Publication Search

Organisasi Kesehatan Dunia (WHO) secara resmi menyebut virus Covid-19 sebagai pandemi global, oleh karena itu semua negara di dunia berusaha meminimalkan dampak yang ditimbulkan oleh virus tersebut, yaitu dengan mengembangkan vaksin. Dalam konteks pandemi Covid-19, pemerintah Indonesia juga meminta dan mendorong masyarakat untuk turut serta mendukung vaksinasi, namun upaya tersebut sebenarnya memiliki kelebihan dan kekurangan, sehingga banyak masyarakat yang mengutarakan pendapatnya di jejaring sosial salah satunya Twitter. Penelitian ini bertujuan untuk mengetahui hasil penerapan analisis sentimen dan mengukur performansi algoritma Naïve Bayes Classifier (NBC) dan Support Vector Machine (SVM) terhadap data vaksin Covid-19 dengan cara mengklasifikasikan data tersebut ke dalam kelas positif dan negatif. Data tweet yang didapat kemudian dilakukan text preprocessing untuk mengoptimalkan pengolahan data. Terdapat 4 tahapan text preprocessing antara lain Case Folding, Tokenizing, Filtering, dan Stemming. Penelitian ini mengkaji kinerja Naïve Bayes Classifier (NBC) dan Support Vector Machine (SVM) dengan menambahkan teknik TF-IDF (Term Frequency-Inverse Document Frequency) yang bertujuan untuk memberikan bobot pada hubungan kata (term) sebuah dokumen. Kemudian melakukan splitting data yaitu membagi data training 80% dan data testing 20% dengan harapan mendapatkan model dengan performansi terbaik dan yang terakhir melakukan visualisasi data tweet dengan menggunakan Word Cloud agar bisa menarik sebuah kesimpulan. Hasil klasifikasi data tweet vaksin Covid-19 menggunakan algoritma Naïve Bayes Classifier mendapatkan nilai accuracy sebesar 81%, precision sebesar 80%, recall sebesar 99%, dan f1-score sebesar 89%, Sedangkan untuk algoritma Support Vector Machine mendapatkan nilai accuracy sebesar 87%, precision sebesar 88%, recall sebesar 96%, dan f1-score sebesar 92%.

The large number of theses will certainly make it difficult to find categories on thesis topics that have been written by students at a university. One of the uses of the Text Mining method is being able to group thesis objects into the number of clusters formed by the clustering algorithm. This study aims to compare 2 clustering algorithms, namely the K-Means and K-Medoids algorithms to obtain an accurate evaluation of the performance and computational time in the case of thesis clustering, so that relevant topics can be grouped and have better clustering accuracy. The evaluation parameter used is the Davies Bouldin Index (DBI) which is one of the testing techniques on clustering results, with the distribution of training data and testing data using cross validation using a repetition parameter of 10 folds iteration. From the results of the study with the Term Weighting condition used is Term Occurrences and using the N-Grams value is 2, it can be concluded that the K-Means algorithm has a better DBI value of -0.426. Meanwhile, the range of DBI values owned by K-Medoids with the same conditions has a DBI value of -1,631. However, from the visualization results using t-SNE with the same supporting parameters, there are options that can be used, namely the number of clusters is 6, and the DBI value is -1.110. For testing the computational time in the clustering process of 50 thesis documents, the K-Means algorithm has an average time of 2.5 seconds while the K-Medoids algorithm has an average time of 261.5 seconds. The computer specifications used are Asus ZenBook UX425EA.312 with the processor used is 11th Gen Intel® Core™ i5-1135G7 @ 2.40GHz @ 2.40GHz, the graphics card is Intel® Iris® Xe Graphics, the RAM used is 8GB, with storage of 512GB SSD.

In developing a business or sale is to follow technological developments including the use of systems for buying and selling interactions. There are already many sellers who make buying and selling interactions online. In addition, to develop a business, it is also necessary to predict future sales so that the seller knows and prepares the number of goods to be sold to avoid shortages or excess quantities of goods. To find sales predictions, various methods can be used, one of which is Double Exponential Smoothing method. Double Exponential Smoothing  method is the time series method that uses data from the past to predict the next period. The data processed is sales data at Dasni clothing stores for one year. The results obtained are in the form of a sales prediction system for the next 3 months period which calculates the level of prediction accuracy using MAPE (Mean Absolute Percentage Error) with the smallest error sought because the smaller the error, the more accurate it is to predict the number of sales in the next period. This prediction system is also designed using the PHP programming language.

