Analisis sentimen merupakan bidang yang saat ini sangat diminati oleh berbagai kalangan. Analisis sentimendapat dilakukan dengan menggunakan dokumen maupun opini dari media sosial. Salah satu media sosial yang biasanya digunakan sebagai sarana opini adalah media sosial Facebook. Sebelum sebuah teks diklasifikasikan, perlu dilakukan POS Tagging yang merupakan tahap pelabelan kata dimana tujuannya adalah untuk menentukan kata yang termasuk opini dan non opini. Untuk pelabelan kata dapat menggunakan Hidden Markov Model maupun Rule Based. Adapun metode yang biasa digunakan dalam analisis sentimen adalah metode Naïve Bayes Classifier. Metode ini mengklasifikasikan probalitas dengan sederhana. Naïve Bayes Classifier dapat digunakan untuk mengklasifikasikan opini ke dalam opini positif maupun negatif. Selain itu metode ini menggunakan data latih dalam proses klasifikasinya. Klasifikasi yang dihasilkan dari metode Naïve Bayes Classifier tergolong cukup baik. Untuk menguji tingkat keakuratan sistem dalam mengklasifikasikan opini, maka dilakukan pengujian hasil klasifikasi. Dari hasil pengujian diperoleh rata-rata akurasi sebesar 87,1 %. Semakin banyak data latih yang mirip dengan data testing maka hasil klasifikasi akan semakin bagus. Kata Kunci—Facebook, Analisis Sentimen, POS Tagging, Naïve Bayes Classifier, Akurasi

— Formulating a marketing strategy for a pioneering or long-running restaurant business is a very important thing. Analyze the weaknesses or strengths of business competitors is one of these strategies. Identification of weaknesses and strengths can be done by taking data from comments on competitors' Instagram accounts using Text Preprocessing Techniques. Text Preprocessing is a text processing algorithm, consisting of Transform Cases, Stopword Filters, Tokenize Filters, and Stemming. Instagram is one of the most widely used social media accounts as a promotional media in Indonesia. Another method that can be used is Full Text Search, this method can analyze the patterns in comments that have been parsed for classified into positive, negative, or neutral sentiment categories. This study concludes that this sentiment analysis system can automatically recognized weaknesses (based on negative comments) and strengths (based on positive comments) based on comments on Instagram accounts owned by restaurant business competitors with an accuracy of 85% and a precision value of 79%.

Various web-based information systems are developed by Indonesian government to improve quality of services for their society. It encourages users, generally civil servants, to perform different authentications on used information systems and have to remember credentials. Account management of the users poses another challenge for administrators. Single Sign-On (SSO) can be the solution by providing a service of centralized authentication and user account management. This study applies a token-based SSO architecture and uses Json Web Token (JWT) to grant permission authorities, since JWT can provide a claim process between 2 parties. Additionally, the built-in dashboard lists associated information systems to facilitate accessing for the authenticated users. This study will discuss JWT implementation on the dashboard of government information systems that implements SSO, which will generate the permission authorities securely for connected information systems on SSO.

Salah satu bencana alam yang hampir sering terjadi pada setiap musim penghujan adalah banjir. Kota Denpasar mengalami perkembangan pembangunan yang cukup pesat dengan berbagai fungsi antara lain kota pendidikan, perdagangan dan pariwisata, karena mengalami perubahan tata guna lahan dan perkembangan penduduk yang pesat dapat menimbulkan dampak negatif yakni berkurangnya daya resap tanah dan meningkatnya kawasan- kawasan rawan banjir yang pada akhirnya menimbulkan keluhan- keluhan dari masyarakat di daerah tersebut. Lewat empat parameter yaitu peristiwa banjir pada beberapa waktu yang lalu, intensitas curah hujan, ketinggiaan wilayah dan kepadatan pemukiman dapat menentukan daerah potensi bencana banjir di wilayah Kota Denpasar dengan menggunakan metode Analytical Hierarchy Process. Bobot perhitungan dari parameter banjir tersebut dapat dihasilkan peta daerah potensi rawan banjir di Kota Denpasar. Diperoleh daerah potensi rawan banjir level tinggi sebesar 9%, level sedang sebesar 28% dan level rendah sebesar 63% dari 43 desa di Kota Denpasar. Hasil ini dapat dijadikan masukan bagi seluruh pemangku kepentingan selaku pengambil kebijakan dapat mengambil keputusan dalam manajemen bencana banjir.

Technology revolution in computer and information made Learning Man-agement System has widely been used to assist learning process. On the other side the advancement of technology in multimedia made many re-searchers have positive result in game based learning as factor that increase motivation and interest to deliver educational information. We try to pro-pose a concept to implement a multiplayer matching quiz in Moodle LMS to enrich game based learning using Moodle future research about game-based learning implementation in Moodle. The proposed model implements websocket as its multiplayer backend and game questions using Moodle Quiz plugin as a question bank.

The plasmasphere within Earth’s magnetosphere plays a crucial role in space physics, with its electron density distribution being pivotal and strongly influenced by solar activity. Very Low Frequency (VLF) waves, including whistlers, provide valuable insights into this distribution, making the study of their propagation through the plasmasphere essential for predicting space weather impacts on various technologies. In this study, we evaluate the performance of different deep learning model sizes for lightning whistler detection using the YOLO (You Only Look Once) architecture. To achieve this, we transformed the entirety of raw data from the Arase (ERG) Satellite for August 2017 into 2736 images, which were then used to train the models. Our approach involves exposing the models to spectrogram diagrams—visual representations of the frequency content of signals—derived from the Arase Satellite’s WFC (WaveForm Capture) subsystem, with a focus on analyzing whistler-mode plasma waves. We experimented with various model sizes, adjusting epochs, and conducted performance analysis using a partial set of labeled data. The testing phase confirmed the effectiveness of the models, with YOLOv5n emerging as the optimal choice due to its compact size (3.7 MB) and impressive detection speed, making it suitable for resource-constrained applications. Despite challenges such as image quality and the detection of smaller whistlers, YOLOv5n demonstrated commendable accuracy in identifying scenarios with simple shapes, thereby contributing to a deeper understanding of whistlers’ impact on Earth’s magnetosphere and fulfilling the core objectives of this study.