Sistemasi Jurnal Sistem Informasi最新文献

{"title":"Penerapan Algoritma K-Medoids Untuk Menentukan Segmentasi Pelanggan","authors":"Anggi Ayu Dwi Sulistyawati, M. Sadikin","doi":"10.32520/stmsi.v10i3.1332","DOIUrl":"https://doi.org/10.32520/stmsi.v10i3.1332","url":null,"abstract":"Abstrak Strategi pemasaran berorientasi pelanggan memiliki peranan penting dalam mengelola hubungan baik dengan pelanggan. Agar strategi pemasaran tepat sasaran, segmentasi pelanggan dapat digunakan untuk mengelompokkan pelanggan berdasarkan karakteristik yang sama. Dalam penyusunan strategi pemasaran dapat memanfaatkan TI di bidang komputasi, salah satunya adalah data mining . Pemanfaatan teknologi komputasi untuk pengolahan data yang belum maksimal mengakibatkan penumpukan data yang miskin informasi. Pada penelitian ini dilakukan penerapan teknik clustering dengan menggunakan algoritma K-Medoids pada dataset transaksi penjualan untuk menentukan segmentasi pelanggan. Penyusunan strategi pemasaran ditentukan berdasarkan tipe dan karakteristik pelanggan pada setiap cluster atau segmen pelanggan yang terbentuk. Uji validitas cluster menggunakan Silhouette Index dan Davies Boulbin Index dilakukan untuk menentukan jumlah cluster yang paling optimal. Hasil penelitian ini menunjukan bahwa jumlah cluster optimal adalah 3 (tiga) cluster dengan nilai maksimum Silhouette Index adalah 0,375 dan nilai minimum Davies Doulbin Index adalah 1,030. Segmen pelanggan hasil penelitian adalah lost customer , core customer , dan new customer .  Kata kunci: algoritma k-medoids, clustering , data mining, segmentasi pelanggan, strategi pemasaran Abstract Customer-oriented marketing strategies play an important role in managing good relationships with customers. To keep marketing strategies on target, customer segmentation can be used to group customers based on the same characteristics. In the preparation of marketing strategies can utilize IT in the field of computing, one of which is data mining. The utilization of computing technology for data processing that has not been maximized resulted in a poor accumulation of information data. In this study, the application of clustering techniques using the K-Medoids algorithm on sales transaction dataset to determine customer segmentation. The preparation of a marketing strategy is determined based on the characteristics and types of customers in each cluster or segment of customers formed. cluster validity tests using the Silhouette Index and Davies-Boulbin Index are performed to determine the most optimal number of clusters. The results of this study showed that the optimal number of clusters is 3 (three) clusters with a maximum silhouette index value of 0.375 and the minimum value of the davies-bouldin index is 1.030. The customer segments of the research results are lost customers, core customers, and new customers.  Keywords: k-medoids algorithm, clustering, data mining, customer segmentation, marketing strategy","PeriodicalId":32367,"journal":{"name":"Sistemasi Jurnal Sistem Informasi","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75524340","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analisis Penerimaan Google Classroom Menggunakan Pendekatan Technology Acceptance Model (TAM) Dan End-User Computing Satisfaction (EUCS) (Studi Kasus: Universitas Informatika Dan Bisnis Indonesia)","authors":"Z. Niqotaini","doi":"10.32520/stmsi.v10i3.1376","DOIUrl":"https://doi.org/10.32520/stmsi.v10i3.1376","url":null,"abstract":"Abstrak Pandemi virus corona (COVID-19) memberikan dampak besar terhadap berbagai aktivitas manusia di seluruh dunia khususnya negara Indonesia, salah satunya aktivitas pendidikan dan kegiatan pembelajaran di kampus. Kebijakan dari pemerintah tentang WFH ( work from home ) menjadikan proses kegiatan pembelajaran secara tatap muka di kampus dihentikan sementara sejak bulan