Klasifikasi pesan spam pada short message service menggunakan algoritma extreme learning machine

Wijaya, Eko Putra (2022) Klasifikasi pesan spam pada short message service menggunakan algoritma extreme learning machine. Bachelor thesis, Universitas Pelita Harapan.

[img]
Preview
Text (Title)
Title.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (313kB) | Preview
[img]
Preview
Text (Abstract)
Abstract.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (373kB) | Preview
[img]
Preview
Text (ToC)
ToC.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (387kB) | Preview
[img]
Preview
Text (Chapter1)
Chapter1.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (233kB) | Preview
[img] Text (Chapter2)
Chapter2.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (578kB)
[img] Text (Chapter3)
Chapter3.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (557kB)
[img] Text (Chapter4)
Chapter4.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (1MB)
[img] Text (Chapter5)
Chapter5.pdf
Restricted to Registered users only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (295kB)
[img]
Preview
Text (Bibliography)
Bibliography.pdf
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (287kB) | Preview
[img] Text (Appendices)
Appendices.pdf
Restricted to Repository staff only
Available under License Creative Commons Attribution Non-commercial Share Alike.

Download (5MB)

Abstract

Short message services (SMS) which provided on any mobile phone has big potential for spreading spam messages. The lack of feature to filter spam messages on mobile phone’s native messaging app gives spammers opportunity to spread spam messages via SMS. This research is aimed to develop a machine learning model using Extreme Learning Machine algorithm to classify spam messages. Before the text can be fitted into the model to be classified, it need to be preprocessed and weighted using TF-IDF algoritm. Using 70% of TF-IDF weighted data to train the model and the remaining used to evaluate, the model is able to predict the test data with 97.37% of accuracy on 10,000 hidden nodes count and 0.5 is used for classification treshold. The model is classified as depentable because it has 94.65% of accuracy, 85.09% of recall, and 89.62% of of f1 score. / Layanan pesan singkat (SMS) yang terdapat pada setiap telepon seluler memiliki potensi yang besar untuk menjadi jalur penyebaran pesan spam. Kurangnya fitur untuk menyaring pesan singkat berupa spam tersebut pada aplikasi pesan bawaan ponsel memberikan peluang bagi pelaku penyebar pesan spam untuk menyebarkan pesan spam ke para calon korban melalui SMS. Penelitian ini dilakukan dengan membuat model pembelajaran mesin menggunakan algoritma Extreme Learning Machine untuk mengklasifikasi pesan spam. Teks SMS sebelum diklasifikasikan menggunakan model ELM melalui tahap pra-proses dan tahap pembobotan menggunakan algoritma TF-IDF. Setelah 70% dari hasil pembobotan TF-IDF digunakan untuk melatih model pembelajaran mesin yang dikembangkan dan sisa dari data yang ada digunakan untuk evaluasi, model yang dikembangkan dapat melakukan prediksi data pengujian dengan tingkat akurasi tertinggi sebesar 97.37% dengan jumlah titik pada lapisan tersembunyi sebanyak 10,000 titik dan ambang batas klasifikasi di 0.5. Model ini dikatakan dapat diandalkan karena memiliki nilai precision sebesar 94.65%, recall sebesar 85.09% dan F1 Score sebesar 89.62%

Item Type: Thesis (Bachelor)
Creators:
CreatorsNIMEmail
Wijaya, Eko PutraNIM03082180026ekoputrawijaya@gmail.com
Contributors:
ContributionContributorsNIDN/NIDKEmail
Thesis advisorSiringoringo, RomindoNIDN0111119101romindo.siringoringo@gmail.com
Uncontrolled Keywords: klasifikasi; machine learning; extreme learning machine
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: University Subject > Current > Faculty/School - UPH Medan > School of Information Science and Technology > Informatics
Current > Faculty/School - UPH Medan > School of Information Science and Technology > Informatics
Depositing User: Users 24145 not found.
Date Deposited: 16 Aug 2022 01:45
Last Modified: 25 Aug 2022 03:36
URI: http://repository.uph.edu/id/eprint/49600

Actions (login required)

View Item View Item