Search

The need for monitoring of children today is very important, especially for children under five, whose physical and verbal abilities are still inadequate to be able to communicate effectively with their parents or caregivers about the conditions they are experiencing. Previous studies related to child safety that were studied generally focused on responses to events that could potentially harm children.This study aims to design a prototype child monitoring system consisting of a wearable device that is used on a child's wrist equipped with sensors and connected to a server via a wireless network. Monitoring software that runs on the server will collect all data parameters from wearable devices with built-in audio signal, temperature, and heart rate sensor then with machine learning algorithm implemented in software will allow the system to predict if stress conditions happen on children and then system can give warnings to child-caregiver through monitoring applications or SMS messages. Using the Decision Tree and Naive Bayes classification methods the system can effectively predict stress conditions in children with an accuracy of 82.8 percent using audio, temperature, and heart rate parameters. This shows that the system has the capability to contribute to increasing child safety in the supervision environment. &nbsp, Kebutuhan pemantauan terhadap anak saat ini sangat penting terutama pada anak-anak usia balita yang secara kemampuan fisik dan verbal mereka masih belum memadai untuk dapat berkomunikasi secara efektif terhadap orang tua atau pengasuh mereka terhadap kondisi yang mereka alami. Penelitian-penelitian terdahulu terkait keamanan anak yang dikaji umumnya berfokus pada respon terhadap kejadian yang berpotensi membahayakan anak yang sebenarnya bisa dideteksi lebih dini melalui kondisi stres yang dialami anak. Penelitian ini bertujuan untuk merancang purwarupa sistem monitoring dan deteksi stres anak berupa perangkat wearable yang dikenakan pada pergelangan tangan anak yang dilengkapi dengan beberapa sensor dan terkoneksi ke server melalui jaringan nirkabel. Parameter yang diterima dari sensor perangkat yaitu data audio, denyut jantung dan suhu. Dengan metode pembelajaran mesin yang diimplementasikan pada perangkat lunak yang terdiri dari fase latih dan uji yang melibatkan proses ekstraksi fitur dari data audio, memilih fitur yang mempunyai nilai diskriminatif yang tinggi dan kemudian melatih metode pembelajaran mesin untuk melakukan klasifikasi berdasarkan data tersebut selanjutnya memungkinkan sistem dapat mendeteksi kondisi stres pada anak dan memberi peringatan kepada pengawas melalui aplikasi monitoring atau pesan SMS. Menggunakan metode klasifikasi Decision Tree dan Naive Bayes sistem mampu secara efektif memprediksi kondisi stress pada anak dengan akurasi sebesar 82,8 persen menggunakan kombinasi parameter audio, suhu dan denyut jantung. Dengan demikian purwarupa sistem yang dikembangkan mampu memberi kontribusi dalam peningkatan keamanan anak dalam lingkungan yang membutuhkan pengawasan.

Diabetes merupakan penyakit yang mengancam kehidupan dengan pertumbuhan tercepat dan jika tidak diobati atau diindentifikasi akan menyebabkan komplikasi lain. Diabetes setiap tahunnya mengakibatkan kematian sebanyak 3.8 juta jiwa dan telah mempengaruhi 422 juta orang di seluruh Dunia. Dataset diabetes yang digunakan dalam penelitian ini adalah dataset publik, dataset ini akan diolah menggunakan model yang diusulkan. Dataset diabetes memiliki permasalahan seperti adanya fitur-fitur yang tidak relevan, fitur-fitur yang tidak relevan dapat menurunkan kinerja dari model yang digunakan. Seleksi fitur Greedy Forward Selection adalah seleksi fitur yang sangat efisien dan cepat dalam prosesnya. Algoritma Naïve Bayes merupakan algoritma yang mudah dan sederhana ketika diimplementasikan. Hasil penelitian menunjukkan bahwa model Naïve Bayes dan Greedy Forward Selection mendapatkan nilai akurasi tertinggi sebesar 91.73%, sedangkan model Naïve Bayes tanpa seleksi fitur Greedy Forward Selection hanya mendapat nilai akurasi sebesar 87.69%

