Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal Informatika: Jurnal Pengembangan IT

Analisis Komparasi Algoritma Machine Learning untuk Sentiment Analysis (Studi Kasus: Komentar YouTube “Kekerasan Seksual”) Chandra Ayunda Apta Soemedhy; Nora Trivetisia; Nawang Anggita Winanti; Dwi Puspa Martiyaningsih; Tri Wulandari Utami; Sudianto Sudianto
Jurnal Informatika: Jurnal Pengembangan IT Vol 7, No 2 (2022)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v7i2.3547

Abstract

Cases of sexual violence in the last decade have been rampant in Indonesia. Cases of sexual violence are increasingly exposed, along with the increasing use of social media. One of them is violence against women. Cases of sexual violence often cause various kinds of stigma in the community, so this study aims to determine the public's response to cases of sexual harassment using sentiment analysis. The data used is sourced from YouTube comments with the title "Kasus Bunuh Diri NW: Bripda Randy Tersangka, Penanganan Polisi Dikritik | Narasi Newsroom." The method used is Machine Learning algorithms such as the SVM algorithm, Naive Bayes, and Random Forest. The results of comparing the three Machine Learning algorithms, Random Forest, obtained the best accuracy rate of 78% compared to the other two algorithms in conducting sentiment analysis on YouTube comments about sexual harassment discussions.
Klasifikasi Judul Berita Clickbait menggunakan RNN-LSTM Widi Afandi; Satria Nur Saputro; Andini Mulia Kusumaningrum; Hikari Adriansyah; Muhammad Hilmi Kafabi; Sudianto Sudianto
Jurnal Informatika: Jurnal Pengembangan IT Vol 7, No 2 (2022)
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/jpit.v7i2.3401

Abstract

Amid technological developments, online news of various life topics is shared across various platforms. Many media often take advantage of this opportunity by uploading their news on several online platforms to increase the traffic and rankings they upload to make much profit. However, many online media attract readers' attention by exaggerating the headlines or news headlines they upload. That way, the news title is often not by the content of the news. This phenomenon is commonly known as "clickbait" among the public. The media usually do this to increase traffic, rankings, and finances. Therefore, this study classified the news with clickbait and non-clickbait titles using the RNN-LSTM architecture. In this study, the classification of clickbait news titles uses the RNN-LSTM architecture. The classification results obtained calculation accuracy of 79% on training data and 77% accuracy on test data.