Sentiment analysis of comments from visitors to tourist attractions and the public on tourist attractions in Sukabumi Regency which is one of the areas with various categories of tourist objects and is a sector of economic income for the surrounding community or for related parties such as the government and managers, in sentiment analysis research This includes using the Nave Bayes classification algorithm to examine the sentiment of tourist visitors and the performance of the classification model used. The data used in this research was taken from the website from Tripadvisor and Google Maps using a crawling technique, which then processed the data by a pre-processing process and then applied a classification to the data and got a sentiment visualization by processing word frequency on tourist visitor sentiment data. The results of the accuracy of the model used were re-tested with the k-fold cross validation method and the results of sentiment visualization got the frequency of words that most often appear on negative sentiment labels are garbage, beaches, lacking, places, roads, parking, dirty, entering, caring, clean , expensive, pay, manage, good and water.

Covid-19 has spread widely with various variants, disrupting human social activities, the activities in question include the implementation of events, but there are other alternatives by utilizing technology, events can still be held online. However, the number of events that are held online makes it difficult for someone to find the event they want because there are too many events on the website so someone experiences information overload. Therefore, the authors conduct research with the goal to make it easier for someone to find the event they want by implementing a recommendation system on the website. In this study, the authors make a recommendation system using the Content-Based Filtering method in recommending an online event. The results of this study obtained an accuracy of 86% of the performance of the model carried out by SVM.

Recording financial transactions is an important activity that must be carried out by a business. In accounting, recording financial transactions is a fundamental thing that must be done. With these records, all business financial transactions can be accounted for and brought to the financial statements. Computerized technology using barcodes in payment transactions has the aim of increasing speed, accuracy, and service quality. In carrying out payment administration activities still using the manual system will have an impact on the Administrative officer having difficulty finding data on students who want to pay and the network (LAN) has not been implemented on the computer is also a problem at the research site, because to share data with the treasurer and principal becomes constrained, data can be damaged, lost or misused because its security is not guaranteed. In solving these problems, the researchers collected data and facts that existed at the research site, then designed a payment administration information that was in accordance with the needs of the school. In making Administrative Information System Integrated With Barcode Reader, researchers used Microsoft Visual Basic 6.0 programming language, MySQL Server database as data storage media and Subtime Text as tools to create source code. In the preparation of this application using object-oriented methods.

Assessment of individual performance in an organization is needed to improve organizational performance, not least in the basketball team. Satya Wacana Saints Salatiga is a basketball team in Indonesia that competes in the Indonesian Basketball League (IBL). All players have statistical values in a basketball game, including points, assists, blocks, rebounds, and steals. These five features can be used as a reference for coaches in determining the performance of players consisting of players with good, moderate, and poor performance. Feature selection determines the feature(s) that most affects a player's performance. In this study, a feature selection of the statistical value of players was carried out to assess the performance of basketball players. The data was obtained from IBL statistical data for the Satya Wacana Saints Salatiga team for the 2021 season. The method used was k-means and fuzzy c-means with feature selection. The experiment results showed that the point value was the main factor influencing players' performance. The comparison between the k-means and fuzzy c-means with the actual performance of the coaches' assessment shows that the fuzzy c-means algorithm has an accuracy rate of 1.0000, while the k-means algorithm is 0.8000. It means that the evaluation of the player's performance can be determined from the point value using the fuzzy c-means algorithm.

The Free Nutritious Meals (MBG) program launched by the Indonesian government aims to address the problem of malnutrition in children and students. However, the acceptance of this program in the community still requires in-depth evaluation because there are many negative sentiments that dominate on social media. This study aims to analyze the sentiment of the Indonesian community regarding the Free Nutritious Meals program on social media X (Twitter) using the Bidirectional Gated Recurrent Unit (BiGRU) model. Of the 1,405 tweet data obtained, 57% were negative opinions and 43% were positive opinions. The evaluation results show that the BiGRU model with FastText support to handle potential overfitting, is able to classify sentiment effectively, with an accuracy of 80%. Sentiment analysis shows that the majority of public responses to the Free Nutritious Meals (MBG) program tend to be negative, with 798 negative tweets and 607 positive. This reflects public dissatisfaction with the implementation of the program and highlights the need for evaluation and improvements so that the benefits can be more widely felt by the community.