COVID-19 has become a global pandemic including Indonesia, so the government is taking vaccinations as a preventive measure. The public's response to this continues to appear on social media platforms, one of which is Twitter. Tweets about the COVID-19 vaccine have generated various kinds of positive and negative opinions in the community. Therefore, it is very important to detect and filter it to prevent the spread of incorrect information. Sentiment analysis is a method used to determine the content of a dataset in the form of negative, positive or neutral text. The dataset in this study was obtained from 5000 COVID-19 vaccine tweets with the distribution of 3800 positive sentiment tweets, 800 negative sentiment tweets and 400 neutral sentiment tweets. The dataset obtained is then pre-processed data to optimize data processing. There are 4 stages of pre-processing, including remove punctuation, case folding, stemming and tokenizing. This study examines the performance of RNN and Naïve Bayes by adding the TF-IDF (Term Frequency-Inverse Document Frequency) technique which aims to give weight to the word relationship (term) of a document. The test results show that RNN (TF-IDF) has a greater accuracy of 97.77% compared to Naïve Bayes (TF-IDF) of 80%. &nbsp, COVID-19 telah menjadi pandemik dunia termasuk Indonesia, sehingga pemerintah mengambil tindakan vaksinasi sebagai upaya pencegahan. Tanggapan masyarakat mengenai hal tersebut terus muncul di platform media sosial salah satunya twitter. Tweet mengenai vaksin COVID-19 menimbulkan berbagai macam opini positif dan negatif di masyarakat. Oleh karena itu, sangat penting untuk mendeteksi dan menyaringnya agar tidak terjadi penyebaran informasi yang tidak benar. Analisis sentimen merupakan suatu metode yang digunakan untuk menentukan isi dari suatu dataset dalam bentuk teks yang bersifat negatif, positif atau netral. Dataset pada penelitian ini diperoleh dari 5000 tweet vaksin COVID-19 dengan pembagian 3800 tweet sentimen positif, 800 tweet sentimen negatif dan 400 tweet sentimen netral. Dataset yang didapat kemudian dilakukan pre-processing data untuk mengoptimalkan pengolahan data. Terdapat 4 tahapan pre-processing antara lain remove punctuation, case folding, stemming dan tokenizing. Penelitian ini mengkaji kinerja RNN dan Naïve Bayes dengan menambahkan teknik TF-IDF (Term Frequency-Inverse Document Frequency) yang bertujuan untuk memberikan bobot pada hubungan kata (term) sebuah dokumen. Hasil pengujian menunjukkan RNN (TF-IDF) memiliki akurasi lebih besar yaitu 97,77% dibandingkan Naïve Bayes (TF-IDF) sebesar 80%.

Muslims believe that, as the speech of Allah, The Quran is a miracle that has specialties in itself. Some of the specialties that have studied are the regularities in the number of letters, words, vocabularies, etc. In the past, the early Islamic scholars identify these regularities manually, i.e. by counting the occurrence of each vocabulary by hand. This research tackles this problem by utilizing centrality in quranic verse topic classification. The goal of this research is to analyze the effect of The Quran word centrality measure on the topic classification of The Quran verses. To achieve this objective, the method of this research is constructing the Quran word graph, then the score of centralities included as one of the features in the verse topic classification. The effect of centrality is observed along with support vector machine (SVM) and naïve Bayes classifiers by performing two scenarios (with stopword and without stopword removal). The result shows that according to the centrality measure the word “الله” (Allah) is the most central in The Quran. The performance evaluation of the classification models shows that the use of centrality improves the hamming loss score from 0.43 to 0.21 on naïve Bayes classifier with stopword removal. Finally, both of classification method has a better performance in word graph that use stopword removal. &nbsp, Muslims believe that, as the speech of Allah, The Quran is a miracle that has specialties in itself. Some of the specialties that have studied are the regularities in the number of letters, words, vocabularies, etc. In the past, the early Islamic scholars identify these regularities manually, i.e. by counting the occurrence of each vocabulary by hand. This research tackles this problem by utilizing centrality in quranic verse topic classification. The goal of this research is to analyze the effect of The Quran word centrality measure on the topic classification of The Quran verses. To achieve this objective, the method of this research is constructing the Quran word graph, then the score of centralities included as one of the features in the verse topic classification. The effect of centrality is observed along with support vector machine (SVM) and naïve Bayes classifiers by performing two scenarios (with stopword and without stopword removal). The result shows that according to the centrality measure the word “الله” (Allah) is the most central in The Quran. The performance evaluation of the classification models shows that the use of centrality improves the hamming loss score from 0.43 to 0.21 on naïve Bayes classifier with stopword removal. Finally, both of classification method has a better performance in word graph that use stopword removal.

The increasing demand for credit applications to banks has motivated the banking world to switch to more sophisticated techniques for analyzing the level of credit risk. One technique for analyzing the level of credit risk is the data mining approach. Data mining provides a technique for finding meaningful information from large amounts of data by way of classification. However, bank marketing data is a type of imbalance data so that if the classification is done the results are less than optimal. The classification algorithm that can be used for imbalance data types can use naïve Bayes. Naïve Bayes performs well in terms of classification. However, optimization is needed in order to obtain more optimal classification results. Optimization techniques in handling imbalance data have been developed with several approaches. Bagging and Genetic Algorithms can be used to overcome imbalance data. This study aims to compare the accuracy level of the naïve Bayes algorithm after optimization using the bagging and genetic algorithm. The results showed that the combination of bagging and a genetic algorithm could improve the performance of Naive Bayes by 4.57%., Peningkatan permintaan pengajuan kredit pada perbankan telah memotifasi dunia perbankan untuk beralih pada teknik yang lebih canggih untuk menganalisa tingkat resiko kredit. Salah satu teknik untuk menganalisa tingkat resiko kredit adalah dengan pendekatan data mining. Data mining menyediakan teknik untuk menemukan informasi yang bermakna dari sejumlah data besar dengan cara klasifikasi. Data bank marketing termasuk jenis data imbalance sehingga apabila dilakukan klasifikasi hasilnya kurang optimal. Algoritma klasifikasi yang dapat digunakan untuk jenis data imbalance dapat menggunakan naïve bayes. Naïve bayes memiliki kinerja baik dalam hal klasifikasi, namun demikian diperlukan optimasi agar mendapatkan hasil klasifikasi yang lebih optimal. Teknik optimasi dalam menangani data imbalance telah banyak dikembangkan dengan beberapa pendekatan. Bagging dan Genetic Algorithm dapat digunakan dalam mengatasi data imbalance. Penelitian ini bertujuan untuk membandingkan tingkat akurasi algoritma naïve bayes setelah dilakukan optimasi dengan menggunakan bagging dan genetic algorithm. Hasil penelitan menunjukkan bahwa kombinasi bagging dengan genetic algorithm dapat meningkatkan performa naive bayes sebesar 4,57%.&nbsp