Maret 2020 hingga waktu yang belum dapat ditentukan. Universitas Informatika dan Bisnis Indonesia sebagai salah satu institusi pendidikan swasta di Jawa Barat, dituntut untuk mengikuti perubahan metode pembelajaran yaitu pembelajaran jarak jauh ( online ) yang sebelumnya menggunakan tatap muka secara langsung. Salah satu platform yang banyak digunakan adalah google classroom . Google classroom merupakan aplikasi yang memungkinkan terbentuknya kelas di dunia maya, sebagai salah satu platform yang banyak digunakan tentunya perlu diperlukan evaluasi kepuasaan pengguna terutama mahasiswa agar terdapat perbaikan kedepannya. Penelitian ini dikaji dengan menggunakan model Technology Acceptance Model (TAM) dengan mempertimbangkan faktor Persepsi Kegunaan (Perceived Usefulness) , Persepsi Kemudahan Penggunaan (Perceived Ease Of Use) dan Sikap Terhadap Perilaku ( Attitude Toward Using). End-User Computing Satisfaction (EUCS) dengan mempertimbangkan Isi (Content) , Akurasi (Accuracy) , Tampilan (Format) , Kemudahan (Ease) dan Ketepatan Waktu (Timeliness) . Subyek penelitian yang digunakan adalah mahasiswa di lingkungan Universitas Informatika dan Bisnis Indonesia (Unibi). Hipotesis yang menghasilkan hubungan antar konstruk di dalam TAM dan EUCS diukur dengan Structural Equation Model (SEM) dan software AMOS 26. Hasil penelitian ini menunjukkan bahwa model TAM dan EUCS dapat menjelaskan faktor – faktor yang mempengaruhi penerimaan google classroom pada Unibi dimana Perceived Usefullness (PU) dipengaruhi oleh Perceived Ease of Use (PEOU) 52,2%. Attitude Toward Using ( AT ) dipengaruhi oleh Perceived Usefullness (PU) 34,4%, Content (CT) 25,4%, Accuracy (AC) 11,9%, dan Format (FT) 18,4%. Kata kunci : e-learning, google classroom, technology acceptance model (TAM) , end user computing satisfaction (EUCS) Abstract Coronavirus pandemic (COVID-19) has a big impact on various human activities around the world, especially indonesia, one of which is educational activities and learning activities on campus. The government's policy on WFH (work from home) has temporarily suspended the process of face-to-face learning on campus from March 2020 until an indefinite period of time. Univers ity Informatics and B usiness Indonesia as one of the private educational institutions in West Java, is required to follow the changes in learning methods, namely distance learning (online) that previously used face-to-face. One of the widely used platforms is google classroom. Google classroom is an application that allows the formation of classes in cyberspace, as one of the widely used platforms of course need to eval","PeriodicalId":32367,"journal":{"name":"Sistemasi Jurnal Sistem Informasi","volume":"174 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76920732","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Komparasi Algoritma C4.5 Dan Naïve Bayes Dalam Penentuan Status Kelayakan Donor Darah","authors":"Kartika Handayani, Lisnawanty Lisnawanty, Abdul Latif, Muhammad Rifqi Firdaus, F. Hasan","doi":"10.32520/stmsi.v10i3.1440","DOIUrl":"https://doi.org/10.32520/stmsi.v10i3.1440","url":null,"abstract":"Donor darah merupakan kegiatan kemanusiaan dimana seseorang dengan sukarela  Abstrak Donor darah merupakan kegiatan kemanusiaan dimana seseorang dengan sukarela menyumbangkan darahnya untuk disimpan di bank darah yang kemudian digunakan untuk transfusi darah. UDD (Unit Donor Darah) PMI Kota Pontianak merupakan tempat pelayanan donor darah dari masyarakat Kota Pontianak. Dalam prakteknya, tidak semua masyarakat yang ingin mendonorkan darah dapat berhasil mendonorkan darahnya. Dalam memprediksi layak atau tidaknya masyarakat untuk mendonorkan darahnya dapat dilakukkan dengan klasifikasi data mining untuk mengetahui faktor yang paling mempengaruhi prediksi donor darah. Penelitian ini menggunakan metode klasifikasi  algoritma C4.5 dan