Video Direct Link | Abstract

Abstract ABS-173

Comparison Of Effectiveness Of Stemming Algorithms In Indonesian Documents Dyah Mustikasari(a), Ida Widaningrum(b*), Rizal Arifin(c), Wahyu Henggal Eka Putri(d) Corresponding Author: Dyah Mustikasari

Question & Answer to the Presentation

Question from Mr. Migunani Migunani 2020.11.18 14:30:38 What method or algorithm was used to compare and how many datasets were used and does it represent a large part of the stemming process? Replies: Reply from Ms. Dyah Mustikasari 2020.11.18 15:34:09 Thank you for your good question, we count the affix words that returned correctly to its basic word by each stemming algorithm, such as ^kesamaan^ return to ^sama^ by sastrawi, nazief-adriani, but not by arifin setiono that return it to the word ^kesamaan^. we used 363 data, but will add to 1000 words of data, in order to represent larger stemming process and obtain more valid result or comparison

Question from Mr. Yusuf Adam 2020.11.18 11:06:37 for the latest vocabulary, has it been included in the process of this research (for example, the word ^Kepo^) Replies: Reply from Ms. Dyah Mustikasari 2020.11.18 14:33:11 Thank you for your excellent question, Our research is limited on affix word, that is the word added with suffix, prefix, and suffix, so the new word or ^slang^ wasn^t included in the data. In addition, slang word is not listed in Indonesian Dictionary or KBBI.

Powered By Konfrenzi Ultimate 1.832L-Build7 © 2007-2025 All Rights Reserved