Direct marketing is an effort made by the Bank to increase sales of its products and services, but the Bank sometimes has to contact a customer or prospective customer more than once to ascertain whether the customer or prospective customer is willing to subscribe to a product or service. To overcome this ineffective process several data mining methods are proposed. This study compares several data mining methods such as Naïve Bayes, K-NN, Random Forest, SVM, J48, AdaBoost J48 which prior to classification the SMOTE pre-processing technique was done in order to eliminate the class imbalance problem in the Bank Marketing dataset instance. The SMOTE + Random Forest method in this study produced the highest accuracy value of 92.61%.

Malaria is a disease caused by the Plasmodium parasite that transmitted by female Anopheles mosquitoes. Malaria can become a dangerous disease if late have the medical treatment. The late medical treatment happened because of misdiagnosis and lack of medical staff, especially in the countryside. This problem can cause severe malaria that has complications. This study creates a system prediction to classify the severe malaria disease using Classification and Regression Tree (CART) method and the probability of malaria complication using Naïve Bayes method. The first step of this study is classifying the patients that have symptom are infected severe malaria or not based on the model that has been built. The next step, if the patient classified severe malaria then the data predicted if there any probability of complication by the malaria. There are 8 possibilities of complication malaria which are convulsion, hypoglycemia, hyperpyrexia, and the combinations of these four. The first step will evaluate by using F-score, precision and recall while the second step will evaluate by using accuracy. The highest result F-score, precision and recall are 0.551, 0.471 and 0.717. The highest accuracy 81.2% which predicted the complication is Hypoglycemia.

In the medical field, there are many records of disease sufferers, one of which is data on breast cancer. An extraction process to fine information in previously unknown data is known as data mining. Data mining uses pattern recognition techniques such as statistics and mathematics to find patterns from old data or cases. One of the main roles of data mining is classification. In the classification dataset, there is one objective attribute or it can be called the label attribute. This attribute will be searched from new data on the basis of other attributes in the past. The number of attributes can affect the performance of an algorithm. This results in if the classification process is inaccurate, the researcher needs to double-check at each previous stage to look for errors. The best algorithm for one data type is not necessarily good for another data type. For this reason, the K-Nearest Neighbor and Naïve Bayes algorithms will be used as a solution to this problem. The research method used was to prepare data from the breast cancer dataset, conduct training and test the data, then perform a comparative analysis. The research target is to produce the best algorithm in classifying breast cancer, so that patients with existing parameters can be predicted which ones are malignant and benign breast cancer. This pattern can be used as a diagnostic measure so that it can be detected earlier and is expected to reduce the mortality rate from breast cancer. By making comparisons, this method produces 95.79% for K-Nearest Neighbor and 93.39% for Naïve Bayes

Berita adalah salah satu sarana informasi bagi masyarakat umum, dengan media online sebagai salah satu sarana untuk mengaksesnya. Di Indonesia, media online memiliki presentase paling besar dalam penyebarluasan berita. Dibutuhkan mekanisme yang dapat mengklasifikasikan setiap topik berita secara akurat. Klasifikasi adalah proses yang krusial, karena memerlukan tahap preprocessing untuk mengubah data tidak terstruktur menjadi informasi yang bermakna. Preprocessing diawali dengan case folding , tokenizing , stemming , dan filtering , diahiri dengan klasifikasi. Penelitian ini menggunakan Enhanced Confix Stripping Stemmer untuk memisahkan kata dasar dari partikel awalan dan imbuhan, yang sebelumnya sulit dilakukan. Algoritma Naive Bayes Classifier kemudian diterapkan untuk proses klasifikasi. Dataset dari portal www.jawapos.com yang digunakan berjumlah 600 dokumen berita. Data tersebut digunakan sebagai data training , terbagi merata ke dalam kategori Olahraga, Teknologi, Ekonomi, dan Lain-lain. Dari 40 data testing yang diuji, akurasi tiap kategori diperoleh 90%, 90%, 100%, dan 100%, yang menghasilkan rata-rata akurasi keseluruhan kategori sebesar 95%.