Naive Bayes kemudian dilakukan perbandingan dua metode tersebut menggunakan confusion matrix , AUC dan uji beda t-test dengan analisa software rapidminer  berdasarkan umur, jenis kelamin, berat badan, tekanan darah, dan hemoglobin. Dari hasil penelitian ini, hemoglobin adalah variabel paling menentukan kelayakan donor darah kemudian tekanan darah. Algoritma terbaik dalam kasus ini adalah Naive Bayes dengan akurasi 93,26%, sedangkan tingkat akurasi C4.5 93,22%. Naive Bayes termasuk dalam predikat good classsification dengan AUC sebesar 0.833, sedangkan C4.5 termasuk dalam predikat fair classsification dengan AUC sebesar 0.758. Dari hasil uji beda t-test diperoleh hasil 0.841 yang menyatakan bahwa tidak ada perbedaan signifikan dalam penentuan  klasifikasi status kelayakan donor darah untuk kedua algoritma. Kata kunci: prediksi, donor darah, c4.5, naive bayes Abstract Blood donation is a humanitarian activity in which someone voluntarily donates blood to be stored in a blood bank which is then used for blood transfusions. UDD (Blood Donation Unit) PMI Pontianak City is a blood donor service area of the Pontianak City community. In practice, not all people who want to donate blood can successfully donate blood. In predicting the feasibility of whether or not the community to donate blood can be done with the classification of data mining to determine the factors that most influence the prediction of blood donors. This study uses the C4.5 algorithm and Naive Bayes classification method, then compares the two methods using a confusion matrix, AUC and t-test different test with rapidminer software analysis based on age, sex, weight, blood pressure, and hemoglobin. From the results of this study, hemoglobin is the most determining variable of eligibility for blood donation then blood pressure. The best algorithm in this case is Naive Bayes with an accuracy of 93.26%, while the accuracy rate of C4.5 is 93.22%. Naive Bayes is included in the category of good class certification with AUC of 0.833, while C4.5 is included in the category of fair class certification with AUC of 0.758. From the results of the t-test different test results obtained 0.841 which states that there is no significant difference in determining the classific","PeriodicalId":32367,"journal":{"name":"Sistemasi Jurnal Sistem Informasi","volume":"6 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84594187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analisis Sentimen Physical Distancing pada Twitter Menggunakan Text Mining dengan Algoritma Naive Bayes Classifier","authors":"Nila Hardi, Yuris Alkahfi, Popon Handayani, W. Gata, Muhammad Rifqi Firdaus","doi":"10.32520/STMSI.V10I1.1118","DOIUrl":"https://doi.org/10.32520/STMSI.V10I1.1118","url":null,"abstract":"Abstrak Physical distancing kini sedang ramai menjadi perbincangan publik sebagai salah satu cara pemerintah dalam menekan penyebaran virus covid-19 yang sedang melanda beberapa negara di belahan dunia. Tidak tersaringnya cuitan terkait physical distancing bisa memunculkan berbagai macam opini, tidak hanya opini yang positif tapi juga yang negatif. Maka dari itu, Twitter di anggap lebih diminati oleh masyarakat indonesia dikarenakan twitter dirasa lebih mudah untuk mengungkapkan opininya. Metode yang digunakan yaitu Naive Bayes Classifier (NBC). Data terkumpul dilakukan filter dari cuitan tersebut dengan menghapus data yang double maka setelah di filter data yang terambil yaitu sebanyak 547 tweets . Pada perhitungan analisis sentimen terhadap physical distancing di tengah pandemi covid-19 menggunakan metode NBC memperoleh hasil akurasi sebesar 50,26%. Tujuan dari penelitian ini, agar dapat mengkategorikan opini negatif atau positif, dari pembahasan physical distancing . Nantinya informasi terkait kebijakan Physical Distancing bisa sampai tepat informasinnya kepada masayarakat. Kata