan data, text preprocessing, dan menerapkan metode Topic Modelling, khususnya Latent Dirichlet Allocation (LDA). Hasil penelitian ini pengujian kinerja pemodelan topik dengan metode LDA dapat dilihat dari nilai coherence score, semakin tinggi nilai coherence suatu topik, semakin mudah diinterprestasikan oleh manusia dan Perplexity merupakan salah satu standar pengukuran yang dapat digunakan untuk menilai kinerja model yang baik dari model tersebut ditunjukkan dengan nilai perplexity yang lebih rendah. Nilai coherence score yang ditunjukkan pada num topic ke-1 sebesar 0.331047, untuk nilai perplexity ditunjukkan dengan nilai yang tinggi terletak pada num topic ke-3 sebesar -8.830172565520245. diharapkan dapat memberikan wawasan mendalam tentang topik-topik yang sering dibahas dan berkonsentrasi pada penerapan sistem pemodelan topik untuk membangun sistem keputusan topik berita yang menggunakan metode Latent Dirichlet Allocation (LDA). Pada Penelitian ini efektif dalam menggunakan metode LDA untuk menentukan topik berita yang mencakup tiga kategori topik yang sering dibicarakan pada masing-masing kelas.