The review of the users of one application is of great help to development in improving the quality of the application and may be the means for assessments that users feel satisfied or not. The study conducted a sentiment analysis of the Ruangguru application by testing the three classification models such as N aive B ayes , R andom F orest and Support V ectors M achine . The study has yielded results that from Random Forest classification model 97,16% by using Cross Validation and an AUC score of 0.996. Then accuracy with the model of Support V ector Machine classification support results in accuracy rate of 96.01% to an AUC value of 0.543 and accuracy in the testing of Naive Bayes classification model was 94,16% of AUC score 0,999. This study shows that an increase in accuracy from previous studies of 7.16% with Random Forest’s final cut as a Random Forest classification model with the best performance.

Aplikasi zoom cloud meetings yang mulai booming digunakan sekarang ini karena adanya pandemi virus corona, sehingga membuat semua kegiatan dilakukan secara virtual. Zoom cloud meetings merupakan aplikasi yang memiliki berbagai fitur termasuk video & audio conference. Pada penelitian ini penulis menggunakan metode Naïve Bayes dan Support Vector Machine dalam menganalisa label sentimen positif atau negatif pada ulasan para pengguna aplikasi zoom di Google Play Store. Jumlah dataset setelah prepocessing menjadi 1.007 record. Data hampir seimbang dengan label positif sebanyak 546 dan label negatif 461 ulasan. Evaluasi model menggunakan 10 fold cross validation diperoleh nilai akurasi dan nilai AUC dari masing-masing algoritma yaitu untuk NB nilai akurasi = 74,37% dan nilai AUC = 0,659. Sedangkan untuk algoritma SVM nilai akurasi = 81,22% dan nilai AUC = 0,886. Dalam penelitian ini dapat diketahui bahwa tingkat akurasi yang didapatkan algoritma Support Vector Machine (SVM) lebih unggul 6,85% dibandingkan algoritma Naïve Bayes (NB). Kata Kunci— Zoom Cloud Meetings, Google Play Store, Virus Corona, Naïve Bayes, Support Vector Machine. Abstract— Zoom cloud meetings application that began to boom is used today because of the corona virus pandemic, so that all activities are carried out virtually. Zoom cloud meetings is an application that has various features including video & audio conferencing. In this study the authors used the Naïve Bayes method and Support Vector Machine in analyzing positive or negative sentiment labels on the zoom users' reviews on the Google Play Store. The number of datasets after prepocessing is 1,007 records. The data is almost balanced with 546 positive labels and 461 negative labels. Evaluation of the model using 10 fold cross validation obtained accuracy values and AUC values from each algorithm, namely for NB, the accuracy value = 74.37% and the AUC value = 0.659. As for the SVM algorithm the accuracy value = 81.22% and the AUC value = 0.886. In this study it can be seen that the accuracy obtained by the Support Vector Machine (SVM) algorithm is 6.85% superior to the Naïve Bayes (NB) algorithm.

Academic achievement is determined by two factors, namely internal factors originating from within the individual in this case students and external factors that come from outside the individual or things that are influenced by the environment. There are many ways to find an academic achievement, one of which uses data mining which aims to predict or classify data using a classification algorithm. This study aims to 1) find out how to apply the Naive Bayes algorithm to student achievement, and 2) see the accuracy of the Naive Bayes algorithm to student achievement. This type of research is secondary data in the form of student data obtained from the information technology center and the Ar-Raniry UIN database. This research uses Naive Bayes algorithm and random forest algorithm. The results obtained from this study indicate the highest correlation value in the initial IP variable of r = 0.783 and the leave variable has a very weak correlation level of r = 0.054. The accuracy value of Naive Bayes algorithm after cleaning is 78.0% and Random Forest algorithm variable is 76.7%.

The COVID-19 pandemic is the first and foremost health crisis in the world. Coronavirus is a collection of viruses from the subfamily Orthocronavirinae in the Coronaviridae family and the order of Nidovirales. This group of viruses that can cause disease in birds and mammals, including humans. In humans, coronaviruses cause generally mild respiratory infections, such as colds, although some forms of disease such as; SARS, MERS, and COVID-19 are more deadly. Anticipating and reducing the number of corona virus sufferers in Indonesia has been carried out in all regions. Among them by providing policies to limit activities out of the house, school activities laid off, work from home (work from home), even worship activities were laid off. This has become a government policy based on considerations that have been analyzed to the maximum, of course. Therefore this research was carried out as an anticipation step towards the Covid-19 pandemic by predicting the spread of Covid-19, especially in Indonesia. The research method applied in this research is problem analysis and literature study, collecting data and implementation. The application of the naive bayes method is expected to be able to predict the spread rate of COVID-19 in Indonesia. The results of the Naive Bayes method classification show that 16 data from 33 data were tested in Covid-19 cases per province with an accuracy of 48.4848%, where of the 33 data tested in the Covid-19 case per province tested there were 16 data that were successfully classified correctly.