Kunci : naive bayes, physyical distancing, twitter Abstract Physical distancing is now busy becoming a public conversation as a way for the government to spread the Covid-19 virus which is currently hitting several countries around the world. There are public tweets related to physical distance that is free from various kinds of opinions, not only positive but also negative ones. Therefore, Indonesian people consider Twitter to be more desirable because it is easier for Indonesians to express their opinion. The method used is the Naive Bayes Classifier (NBC). The data collected was filtered from the tweets with double data, then after filtering the data were taken as many as 547 tweets. In calculating the sentiment analysis of physical distance in the middle of the Covid-19 pandemic using the NBC method, it gets an accurate result of 50.26%. The purpose of this study, to find and categorize negative or positive opinions, from the discussion of physical distancing. So that the implementation of the Physical Distance policy can get accurate information to the public. Keywords : naive bayes, physical distancing, twitter","PeriodicalId":32367,"journal":{"name":"Sistemasi Jurnal Sistem Informasi","volume":"23 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78975320","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Sistem Prediksi Jumlah Pasien Covid-19 Menggunakan Metode Trend Least Square Berbasis Web","authors":"J. Widjaya, R. DewiAgushinta, Sri Rahayu Puji Sari","doi":"10.32520/STMSI.V10I1.1036","DOIUrl":"https://doi.org/10.32520/STMSI.V10I1.1036","url":null,"abstract":"Abstrak Virus Corona telah menjadi masalah kesehatan yang marak terjadi sejak awal tahun 2020, bermula dari negara China, Wuhan. Indonesia telah menjadi salah satu negara di Asia dengan angka kematian ( Death Rate ) tertinggi di dunia. Banyaknya kasus yang masih belum terdeteksi dan terlaporkan membuat situasi di Indonesia menjadi lebih buruk. Jumlah pasien yang terus meningkat dan keterbatasan fasilitas, alat dan tenaga kesehatan menjadi kendala bagi Indonesia untuk menghadapi COVID-19. Berdasarkan permasalahan di atas, penulis tertarik membuat sistem prediksi jumlah pasien COVID-19 menggunakan metode Trend Least Square berbasis web . Proses prediksi dilakukan dengan menggunakan tool RStudio. Hasil prediksi akan diimplementasikan ke dalam website. Analisa hasil prediksi dilakukan dengan menghitung nilai Mean Absolute Percentage Error (MAPE). Sayangnya, nilai rata-rata persentase MAPE prediksi pasien COVID-19 di Indonesia sebesar 59,2 % menunjukkan prediksi dengan metode Trend Least Square tergolong buruk. Sistem prediksi ini dapat memprediksi pasien COVID-19 sesuai waktu yang tersedia dan terproses sebelumnya menggunakan RStudio. Uji coba website menggunakan metode Black Box memiliki hasil sukses untuk setiap skenario uji coba. Tujuan dari penelitian ini adalah membuat sistem prediksi jumlah pasien COVID-19 menggunakan metode Trend Least Square berbasis web. Sistem ini dapat memprediksi perkembangan jumah pasien yang terjangkit, sembuh, dan meninggal terkait COVID-19 khususnya di wilayah Indonesia, sehingga pemerintah daerah dapat menyiapkan sarana dan prasarana serta kebijakan yang tepat untuk menangani epidemi COVID-19. Kata Kunci: COVID-19, prediksi, trend least square, rstudio, data mining Abstract The Coronavirus has becomed a rife health problem since the beginning of 2020, starting in China, Wuhan. Indonesia has become one of the countries in Asia with the highest death rate in the world. The large number of cases that have not been detected and reported has made the situation in Indonesia even worse. The increasing number of patients and limited facilities, equipment, and health personnel are obstacles for Indonesia to deal with COVID-19. Based on the  problems, the authors are interested in making a prediction