Perbandingan akurasi algoritma Naive Bayes Classifier (NBC) dengan K-Nearest Neighbor (KNN) untuk analisis sentimen masyarakat terhadap transportasi online pada Twitter

Pritisen, Ferdinand (2018) Perbandingan akurasi algoritma Naive Bayes Classifier (NBC) dengan K-Nearest Neighbor (KNN) untuk analisis sentimen masyarakat terhadap transportasi online pada Twitter. Diploma thesis, UIN Sunan Gunung Djati Bandung.

[img]
Preview
Text (COVER)
1_cover.pdf

Download (137kB) | Preview
[img]
Preview
Text (ABSTRAK)
2_abstrak.pdf

Download (105kB) | Preview
[img]
Preview
Text (DAFTAR ISI)
3_daftarisi.pdf

Download (213kB) | Preview
[img]
Preview
Text (BAB I)
4_bab1.pdf

Download (259kB) | Preview
[img] Text (BAB II)
5_bab2.pdf
Restricted to Registered users only

Download (416kB) | Request a copy
[img] Text (BAB III)
6_bab3.pdf
Restricted to Registered users only

Download (1MB) | Request a copy
[img] Text (BAB IV)
7_bab4.pdf
Restricted to Registered users only

Download (1MB) | Request a copy
[img] Text (BAB V)
8_bab5.pdf
Restricted to Registered users only

Download (102kB) | Request a copy
[img] Text (DAFTAR PUSTAKA)
9_daftarpustaka.pdf
Restricted to Registered users only

Download (230kB) | Request a copy

Abstract

Transportasi online adalah salah satu transportasi yang semakin diminati masyarakat pada saat ini. Analisis sentimen pada jasa transportasi online merupakan proses mengekstraksi pendapat, sentimen, evaluasi, dan emosi orang tentang pelayanan pada transportasi online salah satunya di media sosial twitter masyarakat mengeluarkan beragam opini tentang pelayanan dari transportasi online ini dengan jumlah yang banyak, sehingga terdapat kesulitan untuk menentukan opini yang bersifat positif ataupun negatif. Ada beberapa tahap untuk melakukan analisis sentimen, diantaranya adalah tahap pengumpulan data, preprocessing data, POS Tagging dan klasifikasi opini menggunakan metode Naïve Bayes Classifier dan membandingkan akurasinya dengan metode K-Nearest Neighbor. Hasil perbandingan algoritma Naïve Bayes Classifier dan K-Nearest Neighbor dengan menggunkan 565 data tweet dari Twitter, dengan pembagian 500 data latih dan 65 data uji, untuk algoritma Naïve Bayes Classifier menghasilkan tingkat akurasi sebesar 66,15 % dan untuk algoritma K-Nearest Neighbor menghasilkan tingkat akurasi sebesar 67,69 %, dari hasil perbandingan akurasi menunjukan algoritma K-Nearest Neighbor memperoleh tingkat akurasi yang lebih besar. Online transportation is one of the transportation interests of the people at this time. Sentiment analysis in online transportation services is a process of extracting opinions, sentiments, evaluations, and emotions of people about service on online transportation, one of them is on twitter, the public issued a variety of opinions about the services of this online transportation in large numbers, so there are difficulties in determining opinions that are positive or negative. There are several steps to uses sentiment analysis. Data collection, preprocessing data, POS Tagging, and opinion classification uses the Naïve Bayes Classifier method, compared to the accuracy of the K-Nearest Neighbor method. The results of the comparison of Naïve Bayes Classifier and K-Nearest Neighbor algorithms uses 565 data tweets from Twitter, divided 500 trained data, and 65 test data, for the Naïve Bayes Classifier algorithm, the result in an achievement rate of 66.15%, and for the K-Nearest Neighbor algorithm, it produces an accuracy rate of 67.69%, from the results of the accuracy comparison showing the K-Nearest Neighbor algorithm obtains greater accuracy.

Item Type: Thesis (Diploma)
Uncontrolled Keywords: algoritma Naive Bayes Classifier (NBC); K-Nearest Neighbor (KNN); transportasi online;
Subjects: Data Processing, Computer Science > Computer Management
Data Processing, Computer Science > Systems Analysis and Computer Design
Data Processing, Computer Science > Internet (World Wide Web)
Data Processing, Computer Science > Internet Discussion Group
Applied Physics > Computer Engineering
Divisions: Fakultas Sains dan Teknologi > Program Studi Teknik Informatika
Depositing User: Ferdinand Pritisen
Date Deposited: 21 Jan 2019 07:05
Last Modified: 21 Jan 2019 07:05
URI: https://etheses.uinsgd.ac.id/id/eprint/18091

Actions (login required)

View Item View Item