cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Mesran
Contact Email
mesran.skom.mkom@gmail.com
Phone
+6282161108110
Journal Mail Official
mib.stmikbd@gmail.com
Editorial Address
Jalan sisingamangaraja No 338 Medan, Indonesia
Location
Kota medan,
Sumatera utara
INDONESIA
JURNAL MEDIA INFORMATIKA BUDIDARMA
Published by Sekolah Tinggi Manajemen Informatika dan Komputer Budi Darma
ISSN : 26145278     EISSN : 25488368     DOI : http://dx.doi.org/10.30865/mib.v3i1.1060
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering
Decission Support System, Expert System, Informatics tecnique, Information System, Cryptography, Networking, Security, Computer Science, Image Processing, Artificial Inteligence, Steganography etc (related to informatics and computer science)
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 1,182 Documents
 112   113   114   115   116 
Implementation of User Sentiment with Naïve Bayes Algorithm to Analyze LinkedIn Application Regarding Job Vacancies in the Play Store Al Ghozi, Dhiyauddin; Hasan, Firman Noor
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7879

Abstract

Mobile applications have become an important part, one of which is the LinkedIn application which is a mobile application that focuses on the recruitment process, job search and as a professional networking platform which is now increasingly relevant, especially in Indonesia. The methodology involves data collection, data preprocessing, data labeling, and application of the Naïve Bayes algorithm. Sentiment analysis can be used as a reference to improve the quality of an application and the level of user satisfaction as well as knowing the number of positive and negative sentiments in user feedback. The 999 data obtained were then divided into 60% training data and 40% test data. In this analysis, negative sentiment outweighs positive sentiment, with a total of 539 negative reviews and 460 positive reviews. Based on evaluation using the confusion matrix, accuracy results were 95.74%, precision was 100%, and recall was 91.46%. This research aims to provide insight into the communication and interaction patterns of LinkedIn users in relation to job opportunities and overall sentiment towards the platform.
Prediksi Jumlah Bayi Penerima Imunisasi DPT 1 dan DPT 2 Menggunakan Support Vector Regression Idriani R, Nova; Permana, Inggih; Salisah, Febi Nur; Megawati, Megawati; Rahmawita M, Medyantiwi
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7694

Abstract

Vaccination against diphtheria, pertussis (whooping cough), and tetanus is known as DPT immunization, which protects a person from three serious diseases. This vaccine is given in the form of an injection where there are 5 antigens in one injection of the vaccine. DPT immunization is a complete routine immunization that will be continued in grades 1 to 6 elementary school. DPT immunization is feared by mothers because of the side effects that occur in babies after the vaccine injection, namely that the baby will have a fever and be fussy. This has resulted in delays in collecting data on babies who have received this immunization, which has an impact on estimates of babies who will receive DPT immunization in the following month. Of course, this will disrupt the stock of vaccines provided, causing the potential for them to be out of stock. To overcome this problem, it is necessary to collect data on babies who have received DPT in the previous month. This data will be used to predict babies who will receive DPT immunization in the following month using the Support Vector Regression (SVR) method. So that the community health center can provide information regarding the prediction of the number of babies who will receive DPT immunization. This method uses three kernels and a Sliding Window to divide the data into smaller segments, moving alternately across the time series data, making it suitable for predicting babies who will receive DPT immunization in the next time interval. From the three kernels used on the two data that have been separated into DPT 1 and DPT 2, windowing size 3 linear kernels were obtained which were selected as an accurate evaluation of model work on DPT 1 with MAPE values of 3.35, RMSE 0.193, and R2 0.1. And windowing size 3 RBF kernels are more optimal in DPT 2 with MAPE values of 7.86, RMSE 0.163, and R2 0.288.
Penggunaan Naïve Bayes Classifier dalam Analisis Sentimen Ulasan Aplikasi McDonald's: Perspektif Pengguna di Indonesia Kurniawan, Salsha Dara Shinta; Fauzy, Akhmad
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7765

Abstract

The McDonald's mobile app has become popular among users, who often review their experiences through various review platforms. However, the sheer number of reviews suggests that the app's performance is still not satisfactory. This research aims to analyze public sentiment towards McDonald's app reviews using the Naïve Bayes Classifier algorithm. This algorithm was chosen because of its ability to classify text based on probability and its wide use in sentiment analysis. The research process began with the collection of review data totaling 4.996. Of these, 1.575 data showed neutral sentiment, while 2.137 data revealed positive sentiment, and 1.104 data showed negative sentiment towards the app. However, for the purposes of analysis using the Naïve Bayes algorithm, the focus is only on data that has positive and negative sentiment labels. Thus, the total amount of data used is 3.241 data, consisting of 2.137 positive data and 1.104 negative data. Followed by text pre-processing which includes cleaning, normalization, stopwords, stemming, tokenizing. The dataset is then divided into training data (80%) and testing data (20%). Naïve Bayes Classifier algorithm is used to classify the reviews into positive, negative, and neutral categories ignored. The results show that this model has an 90% accuracy rate in classifying sentiment. This analysis is necessary for the company's evaluation in order to know the public sentiment regarding the McDonald's app. The conclusion of this study shows that although the Naïve Bayes Classifier algorithm is quite effective in the sentiment classification of McDonald's app reviews, it is not enough to classify the sentiment of the McDonald's app.
Sentiment Analysis of Lazada Product Reviews using Convolutional Neural Network and Naïve Bayes Models Siddiq, Ikhsan Maulana; Lhaksmana, Kemas Muslim
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7834