The decision to move Indonesia's capital city to East Kalimantan received mixed responses on social media. When the poverty rate is still high and the country's finances are difficult to be a factor in disapproval of the relocation of the national capital. Twitter as one of the popular social media, is used by the public to express these opinions. How is the tendency of community responses related to the move of the National Capital and how to do public opinion sentiment analysis related to the move of the National Capital with Feature Selection Naive Bayes Algorithm and Support Vector Machine to get the highest accuracy value is the goal in this study. Sentiment analysis data will take from public opinion using Indonesian from Twitter social media tweets in a crawling manner. Search words used are #IbuKotaBaru and #PindahIbuKota. The stages of the research consisted of collecting data through social media Twitter, polarity, preprocessing consisting of the process of transform case, cleansing, tokenizing, filtering and stemming. The use of feature selection to increase the accuracy value will then enter the ratio that has been determined to be used by data testing and training. The next step is the comparison between the Support Vector Machine and Naive Bayes methods to determine which method is more accurate. In the data period above it was found 24.26% positive sentiment 75.74% negative sentiment related to the move of a new capital city. Accuracy results using Rapid Miner software, the best accuracy value of Naive Bayes with Feature Selection is at a ratio of 9:1 with an accuracy of 88.24% while the best accuracy results Support Vector Machine with Feature Selection is at a ratio of 5:5 with an accuracy of 78.77%., Keputusan pemindahan ibu kota negara indonesia ke Kalimantan Timur mendapat tanggapan beragam pada media sosial. Disaat tingkat kemiskinan masih tinggi dan keuangan negara sedang sulit menjadi faktor ketidak setujuan pemindahan ibu kota negara. Pemerataan pembangunan dan kondisi dunia usaha yang semakin bergairah menjadi faktor yang mendukung pemindahan ibu kota negara. Twitter sebagai salah satu media sosial yang popular, digunakan masyarakat untuk mengungkapkan opini-opini tersebut. Bagaimana kecenderungan tanggapan masyarakat terkait pemindahan ibu kota negara serta bagaimana melakukan analisis sentimen opini masyarakat terkait pemindahan ibu kota negara dengan Feature Selection Algoritma Naive Bayes dan Support Vector Machine untuk mendapatkan nilai akurasi paling tinggi menjadi tujuan dalam penelitian ini. Data analisis sentimen akan mengambil dari opini masyarakat yang menggunakan bahasa Indonesia dari tweet media sosial Twitter secara crawling. Pencarian kata yang digunakan adalah #IbuKotaBaru dan #PindahIbuKota. Jumlah data yang diambil pada periode 23-April-2020 s.d 2-Mei-2020 mendapatkan hasil sebanyak 849 data tweet. Tahapan penelitian terdiri dari pengumpulan data melalui media sosial Twitter, polarity, preprocessing terdiri dari proses transform case, cleansing, tokenizing, filtering dan stemming. Penggunaan feature selection untuk meningkatkan nilai akurasi yang selanjutnya akan memasukan rasio yang telah ditentukan untuk digunakan oleh data testing dan training. Tahap selanjutnya, yaitu perbandingan antara algoritma Support Vector Machine dan Naive Bayes untuk menentukan algoritma mana yang lebih akurat. Dalam periode data diatas didapatkan 24,26% sentimen positif dan 75,74% sentimen negative terkait pemindahan ibu kota baru. Hasil akurasi dengan memakai perangkat lunak Rapid Miner nilai akurasi terbaik algoritma Naive Bayes dengan Feature Selection ada pada rasio 9:1 dengan hasil akurasi 88.24% sedangkan hasil akurasi terbaik algoritma Support Vector Machine dengan Feature Selection ada pada rasio 5:5 dengan hasil akurasi 78.77%.

Context-Aware Security demands a security system such as a Smart Door Lock to be flexible in determining security levels. The context can be in various forms; a person’s activity in the house is one of them and is proposed in this research. Several learning methods, such as Naïve Bayes, have been used previously to provide context-aware security systems, using related attributes. However conventional learning methods cannot be implemented directly to a Context-Aware system if the attribute of the learning process is low level. In the proposed system, attributes are in forms of movement data obtained from a PIR Sensor Network. Movement data is considered low level because it is not related directly to the desired context, which is activity. To solve the problem, the research proposes a hierarchical learning method, namely Hierarchical Hidden Markov Model (HHMM). HHMM will first transform the movement data into activity data through the first hierarchy, hence obtaining high level attributes through Activity Recognition. The second hierarchy will determine the security level through the activity pattern. To prove the success rate of the proposed method a comparison is made between HHMM, Naïve Bayes, and HMM. Through experiments created in a limited area with real sensed activity, the results show that HHMM provides a higher F1-Measure than Naïve Bayes and HMM in determining the desired context in the proposed system. Besides that, the accuracies obtained respectively are 88% compared to 75% and 82%.

