Erwin B. Setiawan

Erwin B. Setiawan

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 March 2019 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
AFAlif Azhar Fakhri
Alif Azhar Fakhri
ZBZ K A Baizal
Z K A Baizal
ESErwin B. Setiawan
Erwin B. Setiawan

17 January 2023 in Jurnal Ilmiah Teknik Elektro Komputer dan Informatika
Verified
Journal Article
Open access
PDF file
AAAhmad Zahri Ruhban Adam
Ahmad Zahri Ruhban Adam
ESErwin B. Setiawan
Erwin B. Setiawan
The advancing technologies are aimed to maximize human performance. One of the great developments in technology is social media. The social media used in this study is Twitter because most people in Indonesia give their opinions to the public through tweets. The opinions given are very diverse, where they write positive, negative, and neutral opinions. The purpose of this study is to analyze the sentiments of the opinions given by the public in Bahasa Indonesia. To conduct sentiment analysis, tweets are collected by crawling the data. Tweets are then labeled positive, negative, and neutral and then represented as 1, -1, and 0. The method used to classify tweet sentiment is the Convolutional Neural Network (CNN) and Gated Recurrent Unit method (GRU). Research stages including feature selection, feature expansion, preprocessing and balancing with SMOTE. The highest accuracy value obtained on the CNN-GRU model with an accuracy value of 97.58% value. Based on these tests, it can be concluded that sentiment analysis research on Twitter social media using the Convolutional Neural Network and Gated Recurrent Unit methods can produce fairly high accuracy, and feature expansion testing of the deep learning model can provide a significant increase in accuracy values.

31 August 2023 in Revue d'intelligence artificielle
Verified
Journal Article
Closed access
MNMuhammad Alfi Syahri Nasution
Muhammad Alfi Syahri Nasution
ESErwin B. Setiawan
Erwin B. Setiawan

1 March 2019 in Journal of Physics: Conference Series
Verified
Conference Paper
Open access
PDF file
AFA Fauzi
A Fauzi
ESErwin B. Setiawan
Erwin B. Setiawan
ZBZ K A Baizal
Z K A Baizal
Twitter is one of the social media that is currently popularly used around the world. It's just that twitter has some problems that adversely affect its users. Hoax is one of the negative things that often occur in social media, news in the hoax is still doubted the truth or the fact. In this final project, the authors built a system to detect hoax news on twitter. The purpose of the research is to minimize the hoax news spread on twitter. The use of the Term Frequency Inverse Document Frequency (TF-IDF) weighting system in the system gives a weighted value to a tweet taken from the occurrence of a hoax news sent by someone on Twitter. Data classification uses the Support Vector Machine (SVM) method of the system to predict the possibility of a twitter account user spreading a hoax news based on the user's behavior. Testing data is done based on the contents of content tweets. Datasets are arranged based on attributes used such as the number of retweets, URLs, number of hashtags, provocations, feuds, anxieties, and unbalanced news. Processed data is divided into training data and testing data. The result of data using all features get the highest accuracy is 78,33%. The contribution of this research is that it can detect news that has a tendency towards hoax and can filter which is classified as hoax or not hoax.

10 July 2023 in Jurnal Ilmiah Teknik Elektro Komputer dan Informatika
Verified
Journal Article
Open access
PDF file
KWKevin Usmayadhy Wijaya
Kevin Usmayadhy Wijaya
ESErwin B. Setiawan
Erwin B. Setiawan
Twitter is a popular social media for sending text messages, but the tweets that can send are limited to 280 characters. Therefore, sending tweets is done in various ways, such as slang, abbreviations, or even reducing letters in words which can cause vocabulary mismatch so that the system considers words with the same meaning differently. Thus, using feature expansion to build a corpus of similarity can mitigate this problem. Two datasets constructed the similarity corpus: the Twitter dataset of 63,984 and the IndoNews dataset of 119,488. The research contribution is to combine deep learning and feature expansion with good performance. This study uses FastText as a feature expansion that focuses on word structure. Also, this study uses four deep learning methods: Convolutional Neural Network (CNN), Gated Recurrent Unit (GRU), and a combination of the two CNN-GRU, GRU-CNN classification with boolean representation as feature extraction. This study uses five scenarios to find the best result: best data split, n-grams, max feature, feature expansion, and dropout percentage. In the final model, CNN has the best performance with an accuracy of 88.79% and an increase of 0.97% from the baseline model, followed by GRU with an accuracy of 88.17% with an increase of 0.93%, CNN-GRU with an accuracy of 87.47% with an increase of 1.86%, and GRU-CNN with an accuracy of 87.55% with an increase of 1.32%. Based on the result of several scenarios, the use of feature expansion using FastText succeeded in avoiding vocabulary mismatch, proven by the highest increase in accuracy of the model than other scenarios. However, this study has a limitation is that the dataset is used in Indonesian.

24 January 2024 in Jurnal Ilmiah Teknik Elektro Komputer dan Informatika
Verified
Journal Article
Open access
PDF file
ANArliyanna Nilla
Arliyanna Nilla
ESErwin B. Setiawan
Erwin B. Setiawan
Film Recommendation System Using Content-Based Filtering and the Convolutional Neural Network (CNN) Classification Methods