KLASIFIKASI KOMENTAR PERUNDUNGAN PADA INSTAGRAM MENGGUNAKAN ALGORITMA CHI-SQUARE DAN SUPPORT VECTOR MACHINE

HERSA, CESIL OKTAVIA and Abdiansah, Abdiansah (2021) KLASIFIKASI KOMENTAR PERUNDUNGAN PADA INSTAGRAM MENGGUNAKAN ALGORITMA CHI-SQUARE DAN SUPPORT VECTOR MACHINE. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021181621013.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021181621013_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (13MB) | Request a copy
Preview	Text RAMA_55201_09021181621013_0001108401_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (2MB) | Preview
	Text RAMA_55201_09021181621013_0001108401_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (859kB) | Request a copy
	Text RAMA_55201_09021181621013_0001108401_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (951kB) | Request a copy
	Text RAMA_55201_09021181621013_0001108401_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021181621013_0001108401_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021181621013_0001108401_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (401kB) | Request a copy
	Text RAMA_55201_09021181621013_0001108401_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (297kB) | Request a copy
	Text RAMA_55201_09021181621013_0001108401_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (417kB) | Request a copy

Abstract

Instagram is one of popular social media platforms to fulfill social needs. However, many cases of bullying occur on Instagram because some users do not understand the ethics of socializing through social media. The impact of this action is very unsettling because it can lead to depression to suicide. Therefore, a classification method is needed that can classify comments on Instagram to find out that comments fall under the category of bullying or non-bullying comments. The Support Vector Machine (SVM) method has a good performance in classifying text data. However, the more data comments, the more features will be processed, so the longer the Support Vector Machine computation time. To solve this problem, the Chi-Square method is used to reduce the number of features in the comment data. The purpose of this research is to determine the performance produced by the SVM method with the Chi-Square feature selection and the SVM method without feature selection in classifying bullying comments on Instagram. The results of the test will be compared and evaluated to determine the effect of the Chi-Square method in improving the performance of the SVM method. Tests were carried out using the Linear, Polynomial and RBF kernel functions with the input parameter C, namely 0,1 , 1 and 10 for each kernel. The results of the tests that have been done show that the SVM method with Chi-Square feature selection has a better performance. Chi-Square method is able to reduce the features of the dataset, thereby increasing performance and reducing the computation time of the Support Vector Machine method. The highest increase in accuracy occurred in the RBF kernel using the parameter C = 0,1 , which was 0,20. Key Words : Bullying, Chi-Square, Classification, Comment, Instagram, Support Vector Machine.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Text Mining, Classification
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Users 11955 not found.
Date Deposited:	04 May 2021 07:34
Last Modified:	04 May 2021 07:34
URI:	http://repository.unsri.ac.id/id/eprint/46251

Actions (login required)

View Item