Claim Missing Document
Check
Articles

Found 3 Documents
Search

Pengaruh Normalisasi Teks Dengan Text Expansion Dalam Deteksi Komentar Spam Pada Youtube Imam Thoib; Arief Setyanto; Suwanto Raharjo
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 2 No 3 (2018): Desember 2018
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (886.168 KB) | DOI: 10.29207/resti.v2i3.602

Abstract

The popularity of Youtube as the largest video sharing website in the wolrd give spammers opportunities to get benefit from Youtube in illegal ways by putting spam comments on Youtube's videos. Spam comments are very troubling to channel owners. The variants of spam comments are becoming more difficult to detect. One of them is spam comments using abbreviations, symbols, terms or misspelled word to make detection difficult. This research evaluate some classification techniques and employ text normalization method called TextExpansion to deal with this problem. This research uses Youtube Spam Collections dataset from UCI Machine Learning Library composed by five different datasets, which each one contains text comments extracted from YouTube videos (Psy, Katty Perry, LMFAO, Eminem and Shakira). The evaluation results shows TextExpansion is able to produce the highest accuracy value of 90.23%. To determine the impact of applying the TextExpansion method, this research conducted t-test for each dataset. The results of t-test for each dataset shows P(T<=t) two-tail < 0.05 which indicates a significant impact after applying text normalization using TextExpansion.
Analisis Sentimen Warganet terhadap Isu Layanan Transportasi Online Berbasis InSet Lexicon menggunakan Logistic Regression Kholifah, Binti; Thoib, Imam; Sururi, Nafis; Kurnia, Nicky Dwi
KLIK- KUMPULAN JURNAL ILMU KOMPUTER Vol 11, No 1 (2024)
Publisher : Lambung Mangkurat University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20527/klik.v11i1.655

Abstract

Beberapa isu terkait layanan transportasi online kerap menjadi pusat perdebatan di media sosial. Hal tersebut memberikan pengaruh pada penilaian layanan tersebut di Google Play Store. Penelitian ini bertujuan untuk melakukan analisis sentimen terhadap isu layanan transportasi online berbasis data warganet di Google Play Store. Analisis sentimen dan pelabelan dilakukan berdasarkan Inset Lexicon, sedangkan klasifikasi dilakukan menggunakan Logistic Regression. Sebelum diolah, data ulasan warganet harus melalui tahap pra-pemrosesan dan eksplorasi data. Selanjutnya, dilakukan optimisasi dengan parameter C, solver, dan max_iter pada model Logistic Regression. Hasil menunjukkan bahwa kombinasi nilai dari beberapa parameter optimisasi membawa pengaruh pada kinerja Logistic Regression. Selama pengujian, dapat dilihat juga bahwa rating tidak selamanya mecerminkan ulasan dari pengguna. Hal ini bisa dipengaruhi beberapa faktor seperti perilaku pengguna itu sendiri.
Perbandingan Performa Pencarian Data Berbasis Teks dengan Dan Tanpa Full-text Index pada Basis Data MySQL Imam Thoib; Beda Puspita Candra; Nafis Sururi; Danang Satya Nugraha
INSOLOGI: Jurnal Sains dan Teknologi Vol. 3 No. 6 (2024): Desember 2024
Publisher : Yayasan Literasi Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55123/insologi.v3i6.4596

Abstract

The amount of text-based data generated today is increasing drastically, especially with the development of digital technology and the internet. With the rapid growth of data, one of the main challenges faced is how to store and search large amounts of text-based data efficiently. This study analyzes the effect of using Full-text index in MySQL on the performance of text-based data searches, especially on large datasets. The study was conducted using a marketplace product dataset containing 2.3 million data. Testing includes searching using one, two, and three-word keywords in tables with and without full-text index. The test results show that tables with full-text index have faster search times than tables without Full-text index. Statistical analysis using the t-test produces a p value <0.05, indicating a significant effect of using Full-text index on data search efficiency. These findings confirm that full-text index is an effective solution to improve the performance of large-scale text data searches.