Garuda - Garba Rujukan Digital

Sistem Pakar untuk Mendiagnosis Gangguan Tidur Menggunakan Metode Dempster Shafer Ivo Dwi Ananda; Rahmad Kurniawan; Novi Yanti; Fitri Insani
J I M P - Jurnal Informatika Merdeka Pasuruan Vol 6, No 3 (2021): DESEMBER
Publisher : Fakultas Teknologi Informasi Universitas Merdeka Pasuruan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37438/jimp.v6i3.354

Poor quality of sleep can cause psychological and physiological health problems. Estimated from 238,452 million people in Indonesia every year, about 67% elderly people reported having trouble sleeping. With a prevalence of 10% or about 28 million people suffering from sleep disorders. This makes Indonesia has the highest number of sleep disorders in Asia. The cases of sleep disorders increased during the Covid-19 pandemic by 23.87% in general public and by 36.53% in medical personnel. This study aims to build a system that can diagnose sleep disorders like an expert. This study employed the Dempster Shafer method with 25 symptoms and four types of sleep disorders. The Dempster Shafer method is a commonly applied technique which is combining evidence in uncertainty cases. The experimental testing based on the validation of the results of the system diagnosis with expert diagnosis, the percentage of test accuracy is 90%. It can be concluded that the system potentially be used for early sleep disorder diagnosis.Keywords—expert system, dempster shafer, sleep disorders, sleep quality, uncertainty.

Penerapan Algoritma K-Means Clustering dan Correlation Matrix Untuk Menganalisis Risiko Penyebaran Demam Berdarah di Kota Pekanbaru m azwan; Rahmad Kurniawan; Pizaini Pizaini; Fitri Insani
J I M P - Jurnal Informatika Merdeka Pasuruan Vol 6, No 3 (2021): DESEMBER
Publisher : Fakultas Teknologi Informasi Universitas Merdeka Pasuruan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37438/jimp.v6i3.353

Dengue cases in Pekanbaru in November 2020 reached 2,788 cases and 33 deaths. The government has carried out socialization to eradicate mosquito nests and provided vector control tools and materials. However, the government's efforts were not practical because the applied method has not been able to refer to vector data and information. Machine learning can be used to analyze specific problems such as Dengue. Therefore this study employed a Machine Learning algorithm, i.e., k-means clustering and correlation matrix for dengue risk analysis in Pekanbaru. This study obtained 12 sub-districts and 50 dengue attributes and weather data in 2020. K-means automatically searches for unknown clusters from dengue cases data quickly, which cluster results C1 (Sukajadi, Senapelan), C2 (Tenayan Raya, Tampan), and C3 (Rumbai Pesisir, Rumbai). Based on experimental testing, this study produced a silhouette score is 0.6. Meanwhile, the correlation matrix looks for relevant relationships hidden in the data. The correlation matrix obtained a strong linear relationship between the population (JP) and sufferers (P) of 0.73 for January and 0.93 for February 2020.Keywords— Dengue Fever, K-means, Correlation matrix, Machine learning.

Algoritme Logistic Regression untuk Mendeteksi Ujaran Kebencian dan Bahasa Kasar Multilabel pada Twitter Berbahasa Indonesia Ayu Fransiska; Surya Agustian; Fitri Insani; Muhammad Fikry; Pizaini Pizaini
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 4 (2022): Agustus 2022
Publisher : Program Studi Teknik Informatika, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i4.4524

Abstrak - Ujaran kebencian semakin meningkat bersamaan dengan banyaknya pengguna media sosial. Twitter merupakan salah satu media sosial yang membantu penyeberan ujaran ujaran melalui fitur twit-nya yang dilakukan berulang-ulang. Penelitian ini dilakukan untuk mengklasifikasi apakah sebuah twit mengandung ujaran kebencian atau bahasa kasar, dan jika terdeteksi mengandung ujaran kebencian maka akan diukur tingkatannya. Dataset yang digunakan diambil dari twitter sebanyak 13.126 twit asli. Klasifikasi menggunakan Algoritma logistic Regression dan fitur teks word embedding. Dilakukan beberapa kali percobaan untuk mendapatkan model terbaik agar pengujian didapatkan secara optimal. Rata-rata akurasi yang dari ketiga kelas sebesar 75,59%, untuk kelas hate speech 75,86%,kelas abusive 80,05%, kelas level 70,86% dengan komposisi 90:10.Kata kunci: Klasifikasi, Logistic Regression, Ujaran Kebencian, Twitter. Abstract - Hate speech is increasing along with the number of social media users. Twitter is one of the social media that helps spread utterances through its repeated tweet features. This study was conducted to classify whether a tweet contains hate speech or abusive language, and if it is detected to contain hate speech, the level will be measured. The dataset used was taken from twitter as many as 13,126 original tweets. Classification using Logistic Regression Algorithm and word embedding text feature. Several experiments were carried out to get the best model so that the test was obtained optimally. The average accuracy of the three classes is 75.59%, for the hate speech class is 75.86%, the abusive class is 80.05%, the level class is 70.86% with a composition of 90:10.Keyword : Classification, Logistic Regression, Hate Speech, Twitter.

