ANALISIS SENTIMEN MENGGUNAKAN K-NEAREST NEIGHBORS DAN LEXICON BASED

KURNIAWAN, ZIKRY and Yusliani, Novi and Buchari, Muhammad Ali (2021) ANALISIS SENTIMEN MENGGUNAKAN K-NEAREST NEIGHBORS DAN LEXICON BASED. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021281621040.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_55201_09021281621040_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
Preview	Text RAMA_55201_09021281621040_0008118205_8812870018_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_55201_09021281621040_0008118205_8812870018_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (272kB) | Request a copy
	Text RAMA_55201_09021281621040_0008118205_8812870018_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (154kB) | Request a copy
	Text RAMA_55201_09021281621040_0008118205_8812870018_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021281621040_0008118205_8812870018_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (206kB) | Request a copy
	Text RAMA_55201_09021281621040_0008118205_8812870018_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (110kB) | Request a copy
	Text RAMA_55201_09021281621040_0008118205_8812870018_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (129kB) | Request a copy
	Text RAMA_55201_09021281621040_0008118205_8812870018_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (184kB) | Request a copy

Abstract

Sentiment analysis is part of text mining used for the classification of text polarity. Sentiment analysis can see how public opinion on an issue or problem occurs. A number of studies on sentiment analysis have been conducted with various machine learning approaches. One of the algorithms in machine learning is K- Nearest Neighbors (KNN). KNN is an algorithm used to classify new objects based on training data. However, in a number of sentiment analysis studies were not evaluated the word negation. The word negation can change the sentiment of a sentence from positive to negative and vice versa. Therefore, there needs to be a technique that is able to evaluate the word negation in order to improve the accuracy of sentiment results. One method that can handle the problem of the word negation is the Lexicon Based method. Based on five tests with five different parameter k values, the best test value was obtained in the second experiment (k = 3) with accuracy value of 0.89, precision value of 0.88, recall of 0.88, and f-measure of 0.88.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Analisis sentimen, K-Nearest Neighbors, kata negasi, Lexicon Based
Subjects:	P Language and Literature > P Philology. Linguistics > P98-98.5 Computational linguistics. Natural language processing Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning T Technology > T Technology (General) > T1-995 Technology (General) > T14 Philosophy. Theory. Classification. Methodology Cf. CB478 Technology and civilization
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Zikry Kurniawan
Date Deposited:	19 May 2021 04:22
Last Modified:	19 May 2021 04:22
URI:	http://repository.unsri.ac.id/id/eprint/46494

Actions (login required)

View Item