1 March 2020 in Cybernetics and Information Technologies
Hoax news in Indonesia spread at an alarming rate. To reduce this, hoax news detection system needs to be created and put into practice. Such a system may use readers’ feedback and Naïve Bayes algorithm, which is used to verify news. Overtime, by using readers’ feedback, database corpus will continue to grow and could improve system performance. The current research aims to reach this. System performance evaluation is carried out under two conditions ‒ with and without sources (URL). The system is able to detect hoax news very well under both conditions. The highest precision, recall and f-measure values when including URL are 0.91, 1, and 0.95 respectively. Meanwhile, the highest value of precision, recall and f-measure without URL are 0.88, 1 and 0.94, respectively.
1 June 2019 in IOP Conference Series: Materials Science and Engineering
Wasting is a condition of a children characterized by a lack of weight by measuring weight for height. Currently, to monitor the growth conditions for childrens in Indonesia, we use the Towards Healthy Card called as Kartu Menuju Sehat (KMS) which is guided by WHO 2005. The samples used to design WHO-2005 standard charts are children from Brazil, Ghana, India, USA, Norway, and Oman that have different physical conditions from children in Indonesia. Therefore, the using of standards growth charts from other countries cause incompatibility with Indonesian’s children growth. To illustrate the growth patterns of children in East Java, we use the semiparametric least square spline estimator that gives more flexible pattern. In this study we used weight (kg) as a response variable, height (cm) as a predictor variable for nonparametric component, and gender as a predictor variable for parametric component. The results show the semiparametric least square spline estimator can explain the growth patterns of children well because it has determination coefficient (R2) of 99.78% and mean square error (MSE) of 0.0353. The standard chart of weight for height of boy is higher than that of girl and percentage of wasting nutritional status of girl greater than that of boy.
23 July 2023 in JURNAL MEDIA INFORMATIKA BUDIDARMA
Badan Penyelenggara Jaminan Sosial (BPJS) Kesehatan is a legal entity that provides social health insurance programs for the public released application called Mobile JKN to support various health services activities using users devices. Mobile JKN has not fully received a positive public perception and still has many shortcomings. It is necessary to conduct a deeper evaluation and analysis of the Mobile JKN. This study focuses on aspect-based sentiment analysis of user reviews on the Google Play Store to evaluate the Mobile JKN. The review data used are the last two versions, 4.2.3 and 4.3.0. This study was carried out by modeling aspects/topics using the Latent Dirichlet Allocation method and sentiment analysis using Naïve Bayes and Lexicon-Based methods. This research resulted in 3 aspects, namely Services and Features, Register and Login, and User Satisfaction. This was obtained based on the model with the highest coherence score of 0.6392 obtained in the model looping with the number of topics from 1 to 9, random state = 42, passes =50, and iteration = 60. Meanwhile, based on the sentiment analysis results, the Naïve Bayes method is better than the Lexicon-Based (Inset Lexicon) method. This is evident from performance of the Naïve Bayes with the highest accuracy score of 94.75% and Lexicon Based with Inset Lexicon obtained an accuracy score of 59.99%.
30 November 2022 in Jurnal Pendidikan Teknologi Informasi (JUKANTI)
Program Beasiswa Bidikmisi adalah program bantuan Kementerian Pendidikan dan Kebudayaan melalui Direktorat Jendral Pendidikan Tinggi Kementerian Pendidikan dan Kebudayaan mulai tahun 2010. Program tersebut ditujukan bagi mahasiswa yang memiliki perokonomian kurang mampu, namun berpotensi untuk melanjutkan ke jenjang yang lebih tinggi (pendidikan tinggi). Dilihat dari jumlah mahasiswa bidikmisi yang diterima di perguruan tinggi dan data histori pendidikan mahasiswa didapatkan data yang dapat memprediksi dan menentukan pola kelulusan mahasiswa penerima bidikmisi pada sebuah perguruan tinggi sehingga dapat dijadikan acuan kemungkinan ketepatan waktu kuliah mahasiswa penerima bidikmisi. Tujuan dari penelitian ini adalah untuk memprediksi ketepatan lulus mahasiswa penerima beasiswa bidikmisi jenjang sarjana pada sebuah universitas dengan menggunakan atribut jenis kelamin, nilai TOEFL, indeks prestasi semester 1 hingga semester 4, rata-rata nilai ijazah SMA, rata-rata nilai ujian nasional, program studi, nilai prestasi keaktifan organisasi. Uji coba dilakukan dengan percentage split data training dan evaluasi 60-40, 70-30, 80-20, dan 90-10, dengan variasi nilai k sebesar 3, 5, 7, 9, 11, 13, dan 15. Hasil dari uji coba didapatkan nilai akurasi tertinggi sebesar 93.93% pada percentage split 70-30 dan nilai k=15
1 January 2017 in AIP Conference Proceedings