Claim Missing Document
Check
Articles

Found 5 Documents
Search

Analisis Sentimen Masyarakat Terhadap Kebijakan Pemerintah Selama Pandemi Covid-19 Menggunakan Algoritma Naïve Bayes Emeraldi, Muhammad Aqil; Ekawati, Inna; Sumadyo, Malikus
Journal of Students‘ Research in Computer Science Vol. 3 No. 1 (2022): Mei 2022
Publisher : Program Studi Informatika Fakultas Ilmu Komputer Universitas Bhayangkara Jakarta Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31599/ycx3jc57

Abstract

The increase in data is very large, one of the sources comes from social media, especially Twitter which talks a lot about Covid-19 . The news through Twitter media regarding the impact of the Covid-19 virus is widely discussed because it causes unrest for the public which has led to the issuance of various government policies with the aim of preventing the spread of Covid-19 . Related to this, it is necessary to conduct a sentiment analysis of the text contained in the Twitter media. In this study, a sentiment analysis process was carried out related to public sentiment towards government policies during the Covid-19 pandemic in Indonesia on Twitter social media using the Naive Bayes Classifier method where the data used was classified into 2 sentiment values, namely positive and negative sentiment. The data used are 300 positive tweets data and 300 negative tweets data, where 80% of the total data is used as training data and 20% data is used as test data. Based on the test results, the data with a total of 120 tweets obtained the results of measuring the recall value of 93.33%, precision 93.33%, F-Score 93.33% and an average accuracy of 93.33%.
Deteksi Emosi Menggunakan Convolutional Neural Network Berdasarkan Ekspresi Wajah Ekawati, Inna; Putra, Fadilla Nidya Riyanto; Sumadyo , Malikus; Whidhiasih, Retno Nugroho
Journal of Students‘ Research in Computer Science Vol. 5 No. 1 (2024): Mei 2024
Publisher : Program Studi Informatika Fakultas Ilmu Komputer Universitas Bhayangkara Jakarta Raya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31599/h0kayy31

Abstract

Facial expression recognition is an effective method for identifying someone's emotional expression. Emotional expressions can be recognized from changes in facial expressions, wrinkles on the forehead, blinking of the eyes, or changes in facial skin color. Facial expressions that a person generally has, such as neutral, angry, happy expressions. The problem that often occurs is the subjective assessment of a person's expression. This research examines how artificial intelligence can recognize facial expressions. The facial recognition process in the research uses a Convolutional Neural Network (CNN), which is a deep learning method capable of carrying out an independent learning process for object recognition, object extraction and classification and can be applied to high resolution images that have a nonparametric distribution model. The two main stages in CNN are feature learning and classification. The results of facial expression recognition can be used to detect a person's emotions. This research uses the FER2013 dataset which contains images of happy, sad, angry, afraid, surprised, disgusted and neutral emotions. The data set in the research received tests that had been carried out, namely the percentage of accuracy level in the model was 76%. It is hoped that the classification of emotions resulting from this research can contribute to the development of artificial intelligence technology and as a tool in various fields such as psychology, education and others. For further research, it can be developed further by adding other architectures such as VGG19, MobileNet, and ResNet-50 so that the resulting CNN model is more optimal.
Prediksi Sentimen Masyarakat Terhadap Kebijakan Pemerintah Selama Pandemi Covid-19 Menggunakan Support Vector Machine dan Naïve Bayes Ekawati, Inna
JREC (Journal of Electrical and Electronics) Vol. 10 No. 2 (2022): JREC (Journal of Electrical and Electronics)
Publisher : Program Studi Teknik Elektro Fakultas Teknik Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/jrec.v10i2.5608