Start-ups have a very important role in economic growth, the existence of a start-up can open up many new jobs. However, not all start-ups that are developing can become successful start-ups. This is because start-ups have a high failure rate, data shows that 75% of start-ups fail in their development. Therefore, it is important to classify the successful and failed start-ups, so that later it can be used to see the factors that most influence start-up success, and can also predict the success of a start-up. Among the many classifications in data mining, the Decision Tree, kNN, and Naïve Bayes algorithms are the algorithms that the authors chose to classify the 923 start-up data records that were previously obtained. The test results using cross-validation and T-test show that the Decision Tree Algorithm is the most appropriate algorithm for classifying in this case study. This is evidenced by the accuracy value obtained from the Decision Tree algorithm, which is greater than other algorithms, which is 79.29%, while the kNN algorithm has an accuracy value of 66.69%, and Naive Bayes is 64.21%.

Sentiment analysis is a field of study that analyzes one's opinions, sentiments, evaluations, attitudes and emotions that are conveyed in written text. There are several factors that cause low accuracy results from sentiment analysis. These factors such as less optimal stemming process, word negation process that does not produce maximum results, writing errors in the dataset, and others. These problems can be overcome by optimizing the process of normalizing words, negation, stemming, and adding methods of semantic expansion. The purpose of adding the Semantic Expansion method and improvement in the process is to increase the accuracy value of the Sentiment Analysis process. This study aims to create a sentiment analysis model from public comments on a public figure (Ridwan Kamil) using the Naïve Bayes Classifier algorithm. Based on the test results in the sentiment analysis model using the Naïve Bayes Classifier method with the addition of the semantic expansion method it is proven that it can improve accuracy. The accuracy obtained using the semantic expansion method is 72%. While the value of accuracy without semantic expansion is 70%., Analisis sentimen merupakan sebuah bidang studi yang menganalisis pendapat, sentimen, evaluasi seseorang, sikap dan emosi seseorang yang disampaikan dalam bentuk teks tertulis. Terdapat beberapa faktor yang menyebabkan rendahnya hasil akurasi dari analisis sentimen. Faktor-faktor tersebut seperti proses stemming yang kurang optimal, proses negasi kata yang tidak menghasilkan hasil yang maksimal, kesalahan penulisan pada dataset, dan lainnya. Permasalahan tersebut dapat diatasi dengan melakukan optimalisasi pada proses normalisasi kata, negasi, stemming, dan penambahan metode semantic expansion. Tujuan dari penambahan metode semantic expansion dan perbaikan pada proses tersebut adalah untuk meningkatkan nilai akurasi dari proses Analisis Sentimen. Penelitian ini bertujuan membuat model analisis sentimen dari komentar masyarakat terhadap seorang tokoh (Ridwan Kamil) menggunakan algoritma Naïve Bayes Classifier. Berdasarkan hasil pengujian yang dilakukan penulis dalam melakukan analisis sentimen menggunakan metode Naïve Bayes Classifier, penambahan metode semantic expansion terbukti dapat meningkatkan akurasi. Akurasi yang didapatkan dengan menggunakan metode semantic expansion adalah sebesar 72% Sedangkan nilai akurasi tanpa semantic expansion adalah 70%.

Twitter merupakan salah satu sosial media yang banyak digunakan oleh masyarakat dalam kehidupan sehari-hari. Salah satunya adalah twitter digunakan sebagai tempat untuk menyampaikan setiap pendapat atau opini terhadap suatu hal seperti pendapat atau opini terhadap tokoh publik. Dalam penelitian ini akan dilakukan analisa sentimen terhadap tokoh publik yang diungkapkan masyarakat melalui jejaring sosial twitter. Ada beberapa tahap dalam melakukan sentiment analis diantaranya adalah pengumpulan data menggunakan API Twitter, memberikan label kepada setiap twit secara manual, Pre Processing Data dan POS Tagging. Untuk mendapatkan hasil esktraksinya, penelitian ini menggunakan metode Naïve Bayes Classifier dan Support Vector Mechine agar hasil tersebut dapat dibandingkan keakurasiannya. Hasil dari penilitian ini didapat bahwa algoritma Support Vector Machine memiliki tingkat keakurasian sebesar 73.96% sedangkan untuk algoritma Naïve Bayes Classifier memiliki tingkat keakurasian sebesar 71.94% dengan menggunakan dataset yang didata.

Time deposits are a product of a financial institution, which is currently increasing. The main target of this time deposit marketing is the old customers of the Bank. To increase the effectiveness of marketing customers are grouped into potential and non-potential customers. This means that potential customers have a greater chance to open a time deposit account. Customer data is taken from the UCI repository, originating from Banks in Portugal. Data is processed with rapidminer software using the Decision Tree method with Particle Swarm Optimization, Naïve Bayes with Particle Swarm Optimization and finally processed using Neural Network with Particle Swarm Optimization. Data processing results were compared and showed that the Naïve Bayes Algorithm with Particle Swarm Optimization had the highest accuracy of 97.04%. Therefore an application designed based on Naive Bayes with Particle Swarm Optimization. From the original attribute consisting of 20, only 9 attributes can be used so that the level of accuracy is high. Attributes used have values ​​more than 0.500, while those that have these values ​​are omitted. The design was created using the Unified Modeling Language (UML) and Visual Basic 6.0 to create an User Interface.

