KLASIFIKASI SENTIMEN TERHADAP DATA TEXT JEJARING SOSIAL DENGAN TOPIK VAKSIN COVID-19 MENGGUNAKAN K-NEAREST NEIGHBOR (KNN)

RONALDO, M. RIZKI and Ubaya, Huda (2021) KLASIFIKASI SENTIMEN TERHADAP DATA TEXT JEJARING SOSIAL DENGAN TOPIK VAKSIN COVID-19 MENGGUNAKAN K-NEAREST NEIGHBOR (KNN). Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011381621110.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_56201_09011381621110_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
Preview	Text RAMA_56201_09011381621110_0216068101_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (3MB) | Preview
	Text RAMA_56201_09011381621110_0216068101_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (369kB) | Request a copy
	Text RAMA_56201_09011381621110_0216068101_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011381621110_0216068101_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011381621110_0216068101_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (151kB) | Request a copy
	Text RAMA_56201_09011381621110_0216068101_06_Ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (352kB) | Request a copy
	Text RAMA_56201_09011381621110_0216068101_07_Lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

The covid-19 vaccine is a substance or product whose working method is inserted into the human body and there will be stimulation of the immune system which can finally protect and protect against the covid-19 virus. In August 2020 the government announced it would distribute the vaccine, this policy sparked a lot of public backlash. The public wants to express all opinions, criticisms and suggestions. In this case, social networks are a suitable place to express this, and Twitter is one of the right platforms. In this study, sentiment classification using Natural Language Processing (NLP) was carried out on social network text data. The K-Nearest Neighbor method was proposed because it was able to classify sentiment on the COVID-19 vaccine data. The data used was obtained from the Drone Emprit Academy. The results of the classification using KNN are evaluated using a confusion matrix. The KNN classification with a comparison of 70% training data and 30% testing data resulted in the highest score with 87.35% accuracy, 88.65% precision, 85.92% recall, and 86.73% f1-score, while the training data was 20% and data testing produces the lowest score with 81.89% accuracy, 80.96% precision, 80.99% recall, and 80.94% f1-score. This study shows that the algorithm designed is able to classify sentiment well, and the results of the calculations can be used as a consideration for the government in making decisions regarding the covid-19 vaccine.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Vaksin Covid-19, Natural Language Precessing, K-Nearest Neighbor, sentimen, data text, confusion matrix.
Subjects:	H Social Sciences > HN Social history and conditions. Social problems. Social reform > HN1-995 Social history and conditions. Social problems. Social reform
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Mr. M. Rizki Ronaldo
Date Deposited:	13 Aug 2021 07:46
Last Modified:	13 Aug 2021 07:46
URI:	http://repository.unsri.ac.id/id/eprint/52026

Actions (login required)

View Item