Abstract

Selama masa pandemi Covid-19 pemerintah telah mengeluarkan berbagai kebijakan dengan tujuan untuk mencegah penyebaran virus Covid-19. Twitter menjadi salah satu pilihan media sosial bagi masyarakat untuk menyampaikan aspirasi maupun sekedar berkomentar. Pada penelitian ini dilakukan analisis sentimen masyarakat terhadap kebijakan pemerintah selama pandemi Covid-19 di Indonesia pada media sosial twitter menggunakan algoritma Support Vector Machine (SVM) dan Naive Bayes. Penelitian ini membandingkan kinerja klasifikasi antar kedua algoritma tersebut. Metode yang digunakan adalah text mining terhadap data tweets pada twitter yang berkaitan dengan kebijakan pemerintah dalam masa pandemi Covid-19. Total dataset yang digunakan adalah 381 data dengan sentimen positif sebanyak 190 data dan sentimen negatif sebanyak 191 data. Keseluruhan dataset yang digunakan akan terbagi menjadi 80% sebagai data training dan 20% sebagai data testing. Evaluasi dari setiap algoritma dilakukan dengan menganalisis akurasi, f1 score, precision, dan recall. Hasil penelitian menunjukkan bahwa kedua algoritma tersebut memiliki timgkat akurasi yang baik, dengan perolehan akurasi sebesar 90,91% untuk Naïve Bayes dan 88,31% untuk SVM yang sedikit lebih rendah dibanding dengan lawannya. Hasil komparasi akurasi yang baik dari kedua algoritma ini dapat dijadikan pilihan dalam menyusun aplikasi analisis sentimen, sehingga dapat menjadi salah satu solusi bagi pemerintah untuk mempermudah evaluasi kebijakannya selama pandemi Covid-19.
Evaluasi Penggunaan Website Kampus Menggunakan Metode Usability Testing dan System Usability Scale Ekawati, Inna; Sumadyo, Malikus; Whidhiasih, Retno Nugroho
JREC (Journal of Electrical and Electronics) Vol. 11 No. 2 (2023): JREC (Journal of Electrical and Electronics)
Publisher : Program Studi Teknik Elektro Fakultas Teknik Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/jrec.v11i2.7957

Abstract

The campus website is the face of an institution that can be accessed online by everyone because the website is a central information service. When individuals such as potential students, the wider public, and those within the institution itself require information about the campus, they will primarily turn to the website as their main source. However, not all campus websites have a perfect role as information and service centers. The quality of a campus website can be seen from the perception and feedback of its users. Therefore, an assessment of online media usage, especially websites, is essential at all times to understand user perceptions of the ongoing website development. This research is intended to evaluate the usability of the website of Islamic University 45 Bekasi to obtain the best recommendations for improvement. In addition to the evaluation, this research also compares two methods of website usability evaluation. The methods to be used are usability testing and the System Usability Scale. Both methods are conducted simultaneously to obtain qualitative and quantitative data. This research yields recommendations for areas that need improvement or enhancement and also provides a comparison of the two methods used as references for usability evaluation. The research results reveal that with the first method, there is a significantly higher number of positive perceptions than negative ones, although there are many suggestions for improvement. On the other hand, when using the second method, the campus website exhibits the second least favorable usability score among a total of eleven levels.
Pelacakan Geometri Segitiga dan Lingkaran di Kawasan Tepi untuk Segmentasi Objek Sucipto, Putra Wisnu Agung; Firasanti, Annisa; Bakri, Muhammad Amin; Ekawati, Inna; Yaqin, Khusnul
Jurnal Telematika Vol. 19 No. 2 (2024)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v19i2.717

Abstract

Segmentation of yellow fish egg spheres in digital images often fails due to the difficulty of determining the boundaries between adjacent or overlapping objects. This research proposes a geometry tracking-based segmentation method to solve the problem. This method uses triangulation of three important edge points around the object to determine the initial segment landmarks. Then, it uses their formation to form a complete circle of candidate segments. The set of pixels enveloped by this circle will be examined for shape and colour to be recognised as segments of an object or not. The method was tested on a fish egg image dataset containing more than 5,473 yellow-orange coloured fish egg spheres in 11 digital images. These egg sphere images vary in size, shape, brightness, contrast, density, shadow, noise, light reflection, and blur. Based on the experimental results, the method was able to correctly segment 4,370 egg spheres with 242 false segments and 1,103 undetected spheres. The performance metrics of this method are precision 94.7%, recall 79.8%, IoU 76.5%, and dice coefficient 86.7%.