Kelulusan mahasiswa merupakan salah satu hal yang harus diperhatikan karena termasuk ke dalam Standar Penjaminan Mutu Internal suatu perguruan tinggi. Program Studi Teknik Informatika merupakan salah satu prodi yang ada di Universitas Suryakancana. Untuk kelulusan terdapat standar yang akan dicapai oleh prodi yaitu waktu studi yaitu empat tahun dan IPK minimal 3,00. Untuk dapat mencapai mutu lulusan tersebut dibutuhkan suatu prediksi tingkat kelulusan dengan standar yang telah ditetapkan untuk mahasiswa yang masih menjalankan studi sehingga dapat dilakukan langkah antisipasi dari awal sehingga dapat menanggulangi terjadinya permasalahan dalam bidang akademik. Untuk memprediksi tingkat kelulusan dan IPK standar tersebut digunakan metode data mining dengan fungsi klasifikasi. Metodologi penerapan data mining ini menggunakan tahapan Discovery Knowledge of Databases (KDD) dimulai dari tahap selecting, preprocessing, transformation, data mining dan evaluation/interpretation. Teknik yang akan digunakan untuk model data mining klasifikasi ini terdiri dari empat algoritma yaitu C4.5, Support vector machine (SVM), k-nearest neigbor (kNN,) dan Naïve Bayes. Metoda klasifikasi terdiri dari variabel-variabel prediktor dan satu variabel target. Variabel-variabel prediktor terdiri dari jenis kelamin dan indeks prestasi dari semester 3 hingga 6. Perangkat lunak yang digunakan untuk mengolah data yaitu software Rapid Miner. Hasil akhir dari keempat algoritma tersebut diperoleh bahwa algoritma Naïve Bayes merupakan algoritma terbaik untuk memprediksi kelulusan mahasiswa yang tepat waktu dan IPK ≥ 3 dengan nilai accuracy (76,79%), error (23,17%) , dan AUC (0,850). Abstract - Graduate students is one factor that must be considered because it is included in the Quality Assurance Standards. The Informatic Engineering Department is one of the department at Suryakancana University. For the graduate standard that will be approved by the department, time period graduation is four years and a minimum GPA of 3.00. To achieve the required level of success, the predetermined standard level must be set for students to be anticipated from the start so they can overcome problems in the academic field. To predict the graduation rate and GPA standard the data mining method is used with the classification function. This data mining implementation methodology uses the stages of Discovery Knowledge of Databases (KDD) starting from selecting, preprocessing, transformation, data mining and evaluation / interpretation. The technique that will be used for this data mining model consists of four algorithms, such as C4.5, Support vector machine (SVM), the nearest k-neigbor (kNN,) and Naïve Bayes. The classification method consists of predictor variables and one target variable. Predictor variables consist of gender and achievement index from semester 3 to 6. The software used to process data is RapidMiner software. The final results of the following four algorithms generated from the Naïve Bayes algorithm are the best algorithms for predicting timely student graduation and GPA ≥ 3 with accuracy (76.79%), errors (23.17%), and AUC (0.850).

Various attempts are needed to control the increment of COVID-19 cases in Indonesia, especially Java Island. One of the effective attempt to do this is through the preventive act by providing news about a region. Indonesia, through Satgas Penanganan COVID-19, has built a risk zone of district/city as a warning system for the public and the substance of policy making for government in region level. The risk zone is built by three kinds of indicator using a conventional technique named score weighting. By considering the importance of the risk zone for policy making in the government, this study aims to build a risk zone classification model for districts / cities in Java using several data mining classification techniques and determine the best classification model based on evaluation results. This study uses several classification technique on the purpose of comparation. These techniques are naive Bayes, decision tree, k-nearest-neighbor, and neural network. Before entering the modeling stage, data is being adjustedat the preprocessing stage where missing value and imbalanced data problems are identifies. These problems is being overcome by doing data imputation and oversampling techniques. The result of this study indicates that k-nearest-neighbor is the best model compared to other three models. This result is based on the evaluation measures of the four models where the k-NN model has the highest accuracy value, the macro average value for sensitivity, specivicity, and F1-Measure compared to other models., Penambahan kasus COVID-19 yang besar di Indonesia, khususnya Pulau Jawa, membutuhkan berbagai upaya untuk mengendalikannya. Salah satu upaya efektif yang dapat dilakukan adalah tindakan preventif dengan memberi informasi mengenai kondisi suatu wilayah. Sebagai peringatan kepada masyarakat dan sebagai upaya pengambilan kebijakan daerah, Indonesia mengeluarkan zona risiko sampai pada tingkat kabupaten/kota melalui Satgas Penanganan COVID-19. Pembentukan level zona risiko tersebut menggunakan teknik konvensional yaitu pembobotan skor menggunakan informasi dari tiga jenis indikator. Dengan mempertimbangkan bahwa zona risiko merupakan hal yang penting dalam penentuan kebijakan terkait COVID-19, penelitian ini bertujuan untuk membangun model klasifikasi zona risiko kabupaten/kota di Pulau Jawa menggunakan beberapa teknik klasifikasi data mining dan menentukan model klasifikasi terbaik berdasarkan hasil evaluasi. Teknik klasifikasi yang digunakan sebagai perbandingan dalam penelitian ini adalah naive Bayes, decision tree, k-nearest-neighbor, dan neural network. Sebelum dilakukan pemodelan, data disesuaikan terlebih dahulu pada tahap preprocessing di mana pada tahap tersebut teridentifikasi terdapat permasalahan missing value dan imbalanced data. Permasalahan tersebut diatasi dengan imputasi data dan teknik oversampling. Hasil penelitian menunjukkan bahwa model k-nearest-neighbor merupakan model terbaik dibandingkan tiga model lainnya. Hasil tersebut didasarkan pada ukuran evaluasi keempat model di mana model k-NN memiliki nilai acccuracy, nilai rata-rata makro untuk sensitivitas, spesifisitas, dan ukuran F1 paling tinggi dibandingkan model lainnya.