Penerapan Algortitma C4.5 untuk Klasifikasi Sentimen Masyarakat terhadap #RUUKUHP pada Twitter Imam Vusuvangat; Siska Kurnia Gusti; Fadhilah Syafira; Novriyanto Novriyanto; Fitri Insani
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 6 No. 4 (2023): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

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

Social media, especially Twitter, has developed into an important tool for people to share their opinions and feelings widely. Users often use hashtags to share messages related to certain topics. Some of the issues that lead to the need for sentiment analysis of the Draft Criminal Code are social impact, Public disapproval, Potential legal uncertainty, Potential abuse, Support and criticism. By conducting a sentiment analysis of the draft Penal Code, the government and policymakers can better understand the views of the public, identify possible problems and address them, and make necessary improvements or clarifications to the draft law. This can help ensure that the draft Penal Code has greater public support and adheres to good legal principles. The classification of public responses to this hashtag provides a significant snapshot of public attitudes and perspectives. This study aims to classify public sentiment towards the RUUKUHP hashtag on the Twitter platform using the C4.5 algorithm. This study uses a collection of tweets with the hashtag RUUKUHP which are manually categorized into two and three sentiment categories, namely positive, negative and positive, negative and neutral. In this study, data preprocessing is carried out before training the model which includes removing links, special characters, removing stopwords, and word tokenization. Furthermore, this research uses text representation methods such as TF-IDF to extract features from the tweet text and convert them into numerical vectors used by the C4.5 algorithm. After training the classification model using the C4.5 algorithm with the classified dataset, it evaluates the performance of the model with the metrics of accuracy, recall, precision, and F1 score. Experimental results using 2 categories of Negative and Positive show that the model applied with the C4.5 algorithm achieved an accuracy of 96.6% with a recall of 96.6%, a percision of 97.1% and an F1 score of 96.8. And experiments using 3 categories of Negative, Positive and Neutral achieved an accuracy of 67%, a recall of 67%, a precision of 65%, and an F1 score of 66%. Thus it can be concluded that the results of the RUUKUHP hashtag sentiment classification with 2 class predictions are more relevant than 3 sentiment class predictions with a value reaching 96.6%.

Algoritme Logistic Regression untuk Mendeteksi Ujaran Kebencian dan Bahasa Kasar Multilabel pada Twitter Berbahasa Indonesia Ayu Fransiska; Surya Agustian; Fitri Insani; Muhammad Fikry; Pizaini Pizaini
Jurnal Nasional Komputasi dan Teknologi Informasi (JNKTI) Vol 5, No 4 (2022): Agustus 2022
Publisher : Program Studi Teknik Komputer, Fakultas Teknik. Universitas Serambi Mekkah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32672/jnkti.v5i4.4524

Abstrak - Ujaran kebencian semakin meningkat bersamaan dengan banyaknya pengguna media sosial. Twitter merupakan salah satu media sosial yang membantu penyeberan ujaran ujaran melalui fitur twit-nya yang dilakukan berulang-ulang. Penelitian ini dilakukan untuk mengklasifikasi apakah sebuah twit mengandung ujaran kebencian atau bahasa kasar, dan jika terdeteksi mengandung ujaran kebencian maka akan diukur tingkatannya. Dataset yang digunakan diambil dari twitter sebanyak 13.126 twit asli. Klasifikasi menggunakan Algoritma logistic Regression dan fitur teks word embedding. Dilakukan beberapa kali percobaan untuk mendapatkan model terbaik agar pengujian didapatkan secara optimal. Rata-rata akurasi yang dari ketiga kelas sebesar 75,59%, untuk kelas hate speech 75,86%,kelas abusive 80,05%, kelas level 70,86% dengan komposisi 90:10.Kata kunci: Klasifikasi, Logistic Regression, Ujaran Kebencian, Twitter. Abstract - Hate speech is increasing along with the number of social media users. Twitter is one of the social media that helps spread utterances through its repeated tweet features. This study was conducted to classify whether a tweet contains hate speech or abusive language, and if it is detected to contain hate speech, the level will be measured. The dataset used was taken from twitter as many as 13,126 original tweets. Classification using Logistic Regression Algorithm and word embedding text feature. Several experiments were carried out to get the best model so that the test was obtained optimally. The average accuracy of the three classes is 75.59%, for the hate speech class is 75.86%, the abusive class is 80.05%, the level class is 70.86% with a composition of 90:10.Keyword : Classification, Logistic Regression, Hate Speech, Twitter.

Title

Found 5 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 5 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 5 Documents
Search