Laibu Samsaman : with the title "Effectiveness of the Process of Determining Village Devices in the Administrative Village of Otademan, Wakate District, Eastern Seram Regency". Accompanied by Advisor I: Z. A. Rengifurwarin and Advisor II: I. S. Ponto. This research is a descriptive qualitative research. Aims to describe and explain an overview of the Effectiveness of the Process of Determining Village Devices in the Administrative Village of Otademan Kec. Wakate Kab. SBT. Informants of this study amounted to 10 people. The data needed in this study were collected through observation, interviews and documentation techniques. Data was successfully collected, processed and analyzed with the help of descriptive qualitative analysis techniques. The results of this study indicate that the effectiveness of determining Otademan Administrative village apparatus is generally ineffective or not optimal, which is seen based on a) accuracy of age/age, b) accuracy of education, c) accuracy of work experience, d) accuracy of work skills, e) accuracy as villagers. This is influenced by supporting and inhibiting factors such as: a) likes and dislikes, b) group fanaticism, c) nepotism, and d) loyalty. The implications of this research, if you want to increase the effectiveness of determining village officials in the Otademan Administrative Village, Kab. SBT. district Wakate, the things that need to be considered are the level of accuracy of age/age, accuracy of education, accuracy of work experience, accuracy of work skills, and accuracy as a villager.

Incremental rotary encoder is a sensor that can be used to measure the degree of rotation in ship steering simulations. To create a ship steering simulation, Visual Basic software was used to simulate the movement of the rudder and ship. Meanwhile, to obtain incremental rotary encoder reading data, serial communication is used via Universal Serial Bus (USB) media bridged by Arduino which is programmed to convert incremental sensor signals into ASCII signals with a bolt rate of 9600 bps. The aim of this research is to test the accuracy level of the incremental rotary encoder sensor in ship steering simulations using Visual Basic software on commercial ships by using the Solas rule that a ship's rudder must comply when rotated from the midship position to the 35 degree port side position followed by the 35 degree position. starboard side and returning to midship, the rudder movement time was less than 28 seconds. Test results in terms of response speed of the incremental rotary encoder sensor are very good, while in terms of accuracy level for one degree of steering rotation, the result is 4.571 on the Arduino IDE serial monitor reading..

Starting from the development of medical technology that is increasingly sophisticated and rapidly growing,researchers conduct medical research, namely about patient infusion handling services. In handling patient infusion, currently it is still manual which is carried out by nurses / medical personnel. Infusion handling services for patients still have shortcomings, namely the process of monitoring and replacing infusion fluids which are often late. If the problem is not treated quickly, it can lead to problems, namely the presence of air embolism in the blood vessels (the entry of foreign objects into the blood vessels, for example air). From that problem, the researchers made a new innovation in medical technology in handling infusions automatically and based on IoT. In this study, the smart online infusion device that has been made has good features and is very effective in handling infusions. This device has 3 main functions, namely: it can monitor the remaining infusion, it can change the infusion fluid automatically and it can indicate a blocked patient's infusion. This device already has a method for processing data with fuzzy logic. Media monitoring has been supported by a website that can be controlled remotely and in real time. Tests have been carried out and the effectiveness of the system is found to have an error rate of 0.2% - 0.7% and has an accuracy of 98%. Thus this tool can be used in terms of handling patient infusion automatically.

For an organization, speed and accuracy in obtaining information has become a necessity. The existence of an information system becomes a necessity to solve the problem of speed and accuracy in accessing information. XYZ Electronic Store before implementing the information system, had difficulty in knowing quickly and accurately about sales information and how much the store's debt had not been paid. The research method used in this research is observation, interviews and design and implementation of the system. Design system design with DFD, ERD and implementation with PHP programming language. Design system design with the prototype method. After implementing the sales accounting information system and debt recording, the problems faced by XYZ Electronic Store can be resolved. Information on the number of sales in a certain period can be quickly identified, and can schedule debt payments. Debt payment time can be set because the system records all complete debt lists along with the due date.