system for the number of COVID-19 patients using the web-based Trend Least Square method. The prediction process is carried out using the RStudio tool. The prediction results will be implemented on the website. Analysis of the prediction results is done by calculating the value of Mean Absolute Percentage Error (MAPE). Unfortunately, the average value of the predicted MAPE percentage for COVID-19 patients in Indonesia is 59.2%, indicating that the prediction using Trend Least Square method is poor. This prediction system can predict COVID-19 patients according to the available time and are processed in advance using RStudio. Testing the website using the Black Box method has successful results for each test scenario. The purpose o","PeriodicalId":32367,"journal":{"name":"Sistemasi Jurnal Sistem Informasi","volume":"45 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86580214","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Penilaian Risiko Data Sistem Informasi Manajemen Puskesmas dan Aset Menggunakan ISO 27005","authors":"Jonny Jonny, Awalludiyah Ambarwati, Cahyo Darujati","doi":"10.32520/STMSI.V10I1.995","DOIUrl":"https://doi.org/10.32520/STMSI.V10I1.995","url":null,"abstract":"AbstrakSistem Informasi Manajemen Puskesmas atau SIMPUS merupakan sistem informasi manajemen yang digunakan oleh staf Puskesmas Pasir Putih guna menyediakan layanan kesehatan kepada masyarakat. Keberadaan SIMPUS sangat mendukung kegiatan pelayanan kesehatan. Namun ada permasalahan pada sistem informasi puskesmas dalam pelayanan pasien, pada komputer terkena virus sehingga SIMPUS tidak bisa digunakan sementara. Penelitian ini dilakukan untuk penilaian risiko terhadap kemungkinan ancaman dan risiko yang muncul menggunakan ISO 27005. Hasil penelitian dari penilaian risiko rata-rata risiko sedang dan risiko tinggi masih kecil pada ancaman yang mungkin terjadi dan penanganan risiko dari 30 skenario ancaman yang mungkin terjadi yaitu, risk modification (RM) 20 skenario, risk Avoidance (RA) 3 skenario dan risk sharing (RS) 7 skenario. Rekomendasi untuk penanganan risiko pada Puskesmas Pasir Putih yaitu perlu adanya kebijakan dan aturan dari kepala puskesmas terhadap aset utama aplikasi SIMPUS untuk pengolahan, penghapusan dan output data SIMPUS. Dilakukan pelatihan terhadap pengelola dan pengguna aplikasi SIMPUS. Penambahan keamanan, pemeliharaan dan kontrol pada aset pendukung dan menambah kebutuhan yang diperlukan.Kata Kunci: ISO 27005, Puskesmas Pasir Putih, Penilaian Risiko AbstractSistem Informasi Manajemen Puskesmas or SIMPUS is a health center management information system that is used by Puskesmas Pasir Putih staff to provide health care services for citizens. SIMPUS have supported health care service. But, there is a problem in patient service when virus computer attack SIMPUS. This incident caused SIMPUS cannot be used temporarily. This research was conducted to assess the risk of possible threats and risks that arise using ISO 27005. The result shown that the average risk assessment of moderate risk and high risk were still small on the threats that might occur, and the risk management of 30 possible threat can be occurred such as risk modification (RM) 20 scenarios, risk Avoidance (RA) 3 scenarios and risk sharing (RS) 7 scenarios. There are several recommendations for risk management at Puskesmas Pasir Putih. Policies and rules need to be made by the head of Puskesmas to maintain the main assets of SIMPUS application for processing, deleting and outputing the SIMPUS data. Doing training for maintainers and simpus application users, increasing security, maintaining and controlling to support assets and increasing need. Keywords: ISO 27005, Puskesmas Pasir Putih, Risk Assessment","PeriodicalId":32367,"journal":{"name":"Sistemasi Jurnal Sistem Informasi","volume":"67 