Article Per Year (5 Year)
p-Index From 2020 - 2025
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Franklid Gunawan
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Pemerolehan Informasi Artikel terkait Covid-19 dengan menggunakan Metode Vector Space Model dan Word2Vec untuk Query Expansion Franklid Gunawan; Imam Cholissodin; Putra Pandu Adikara
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 5 No 3 (2021): Maret 2021
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

COVID-19 has shaken the world since the end of 2019. There are still many people who are not aware of the risk of COVID-19 despite the updated information. To prevent misinformation, trusted access is required. The amount of information provided in an information access is also not small in numbers. From those problems, a system is needed that can make it easier for people to find desired information in accessing the information provided. One system that suitable for the problem is COVID-19 articles information retrieval based on keywords provided by users. The method that can be used to build an article information retrieval is the Vector Space Model combined with Query Expansion using Word2Vec. The stages of article information retrieval system are pre-processing the dataset, word weighting, training the Word2Vec model, performing Query Expansion, calculating similarity between document and query, and sorting the document articles. The process will produce 10 news article documents related to COVID-19 that have similarities between its content and the keyword from user, the test results that get the best precision@10 and recall@10 is when the system uses 500 hidden neuron for Word2Vec training and 40 words added at the Query Expansion stage.
Co-Authors Imam Cholissodin Putra Pandu Adikara