Online media news is known for its lack of credibility in conveying information and its lack of prioritizing objectivity (accuracy, fairness , completeness) in pursuit of instantaneousness. There is quite a bit of news that puts Muslims in a corner, creating a negative image of the Islamic religion . This research aims to find out how the Radar Bogor media presents news content, as well as knowing the accuracy of news content about Islam on the Radar Bogor online media. This research uses the library research method or library study using Roland Barthes' Semiotics. The assessment categories in analyzing accuracy are in accordance with research conducted by the Press Council in reporting research on 28 newspapers in Java in 2004, including checking, writing errors, relevant news sources, title and content accuracy, photo and content accuracy. The results of the research show that in terms of checking and rechecking, suitability of photos and news content, relevant news sources, suitability of news titles and content, Radar Bogor accurately presents news about Islam. However, in news writing, the 5W 1 H element is complete, the sentences are connected to each other. In spelling, typos or typos were found in 6 news stories which did not reduce the original meaning.

The development of Information Technology (IT) is now very rapid and has been used in various aspects of life both in the field of government, banking, socio- cultural, industrial, education, and even health. One type of disease that gets attention for the application of IT is corona virus or better known as Covid 19 because the spread is quite widespread throughout the country, especially in the territory of Indonesia. Corona virus disease development in Indonesia is growing, based on WHO data as of today on August 30, 2020 positive cases have reached 172,053 people, cases died 7,343 people and recovered 124,185 people and the number of cases is increasing every day. Based on these conditions, Central Aceh is in a state of alert against the threat of corona virus. then a form of prevention  of the widespread spread of the virus can be done by breaking the chain of transmission by doing social distancing. In this study, a system will be designed to anticipate the Covid-19 pandemic by predicting the rate of spread of covid-19, especially in central Aceh districts using the Naive Bayes Classifier method. The accuracy level of this system is a positive case of 60%.

One of the tests that measures intelligence is the IST Test with 9 sub tests, and one of the sub tests in it is the last sub test, namely ME (Merkaufgaben). This subtest measures memory. This memory is closely related to attention and the ability to remember. Memory can be said to be sharp or dull when viewed from the accuracy, thoroughness or outline, or shallowness of the memory content. Estimates, feelings, emotions, affection, hopes and desires; Also plays a role in memory function. In this research, the researcher took only one thing, namely memory ability, the sample was carried out on psychology students in semesters 4, 6, 8, totaling 98 students. Using descriptive research methods. The aim of this research is to see a picture of the memory level of Psychology students at the Main Potential University in the morning and evening students because memory is very important for their ongoing learning process. Recall or memory is a mental process that an individual has to code, store, maintain and remember information, knowledge or past experiences in the brain which can be recalled for use some time later. This research approach uses a 6 minute test, then scoring based on morning and evening groups and based on semester level. Tests are given based on each class, the morning class is carried out during the morning class at 09.00 and the evening class is carried out at 18.00. The results obtained were that the superior level of memory was found in semester 8 students at 17.3%, semester 6 at 11.2%, semester 4 at 7.14%. High average memory level at semester 8 at 13.26% and semester 6 at 9.1% and semester 4 at 13.26%. 7 is 7.14% Average memory level is located in semester 6 with 14, namely 14.26% and semester 4 with 10, namely 10.20% and semester 8, namely 3, is 3.06%. Low Average level of memory is located in semester 6, namely 7, namely 7.14% and semester 6. of 6, namely 1.12% and semester 8 of 1 with 1.02%. The highest level of superior memory based on morning and evening classes is in semester 8 of the evening class, 17.34%. These results are useful in the future and need to be improved in upgrading memory to be able to carry out daily learning activities.

The increased garbage creation in Maros may motivate businesses to become more concerned with environmental sustainability. Armour Coffee's green marketing strategy begins with the brand logo and extends to the firm's vision and objective. According to statistics from the top brand index, Armour Coffee remains the least popular local coffee shop in Indonesia, which is both a phenomena and a problem in this study. Based on the findings, the study concludes that Green Product and Green Place have a favourable influence on Interest in Purchasing Armour Coffee in Maros. Meanwhile, Green Price and Green Promotion had little influence on Interest in Purchasing Armour Coffee in Maros. Simultaneously, green product, green pricing, green location, and green promotion (green marketing mix) impact interest in purchasing Armour Coffee in Maros.