9","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72610762","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analisis Sentimen Publik dari Twitter Tentang Kebijakan Penanganan Covid-19 di Indonesia dengan Naive Bayes Classification","authors":"Ni Putu Gita Naraswati, Rani Nooraeni, Delvira Cindy Rosmilda, Dinda Desinta, Fadhilatul Khairi, Riska Damaiyanti","doi":"10.32520/STMSI.V10I1.1179","DOIUrl":"https://doi.org/10.32520/STMSI.V10I1.1179","url":null,"abstract":"Abstrak Beberapa bulan terakhir, penanganan COVID-19 menjadi salah satu permasalahan kompleks yang dihadapi oleh hampir seluruh negara di dunia. Menilik dari hal tersebut, pemerintah membentuk kebijakan guna mencegah semakin meluasnya penyebaran virus diantaranya Pembatasan Sosial Berskala Besar (PSBB), wajib masker, dan jam malam. Kebijakan tersebut mendapat tanggapan yang beragam, tidak terkecuali di media sosial seperti twitter. Berdaarkan hal tersebut, penelitian ini bertujuan untuk menganalisis sentimen publik dari cuitan Twitter mengenai penanganan COVID-19 di Indonesia. Adapun metode yang digunakan Naive Bayes Classification karena memiliki algoritma yang sederhana dengan akurasi yang tinggi. Hasil penelitian menunjukkan, masyarakat lebih banyak memberikan sentimen negatif terhadap kebijakan penanganan COVID-19 khususnya PSBB, wajib masker, dan jam malam. Pada sentimen positif, tiga kata dengan frekuensi kemunculan terbanyak yaitu demo, jakarta, dan kerja. Sedangkan pada sentimen negatif yaitu jakarta, demo, dan orang. Kemunculan kata “demo” dan “jakarta” pada kedua sentimen menunjukkan bahwa tweet masyarakat mengenai kebijakan penanganan COVID-19 tidak lepas dari peristiwa/kejadian saat pengumpulan data dilakukan. Selain itu, tingginya frekuensi kata “jakarta” pada sentimen negatif juga menunjukkan bahwa pelaksanaan kebijakan penanganan COVID-19 di Jakarta belum dilaksanakan secara optimal. Berdasarkan hasil evaluasi, diperoleh tingkat akurasi klasifikasi sebesar 87,34%, sensitivitas sebesar 93,43%, dan spesifisitas 71,76% yang berarti metode ini sudah cukup baik. Kata Kunci: COVID-19 , naive bayes classification , kebijakan, text mining , twitter Abstract In recent months, handling COVID-19 has become one of the complex problems faced by almost all countries in the world. In view of this, the government formed policies to prevent the spread of the virus, including Large-Scale Social Restrictions (PSBB), mandatory masks, and curfews. This policy received various responses, including on social media such as Twitter. Based on this, this study aims to analyze public sentiment from Twitter tweets regarding the handling of COVID-19 in Indonesia. The method used is the Naive Bayes Classification because it has a simple algorithm with high accuracy. The results showed that the public gave more negative sentiments towards the policy of handling COVID-19, especially PSBB, mandatory masks, and curfews. On the positive sentiment, the three words with the highest frequency were “demo”, “jakarta”, and “work”. Meanwhile, the negative sentiment is “jakarta”, “demo”, and “orang”. The appearance of the words \"demo\" and \"jakarta\" in both sentiments shows that the public's tweet regarding the policy for handling COVID-19 cannot be separated from the events / incidents when data collection was carried out. In addition, the high frequency of the word “jakarta” in negative sentiments also shows that the implementation of policies for handling COVID-19 in Jakar","PeriodicalId":32367,"journal":{"name":"Sistemasi Jurnal Sistem Informasi","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80343265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analisis Proses Bisnis Pengemasan Semen Menggunakan 7 Tools dan 11 Improvements Patterns","authors":"Sari Setyaningsih, N. Nadhiroh, Renny Sari Dewi","doi":"10.32520/STMSI.V10I1.1167","DOIUrl":"https://doi.org/10.32520/STMSI.V10I1.1167","url":null,"abstract":"Abstrak