Merdikatama, Agus (2018) Klasifikasi komentar di instagram untuk rekomendasi pemilihan online shop menggunakan algoritma K-Nearest Neighbor. Diploma thesis, UIN Sunan Dunung Djati Bandung.
|
Text (COVER)
1_cover.pdf Download (17kB) | Preview |
|
|
Text (ABSTRAK)
2_abstrak.pdf Download (89kB) | Preview |
|
|
Text (DAFTAR ISI)
3_daftarisi.pdf Download (286kB) | Preview |
|
|
Text (BAB I)
4_bab1.pdf Download (182kB) | Preview |
|
Text (BAB II)
5_bab2.pdf Restricted to Registered users only Download (293kB) | Request a copy |
||
Text (BAB III)
6_bab3.pdf Restricted to Registered users only Download (1MB) | Request a copy |
||
Text (BAB IV)
7_bab4.pdf Restricted to Registered users only Download (2MB) | Request a copy |
||
Text (BAB V)
8_bab5.pdf Restricted to Registered users only Download (92kB) | Request a copy |
||
Text (DAFTAR PUSTAKA)
9_daftarpustaka.pdf Restricted to Registered users only Download (204kB) | Request a copy |
Abstract
Peningkatan jumlah online shop di indonesia menyebabkan dalam pemilihan online shop yang terpercaya sulit untuk dilakukan. Permasalahan tersebut dapat diselesaikan dengan membuat sistem untuk klasifikasi komentar pada online shop. Tujuan penelitian ini membangun sistem untuk pengklasifikasian komentar dalam pemilihan online shop yang terpercaya menggunakan algoritma K-Nearest Neighbor. Metode yang digunakan yaitu teks mining. Pada penelitian ini data latih yang digunakan berjumlah 196 data sebagai data training. Teknik praproses yang dilakukan dimulai dari case folding, normalisasi, filtering, stemming, tokenisasi dan pembobotan dengan menghitung nilai TF-IDF. Sistem ini diharapkan dapat melakukan klasifikasi data secara otomatis dan tepat. Hasil dari penelitian ini menunjukan bahwa algoritma K- Nearest Neighbor mampu menghasilkan tingkat akurasi sebesar 83 %. The increasing number of online shops in Indonesia causes about how dificulty in choosing the trusted one of the online shops. These problems can be solved by creating a system for classifying from comments on the online shop. The purpose of this study is to build a system for classifying from comments in the selection of trusted online shops using the K-Nearest Neighbor algorithm. The method used is text mining. In this study the training data used amounted to 196 data as training data. Preprocessing techniques carried out starting from case folding, normalization, filtering, stemming, tokenization and weighting by calculating the TF-IDF value. This system is expected to be able to classify data automatically and precisely. The results of this study indicated that the K-Nearest Neighbor algorithm is able to produce an accuracy rate of 83%.
Item Type: | Thesis (Diploma) |
---|---|
Uncontrolled Keywords: | Online shop; Teks Mining; K-Nearest Neighbor |
Subjects: | Operations, Archieves, Information Centers > Classification of Specific Subject |
Divisions: | Fakultas Sains dan Teknologi > Program Studi Teknik Informatika |
Depositing User: | agus merdikatama |
Date Deposited: | 28 Nov 2018 03:17 |
Last Modified: | 28 Nov 2018 03:17 |
URI: | https://digilib.uinsgd.ac.id/id/eprint/17022 |
Actions (login required)
View Item |