Article Per Year (5 Year)
p-Index From 2020 - 2025
0
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Fera Fanesya
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 
Deteksi Emosi Pada Twitter Menggunakan Metode Naive Bayes Dan Kombinasi Fitur Fera Fanesya; Randy Cahya Wihandika; Indriati Indriati
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 3 No 7 (2019): Juli 2019
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (911.155 KB)

Abstract

Emotion shapes human behavior in general and very important in life. Detecting emotions provides an important role in various aspects because it can be applied in various fields such as decision-making, predicting human emotions conditions, providing a review product quality, tracking support for political problems, and recognizing depression disorders. Identifying emotions can use textual data that is text, text can be used to communicate and declare information. The social media that used to exchange information is Twitter. Twitter contains information about human attitude and human emotions. Therefore, emotional detection is needed to determine human emotions using Naive Bayes method and feature combinations. This research using several Naive Bayes classification models namely Bernoulli Naive Bayes for binary data types and Multinomial Naive Bayes for discrete data types. Feature Combination used in this research is as follows: linguistic features, orthographic features, and N-gram feature combinations. The best accuracy result obtained a value of 0.555 that is in testing N-gram feature combinations. While the combination of features including linguistic features, orthographic features, and N-gram features produced an accuracy value of 0.5317 which means this value was better than testing with a single feature and lower than testing the N-gram feature combinations. This is due to the influence of linguistic features, orthographic features, and N-gram features. Based on these results it can be concluded that by using combination features can cover the weaknesses of each feature that can improve the performance of accuracy even though the increase is not too significant.
Co-Authors Indriati Indriati Randy Cahya Wihandika