Menurut Direktur Utama Semen Indonesia Group, terdapat 19 perusahaan semen yang bermain di tahun 2020 ini, artinya terdapat kenaikan persaingan bisnis semen dibandingkan tahun 2015 yang hanya 7 perusahaan. Salah satu cara memenangkan persaingan ini yaitu dengan memahami proses bisnis, analisis kualitas, dan pengembangan proses bisnis. Penelitian ini bertujuan untuk menhasilkan saran yang dapat meningkatkan kualitas release semen dengan menggunakan metode 7 tools quality dan 11 improvement patterns . Objek penelitian yang digunakan ialah salah satu divisi packer pada salah satu plant di PT. XYZ. PT. XYZ sendiri merupakan salah satu produsen semen di Indonesia yang saat ini turut barmain pada pasar produksi semen. Data yang digunakan pada penelitian ini merupakan data primer yang didapatkan melalui pengamatan lapangan dan wawancara selama bulan Juli 2020 dan data sekunder yang didapatkan dari staff divisi packer . Analisis ini dapat digunakan untuk mengakomodir kebutuhan perusahaan untuk mengetahui masalah proses bisnis di salah satu divisi packer PT.XYZ agar perusahaan bisa mendapatkan saran untuk meningkatkan proses bisnis yang ada. Kata Kunci : analisis proses bisnis, 7 tools , 11 improvement patterns Abstract According to the Managing Director of the Semen Indonesia Group, there are 19 cement companies playing in 2020, meaning that there is an increase in competition in the cement business compared to 2015 which only 7 companies. One way to win this competition is by understanding business processes, quality analysis, and business process development. This study aims to produce suggestions that can improve the quality of the cement release using the 7 quality tools and 11 improvement patterns. The object of research used is one of the packer divisions at one of the plants at PT. XYZ. PT. XYZ itself is one of the cement producers in Indonesia which is currently playing in the cement production market. The data used in this study are primary data obtained through field observations and interviews during July 2020 and secondary data obtained from the packer division staff. This analysis can be used to accommodate the company's needs to find out business process problems in one of the packer divisions of PT. XYZ so that the company can get suggestions for improving existing business processes. Keywords: business process analysis, 7 tools, 11 improvement patterns","PeriodicalId":32367,"journal":{"name":"Sistemasi Jurnal Sistem Informasi","volume":"13 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-01-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89321960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"KLASIFIKASI TEKS LAPORAN MASYARAKAT PADA SITUS LAPOR! MENGGUNAKAN RECURRENT NEURAL NETWORK","authors":"Imam Fahrur Rozi, Vivi Nur Wijayaningrum, Nur Khozin","doi":"10.32520/STMSI.V9I3.977","DOIUrl":"https://doi.org/10.32520/STMSI.V9I3.977","url":null,"abstract":"ABSTRACT The existence of public dissatisfaction with public services causes the public to be provided with facilities to make complaints. One of the sites that can be used to make complaints is the Public Service Complaint Management System (SP4N LAPOR!). With this site, complaints made by the public can be handled quickly, transparently and accountably in accordance with the authority of each organizer. However, the large number of complaints that had to be processed caused the process of data verification and sorting of reports by respective departments to take quite a long time, so the report classification process was needed to speed up the handling and follow-up of a report. The purpose of this research is to classify each complaint report from the public in preparation for the verification process of each public report document, which is expected to have an impact on the accelerated