Claim Missing Document
Check
Articles

Klasifikasi Sentimen Komentar Youtube Tentang Pembatalan Indonesia Sebagai Tuan Rumah Piala Dunia U-20 Menggunakan Algoritma Naïve Bayes Classifer Hasibuan, Ilham Habibi; Budianita, Elvia; Agustian, Surya; Pizaini, Pizaini
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 5 No. 2 (2023): Desember 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v5i2.7096

Abstract

Text mining is a method used to perform tasks such as document classification, clustering, information extraction, sentiment analysis, and information retrieval. The Federation Internationale Football Association (FIFA), the international football governing body, has designated Indonesia as the host country for the U-20 World Cup starting in 2019. Indonesia is expected to be the choice venue for the U-20 World Cup in 2021. However, due to the Covid outbreak -19, the World Cup was rescheduled and is now scheduled to take place in 2023. Indonesia officially relinquished its position as host on March 31 2023. One of the reasons is the many factions that oppose the presence of the Israeli national team in Indonesia. As a result, various public reactions responded to Indonesia's decision to cancel holding the U-20 World Cup, especially on the Narasi tv YouTube channel video entitled "The U-20 World Cup Failed to Be Held in Indonesia, Let's Look at it from Two Perspectives | Discussion". Since the video was uploaded until August 16 2023, the total comments generated were 4,629 comments. This research uses a Naïve Bayes classifier approach. Naïve Bayes Classifier (NBC) is a direct probabilistic classifier that exploits Bayes' Theorem under strong independence conditions. The tests carried out show that the model performance when using stopword removal and stemming techniques is superior in classifying classes in the dataset. The F1-Score is 59.70% and the Accuracy value is 63.43%. Furthermore, after identifying the most efficient model for applying naïve Bayes classification, evaluation was carried out on validation data resulting in an F1-Score of 58.72% and an accuracy rate of 61.65%. Classification analysis shows that Indonesian people have a negative view or are disappointed with the cancellation
Klasifikasi Sentimen Masyarakat Terhadap Kaesang Pangarep pada Media Sosial Twitter/X Menggunakan MLP Classifier dengan Fitur FastText Tarmizi, Veci Cahyono; Agustian, Surya; Okfalisa, Okfalisa; Pizaini, Pizaini
TIN: Terapan Informatika Nusantara Vol 6 No 7 (2025): December 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v6i7.8815

Abstract

Social media has become a primary channel for the public to express their opinions and reactions toward various political developments in Indonesia. One of the prominent discussions revolves around Kaesang Pangarep’s appointment as the Chairman of the Indonesian Solidarity Party (PSI). This study aims to analyze and classify public sentiment regarding this issue by employing the Multi-Layer Perceptron (MLP) algorithm integrated with FastText-based text representation. The dataset was collected from Twitter using keywords such as “Kaesang PSI”, and was further expanded with additional data from general topics including Covid-19 and Open Topic, ensuring a balanced distribution across positive, neutral, and negative sentiment categories for a more comprehensive representation of public opinion. The model’s performance was evaluated through four metrics: accuracy, precision, recall, and F1 Score. The experimental results demonstrate that the MLP–FastText model achieved consecutive scores of 0. 5129 for F1 Score, 0. 6035 for accuracy, 0. 5319 for precision, and 0. 5996 for recall. These findings indicate that the combination of MLP and FastText effectively captures sentiment patterns within textual data, particularly in the context of unstructured and dynamic social media content, and performs well when enhanced with relevant external data augmentation strategies.
Co-Authors Abdillah, Rahmad Adha, Martin Aditya Dyan Ramadhan Afdhalel Vickro Agung Teguh Wibowo Almais Ahmad Fauzan Akhyar, Amany Albis Ya Albi Alwis Nazir Alwis Nazir Andrian Wahyu Arvansyah, M Afdhol Aslis Wirda Hayati Ayu Fransiska Bebi Oktaviani Che Hussin, Ab Razak citra ainul mardhia putri Deny Dewana Hastanto Dhymas Julyan Riyanto Eka Pandu Cynthia Elin Haerani Elvia Budianita Fadhilah Syafria Fahmi Kasri Fajar Febriyadi Fakhrezi, Muhammad Dzaki Faris Apriliano Eka Fardianto Faris Fauzan Ray T Febi Yanto Fitra Kurnia Fitri Insani Fitri Insani Fitri Insani Fitri, Dina Deswara Gusti, Siska Kurnia Haikal Zikri Hasibuan, Ilham Habibi Heru Sukoco Husnan Husnan Ibrahim Armadian Pujakesuma Iwan Iskandar Iwan Iskandar Iwan Iskandar Iwan Iskandar Iwan Jasril Jasril Jesi Alexander Alim Jesi Alexander Alim Kana Saputra S Khonofi, Khoidir Lestari Handayani Lola Oktavia m azwan M Wandi Dwi Wirawan M. Saski Mandiro, Mulia Anton Muhammad Affandes Muhammad Affandes Muhammad Fauzan Muhammad Fikry Muhammad Irsyad Muhammad Irsyad Muhammad Ridha Mulia Anton Mandiro Musa Thahir Muslimin, Al’hadiid Najmi, Risna Lailatun Nanda Sepriadi Nazir, Alwis Nazruddin Safaat H Neni Hermita Novi Yanti Novialdi T Novri Rahman Novriyanto Novriyanto Nur Iza Nuradha Liza Utami Okfalisa Okfalisa Okfalisa Okfalisa Putri, Adilah Atikah Rahmad Abdillah Rahmad Kurniawan Reski Mai Candra Reski Mai Chandra Rometdo Muzawi, Rometdo Roziana Roziana, Roziana Saktioto Saktioto Suci Rahayu Sugi Guritman Sukma Evadini Surya Agustian Suwanto Sanjaya Syarifuddin Syarifuddin Tarmizi, Veci Cahyono Teddie Darmizal Thahir, Musa Tommy Tanu Wijaya Umar Syarif Vebrianto, Rian Wenny Tarisa Oktaviany Wirdiani, Putri Syakira Yelfi Vitriani Yusra Yusra, Yusra Zuriati Ardila Safitri