MODIFIKASI ALGORITMA STEMMING SASTRAWI MENGGUNAKAN RULE PRECEDENCE DAN PREFIX REMOVAL

AKBAR, ANWARIPASHA and Abdiansah, Abdiansah (2024) MODIFIKASI ALGORITMA STEMMING SASTRAWI MENGGUNAKAN RULE PRECEDENCE DAN PREFIX REMOVAL. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282025072.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021282025072_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_55201_09021282025072_0001108401_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (918kB)
	Text RAMA_55201_09021282025072_0001108401_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (292kB) | Request a copy
	Text RAMA_55201_09021282025072_0001108401_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (414kB) | Request a copy
	Text RAMA_55201_09021282025072_0001108401_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (804kB) | Request a copy
	Text RAMA_55201_09021282025072_0001108401_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (843kB) | Request a copy
	Text RAMA_55201_09021282025072_0001108401_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (180kB) | Request a copy
	Text RAMA_55201_09021282025072_0001108401_07_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (184kB)
	Text RAMA_55201_09021282025072_0001108401_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (627kB) | Request a copy

Abstract

Text pre-processing is increasingly important in the era of rapidly growing digital information One of the important stages in text processing is stemming, which aims to convert words to their basic form by cutting off certain prefixes or suffixes. The Indonesian stemming algorithm that is often used is Sastrawi. To improve the accuracy and efficiency of the stemming process, this research modifies the Sastrawi stemming algorithm using rule precedence and prefix removal. Rule precedence allows better handling of the priority order of removal, while prefix removal modification also aims to improve stemming accuracy. The method was tested through a series of correct stem accuracy tests using datasets from Kompas articles totaling 1666, 1888, 1736, and 1866 words respectively. The experimental results show that the modified Sastrawi stemming outperforms the baseline (Sastrawi Stemmer) with an average stemming accuracy improvement of 0.26%. This research makes an important contribution in the development of a more accurate Indonesian stemming algorithm in Indonesian text processing

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Stemming, Sastrawi Stemmer, Rule Precedence, Prefix Removal
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Anwaripasha Akbar
Date Deposited:	22 Mar 2024 04:05
Last Modified:	22 Mar 2024 04:05
URI:	http://repository.unsri.ac.id/id/eprint/142144

Actions (login required)

View Item