process of handling and follow-up of each related institution or agency. In this study, Long Short-Term Memory Recurrent Neural Network was used to perform the classification process for each public report document. The learning model is evaluated using k-fold cross-validation of 10 parts of data. The evaluation results show that the average f-measure percentage is 85.69% for the balanced dataset and 79.44% for the unbalanced dataset, while the highest evaluation value of all evaluations results in an f-measure of 88.82%. The high accuracy of the modeling indicates that the proposed method can be used to classify public report documents. Keywords: classification, complaint, , long short-term memory, recurrent neural network, report ABSTRAK Adanya ketidak puasan masyarakat terhadap layanan publik menyebabkan masyarakat perlu disediakan fasilitas untuk melakukan pengaduan. Salah satu situs yang dapat digunakan untuk melakukan pengaduan adalah Sistem Pengelolaan Pengaduan Pelayanan Publik (SP4N LAPOR!). Dengan adanya situs ini, aduan yang dilakukan oleh masyarakat dapat ditangani dengan cepat, transparan, dan akuntabel sesuai dengan kewenangan masing-masing penyelenggara. Namun, banyaknya aduan yang harus diproses menyebabkan proses verifikasi data dan pemilahan laporan berdasarkan instansi masing-masing membutuhkan waktu yang cukup lama, sehingga proses klasifikasi laporan sangat dibutuhkan untuk mempercepat penanganan dan tindak lanjut dari sebuah laporan. Tujuan dari penelitian ini adalah mengklasifikasikan setiap laporan pengaduan dari masyarakat untuk persiapan proses verifikasi setiap dokumen laporan masyarakat, yang nantinya diharapkan dapat berdampak pada proses percepatan penanganan dan tindak lanjut dari setiap Lembaga atau instansi yang terkait. Pada penelitian ini, Long Short-Term Memory Recurrent Neural Network digunakan untuk melakukan proses klasifikasi setiap dokumen laporan masyarakat. Model pembelajaran dievaluasi menggunakan k-fold cross-validation sebanyak 10 bagian data. Hasil evaluasi menunjukkan rata-rata persentase f-measure sebesar 85,69% ","PeriodicalId":32367,"journal":{"name":"Sistemasi Jurnal Sistem Informasi","volume":"20 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78981676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Penerapan Social Network Analysis dengan Menggunakan Metode Sociomatrix pada Akun Instagram Siswa SMA di Surabaya","authors":"Nur Aini Rakhmawati, Rheindra Alfarhizi, Irmasari Hafidz","doi":"10.32520/stmsi.v9i2.807","DOIUrl":"https://doi.org/10.32520/stmsi.v9i2.807","url":null,"abstract":"Penelitian ini memetakan bentuk hubungan berdasarkan media sosial Instagram pelajar Sekolah Menengah Atas (SMA) di Surabaya dengan menggunakan socimatrix yang merupakan bagian dari Social Network Analysis . Hasil penelitian ini memetakan 18 kelompok berdasarkan 18 SMA di Surabaya , terdiri dari 1 sociogram besar dan 7 sociogram kecil , dimana setiap kelompok rata-rata berasal dari sekolah (SMA) yang sama . Sociogram besar terdiri dari 12 SMA. Akun yang paling dikenal oleh teman sekitarnya atau node terbesar berasal dari SMAN 7 Surabaya dengan 22 teman yang saling follow dengannya. Adapun akun yang memiliki pertemanan yang kuat atau link tertebal berasal dari SMAN 7 Surabaya dengan jumlah kesamaan followings dan followers sebanyak 360 akun atau senilai 6.00 pada link yang terbentuk. Pertemanan antar siswa perempuan (289) memiliki jumlah 2,5 kali dari jumlah pertemanan antar siswa laki-laki (115) dan pertemanan antar siswa perempuan memiliki jumlah hampir yang sama dengan pertemanan lawan jenis (284).","PeriodicalId":32367,"journal":{"name":"Sistemasi Jurnal Sistem Informasi","volume":"27 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-05-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84976836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}