Analisis Twitter Untuk Konsumen Belanja Online Menggunakan Metode Naïve Bayes Classifier(Nbc)Dan Artificial Neural Network(Ann)

Damayanti, Fransiska Kristin (2018) Analisis Twitter Untuk Konsumen Belanja Online Menggunakan Metode Naïve Bayes Classifier(Nbc)Dan Artificial Neural Network(Ann). Undergraduate thesis, Institut Teknologi Sepuluh Nopember.

[img]
Preview
Text
06211645000035-Undergraduate_Theses.pdf - Accepted Version

Download (2MB) | Preview

Abstract

Tokopedia dan Bukalapak merupakan perusahaan yang mengusung bisnis marketplace dan mall online. Untuk menanggapi pendapat, kritik, saran dan masalah complain, Tokopedia dan Bukalapak mempunyai akun khusus pada Twitter yang diberi nama TokopediaCare dan BukaBantuan. Jenis komentar tersebut berbentuk unstructured text dalam jumlah besar. Kondisi ini dapat mengakibatkan perusahaan belanja online dapat melewatkan informasi yang berguna dari sekumpulan dokumen teks. Oleh karena itu, dilakukan analisis text mining dengan membandingkan metode klasifikasi Naïve Bayes Classifier (NBC) dan Artificial Neural Network (ANN). Berdasarkan hasil analisis dapat diketahui metode klasifikasi Artificial Neural Network lebih baik digunakan jika dibandingkan dengan Naïve Bayes Classifier dengan hasil ketepatan klasifikasi mencapai 0.9492 pada akun TokopediaCare dan 0.97564 akun BukaBantuan . Selain itu dilakukan pula Social Network Analysis yang digunakan untuk menggambarkan struktur komunikasi dan tingkat partisipasi dari setiap pelanggan. ============================================================ Tokopedia and Bukalapak is a company engaged in marketplace and online mall. To respond to opinions, critics and complaints, Tokopedia and Bukalapak have a special account on Twitter called @tokopediacare and @bukabantuan. The comment type is unstructured text in large numbers. This condition can lead to online shopping companies skipping useful information from a collection of text documents. Therefore, text mining analysis is used by comparing Naïve Bayes Classifier (NBC) and Artificial Neural Network (ANN) classification method. Based on the analysis results, it is known that ANN classification method.is better used when compared with NBC classification method, with classification accuracy reach 0.9492 for TokopediaCare and 0.9764 for BukaBantuan. In addition, Social Network Analysis (SNA) is also used to describe the structure of communication and the level of participation of each customer.

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Artificial Neural Network, Naive Bayes Classifier, Social Network Analysis, Twitter
Subjects: H Social Sciences > HD Industries. Land use. Labor > HD108 Classification (Theory. Method. Relation to other subjects )
Q Science > QA Mathematics > QA279.5 Bayesian statistical decision theory.
Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
Divisions: Faculty of Mathematics and Science > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Damayanti Fransiska Kristin
Date Deposited: 09 Jul 2021 10:16
Last Modified: 09 Jul 2021 10:16
URI: https://repository.its.ac.id/id/eprint/57314

Actions (login required)

View Item View Item