Rancang Bangun Sistem Pendeteksi Kemiripan Pertanyaan Pada Kegiatan Seminar Menggunakan Metode Term Frequency – Inverse Document Frequency Dan Vector Space Model (Studi Kasus : IT PLN)
Total View This Week0
Total View This Week0
Institusion
Institut Teknologi Perusahaan Listrik Negara
Author
Dharma, Alvian Adi
Putra, Rakhmadi Irfansyah
Prathama, Muhammad Fadli
Putra, Rakhmadi Irfansyah
Prathama, Muhammad Fadli
Subject
Teknik Informatika
Datestamp
2022-09-26 07:13:47
Abstract :
The purpose of this research is to create a question-similarity detector in a seminar event where the current system of collecting the questions is by asking through the seminar moderator and those questions will be asked to the speaker when the QnA session is started. Sometimes, there are many similar purposes of those participants? questions are found. This research is using Waterfall model where it is consist of requirement analysis, system design, implementation, verification, operation and maintenance. On the other hand, Text Mining, TF IDF, and Vector Space Model are used as this research?s methods. Text Mining is used to extract the information from the question documents. TF-IDF and Vector Space Model are used to measure the weight of those questions and count the similarity value for each question. As result, 9 similar questions has been obtained by inputting the keywords related to the seminar?s topic and the similarity ranking is displayed
The purpose of this research is to create a question-similarity detector in a seminar event where the current system of collecting the questions is by asking through the seminar moderator and those questions will be asked to the speaker when the QnA session is started. Sometimes, there are many similar purposes of those participants? questions are found. This research is using Waterfall model where it is consist of requirement analysis, system design, implementation, verification, operation and maintenance. On the other hand, Text Mining, TF IDF, and Vector Space Model are used as this research?s methods. Text Mining is used to extract the information from the question documents. TF-IDF and Vector Space Model are used to measure the weight of those questions and count the similarity value for each question. As result, 9 similar questions has been obtained by inputting the keywords related to the seminar?s topic and the similarity ranking is displayed
Download
book
BibTex
Latex, Jabref
cloud_download
Original Resource
url resource Institution
