Service in the world of education is an important element for the creation of an academic atmosphere that is conducive to the implementation of a successful teaching and learning process. The process of service to students there is a tendency to be implemented not following the minimum service standards that must be provided to students so that students tend to complain about the services provided. Submission of criticism, complaints, input, or suggestions for dissatisfaction and problems that exist in the university environment is still very limited. Complaints can be constructive if submitted to the right place and party. In this research the data processing of email complaints from students conducted at the academic student body (students.bsi.ac.id). Student complaint data that will be processed is data in the form of * .xls complaint file. Before text data is analyzed using text mining methods, the pre-processing text needs to be done including tokenizing, case folding, stopwords, and stemming. After pre-processing, the classification method is then performed in classifying each complaint category and dividing the status into two parts, namely complaint and not complaint so that the status becomes a normal condition in text mining research. The purpose of this study is to obtain the most accurate algorithm in the classification of student complaints and can find out the results of the classification of the Naïve Bayes algorithm method and Support vector Machine used and compared. In this study, the results of testing by measuring the performance of these two algorithms using Cross-Validation, Confusion Matrix, and ROC Curves. The obtained Support vector Machine algorithm has the highest accuracy value compared to Naïve Bayes. AUC value = 0.922. for the Support vector machine method using the student academic data collection dataset (students.bsi.ac.id) has 84.45%, from the Naïve Bayes algorithm has an accuracy rate of about 69.75% and AUC value = 0.679.
Twitter merupakan salah satu media sosial yang digunakan untuk menyampaikan pendapat dan mendiskusikan berbagai topik seputar. Salah satu topik yang sering dibahas adalah marketplace. Bukalapak merupakan salah satu marketplace terpopuler di Indonesia. Bukalapak memberikan penggunanya kemampuan untuk melakukan transaksi dengan cepat dan aman. Tanggapan yang diberikan oleh pengguna tersebut dapat berupa tanggapan positif, negatif dan netral. Oleh karena itu diperlukan suatu metode yang dapat digunakan untuk mengetahui pendapat pengguna Bukalapak di media sosial Twitter. Untuk mengatasi masalah ini, diperlukan suatu metode yang dapat mengkategorikan pendapat-pendapat tersebut. Support Vector Machines merupakan salah satu metode penggalian teks yang dapat mengkategorikan opini tersebut. Data yang diperoleh dari Twiiter akan diberi label dan dianalisis menggunakan metode SVM untuk mengklasifikasikan opini-opini tersebut. Hasil klasifikasi menggunakan metode SVM diperoleh tingkat akurasi sebesar 93%.
Corona Virus 19 (COVID-19) is a contagious viral infection that has now spread to various countries, one of which is Indonesia. Monitoring of the spread of COVID-19 in Indonesia is handled directly by the Government of Indonesia, especially by the Ministry of Communication and Information (KOMINFO) with the creation of the Protected application found on Google Play. Users provide reviews or comments about the application, of course, users will choose applications that have good reviews. However, monitoring reviews from the general public is not easy, because there are so many of them to process. So that the researcher wants to know the extent of the analysis of user reviews of the PeduliLindungi application based on reviews of user comments by using classification techniques, namely the Support Vector Machine (SVM) Algorithm and Naive Bayes Based on Particle Swarm Optimization (PSO). The test results with the accuracy value and AUC value of each, namely for the PSO-based Naive Bayes algorithm the accuracy value = 69.00%, and AUC value = 0.659, while for the PSO-based SVM algorithm the accuracy value = 93.0% and the AUC value = 0.977. For this reason, the application of Particle Swarm Optimization (PSO) -based Support Vector Machine in this study has higher accuracy so that it can be used to provide solutions to sentiment analysis problems in review comments of users of the PeduliLindungi application.
Informasi mengenai Akademik adalah bagian sangat penting dalam kehidupan sehari-hari, dimana informasi Akademik tersebut diperoleh salah satunya dengan kosultasi langsung dengan customer service. Berdasarkan wawancara yang dilakukan terhadap beberapa mahasiswa. mahasiswa memperoleh informasi Akademik dengan cara berkunjung ke kampus dan bertanya langsung terhadap customer service.Penyampaian informasi Akademik tersebut dirasa kurang karena keterbatasan oleh waktu jam buka kampus, sedangkan banyak mahasiswa sangat membutuhkan informasi Akademik dan konsultasi Akademik dengan cepet dan tidak mau terikat oleh waktu buka kampus, bahkan mahasiswa mengalami masalah Akademik disaat kampus sudah tutup, dan membutuhkan konsultasi customer service. Dengan permasalahan tersebut maka banyak mahasiswa yang salah terima dalam mencerna informasi dari akademik. Untuk menyampaikan informasi Akademik yang tidak terikat oleh waktu buka kampus, Universitas AMIKOM Yogyakarta memerlukan suatu alat media layanan informasi Akademik yang dapat merespon setiap pertanyaan mahasiswa tanpa ada keterbatasan waktu dan jumlah customer service. Pada penelitian ini solusi yang diusulkan untuk masalah tersebut salah satunya dengan cara membangun sebuah aplikasi chatbot informasi Akademik (customer service virtual) dengan pendekatan Natural Language Processing dengan menggunakan medote Fuzzy String Matching sebagai media penalarannya. Teknologi chatbot merupakan salah satu bentuk aplikasi Natural Language Processing, NLP itu sendiri merupakan salah satu bidang ilmu Kecerdasan Buatan ( Artificial Intelligence ) yang mempelajari komunikasi antara manusia dengan komputer melalui bahasa alami.
Indonesia is an agrarian country, which is a sector that plays an important role most of the Indonesian population makes agriculture the main focus, but the function of rice fields into housing or industry has resulted in a decrease in rice production, in addition to pests, diseases, unfavorable weather, Irrigation is not smooth resulting in less than the maximum yield. For this reason, it is necessary to have technology that can implement the process of detecting rice leaf disease in order to provide information to farmers about rice leaf damage. The most modern approach today can be done with machine learning or deep learning by using various algorithms to improve recognition and accuracy in the detection and diagnosis of plant diseases. Based on this, this study aims to propose a method of classifying rice leaf diseases in order to provide information to farmers about rice leaves which are expected to reduce the disease by detecting the disease early so as to increase rice production. In this study, the classification process is carried out using the augmented image, then the Color Histogram feature extraction method is applied, and the classification is carried out using the Random Forest algorithm. In addition, this study also conducted several comparisons, including feature extraction and yahoo to get the results, and the highest results reached 99.65% of the proposed method. Keywords: Color Histogram; Rice Leaf Disease; Random Forest.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.