This research aims to build an information system that can support the company in decision-making, especially about the promotion of positions at PT. Global Beautiful Fashion. This is motivated by the difficulty of determining whether or not an employee has been promoted to office, due to an uncomputed system and stacked employee data documents. In this study, the data used is data on the promotion of employee positions at PT. Global Beautiful Clothing and the method used is the Naïve Bayes Classifier algorithm method. And to find out how well the Naïve Bayes Classifier algorithm was used in this study, RapidMiner software was used to conduct testing. RapidMiner's testing yielded an accuracy score of 91.67% and a ROC value of 0.979 which means the Naïve Bayes Classifier algorithm was very well used in this study. After testing using RapidMiner software and obtaining test results, it is then implemented into a system using PHP and MySQL designed to predict promotion. The prediction results obtained from the system are following the calculation results obtained from RapidMiner software and manual calculations. Based on the research that has been done that the decision support system built can be applied to PT. Busana Indah Global (BIG) to make it easier to determine the feasibility of promotion for its employees., Penelitian ini bertujuan untuk membangun sebuah sistem informasi yang dapat menunjang perusahaan dalam pengambilan keputusan khususnya tentang promosi jabatan pada PT. Busana Indah Global. Hal ini dilatar belakangi oleh sulitnya menentukan layak tidaknya seorang karyawan yang telah dipromosikan untuk naik jabatan, dikarenakan sistem yang belum terkomputerisasi dan dokumen data karyawan yang bertumpuk. Pada penelitian ini, data yang digunakan adalah data kenaikan jabatan karyawan di PT. Busana Indah Global dan metode yang digunakan adalah metode algoritma Naïve Bayes Classifier. Dan untuk mengetahui seberapa baik algoritma Naïve Bayes Classifier digunakan pada penelitian ini, maka digunakan software RapidMiner untuk melakukan pengujian. Dari pengujian di RapidMiner menghasilkan nilai akurasi sebesar 91,67% dan nilai ROC sebesar 0,979 yang artinya algoritma Naïve Bayes Classifier sangat baik digunakan pada penelitian ini. Setelah melakukan pengujian menggunakan software RapidMiner dan mendapatkan hasil pengujian, kemudian diimplementasikan ke dalam sebuah sistem menggunakan PHP dan MySQL yang dirancang untuk melakukan prediksi kenaikan jabatan. Hasil prediksi yang didapatkan dari sistem sudah sesuai dengan hasil perhitungan yang didapatkan dari software RapidMiner dan perhitungan manual. Berdasarkan penelitian yang telah dilakukan bahwa sistem pendukung keputusan yang dibangun ini dapat diaplikasikan pada PT. Busana Indah Global (BIG) sehingga mampu mempermudah dalam menentukan kelayakan kenaikan jabatan bagi karyawannya.

This paper proposes fire alarm system by implementing Naive Bayes Method for increasing smoke classifier accuracy on Internet of Things (IoT) environment. Fire disasters in the building of houses are a serious threat to the occupants of the house that have a hazard to the safety factor as well as causing material and non-material damages. In an effort to prevent the occurrence of fire disaster, fire alarm system that can serve as an early warning system are required. In this paper, fire alarm system that implementing Naive Bayes classification has been impelemented . Naive Bayes classification method is chosen because it has the modeling and good accuracy results in data training set. The system works by us ing sensor data that is processed and analyzed by applying N aive B ayes classification to generate prediction value of fire threat level along with smoke source. The smoke source was divided into five types of smoke intended for the classification process. Some experiments have been done for concept proving. The results show the use of N aive B ayes classification method on classification process has an accuracy rate range of 88% to 91%. This result could be acceptable for classification accuracy.