Abstract

Lazada is one of the biggest marketplaces in Southeast Asia. One of the main features of Lazada is product reviews, any customer who has purchased and used a product from Lazada can provide reviews and ratings on the ones that have been purchased. Sentiment analysis on product reviews can help improve product and service quality, increase customer satisfaction, and improve purchasing decisions. Doing sentiment analysis of product reviews aims to help customers how to feel about the product, reading and analyzing each review manually is very not efficient. Sentiment analysis can automate handling large volumes of data quickly and accurately. In this research, using Lazada product review dataset to analyze sentiment by comparing Convolutional Neural Network (CNN) and Naive Bayes. CNN and Naive Bayes are two common methods used in text analysis and a comparison of their performance can provide the effectiveness of each in analyzing product sentiment. In this study, the authors propose to analyze the sentiment of product reviews using deep learning algorithm with CNN method. The results of this study explain that the CNN method can provide satisfactory results than Naive Bayes. Based on the overall evaluation, CNN gets an accuracy value of 99.31%, precision of 99.31%, recall 99.31%, and f1-score of 99.31%, while Naive Bayes gets the highest accuracy rate of 96.16%, precision 96.34%, recall 96.16%, and f1-score 96.16%.
Perbandingan Algoritma K-Nearest Neighbor dan Support Vector Machine Pada Pengenalan Pola Tulisan Tangan Widiyanti, Adella; Megawaty, Dyah Ayu
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7757

Abstract

Handwriting is a biometric characteristic because each person has a unique handwriting pattern. This uniqueness can be utilized as a biometric identity. Handwriting pattern recognition is one of the important fields in document analysis to biometric authentication. This research explores the implementation of K-Nearest Neighbors (K-NN) and Support Vector Machine (SVM) algorithms in the context of handwriting pattern recognition. In addition, this research incorporates digital image processing technology by utilizing feature extraction using Gray-Level Co-occurrence Matrix (GLCM). This process involves taking handwriting samples, digitizing them into digital images, and utilizing GLCM to extract texture features. These features play an important role in capturing the unique characteristics of each handwriting pattern. This research was conducted because handwriting has a wide implementation in various fields. In the field of data security, handwriting recognition can be used for data verification in financial transactions and official documents. A comparison of the K-NN and SVM algorithms was conducted to determine the most effective and efficient algorithm in handwriting pattern recognition. These two algorithms are very popular and often used in classification. By comparing these two algorithms, this research aims to evaluate and compare the performance of two classification algorithms in handwriting pattern recognition so as to provide recommendations for implementation in handwriting pattern recognition. The main focus of this research is to investigate the effectiveness and accuracy of the K-NN and SVM algorithms in recognizing and classifying handwriting. K-NN algorithm produces the highest accuracy value of 82.11%, while the SVM algorithm produces the highest accuracy value of 83.87%, so that the SVM algorithm becomes the best algorithm in the classification of handwriting pattern recognition.
DESIGNING AN AI CHATBOT (STYLESAVVY) FOR CHOOSING CLOTHES FASHION BASED ON SKIN TONE AT XI-XIU STORE Ayuningsih, Ekatri Ayuningsih; Lubis, Sevana Rizki; Tembusai, Zulkarnain
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.8220

Abstract

Chatbot is a computer program with artificial intelligence to interact with humans through conversation, provide responses, and offer services. Its function is to provide services or information to users in a way that resembles human conversation. This study can give recommandation towaards fashion and makeover based on skin tone and enhance confidence about self  performance. This study did not only provide recommendation by picture and description, but also a link to view the video that can be seen by the users. The result of this study gives varies benefits for researcher in understanding further about AI technology users in fashion industry, then for the company and education institution in progressing service and relevant curriculum. On the other side, this study contributes on AI technology development in the future, especially in terms of fashion and aesthetic.
Analisis Perbandingan Prediksi Tingkat Kemiskinan Menggunakan Metode XGBoost dan Random Forest Regression Prastiyo, Isnan Wisnu; Febriandirza, Arafat
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7892

Abstract

This research aims to compare the performance of two prediction algorithms, XGBoost Regression and Random Forest Regression, in predicting poverty levels in the DKI Jakarta area. For this research, researchers obtained data from the DKI Jakarta Central Statistics Agency (BPS) covering the period 2010 to 2023. The testing method used involved measuring Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) to assess the accuracy of predictions from the two algorithms. . The findings show that the Random Forest Regression algorithm generally produces more accurate predictions compared to the XGBoost Regression algorithm as seen from the test results on (MSE) and (MAPE) for most of the areas analyzed. As with MAPE for the West Jakarta area, the test results for XGBoost Regression were 1.43, while Random Forest Regression produced 1.42, so Random Forest Regression is better than XGBosst Regression. However, in the Seribu Islands, the MAPE for XGBoost is better with a value of 4.49 than for Random Forest Regression which has a value of 4.56. Then MSE Random Forest is better than XGBoost in this prediction test. For example, in the Central Jakarta area with a value of 0.02 for XGBoost Regression, while Random Forest Regression has a smaller test result with a value of 0.01.
Rancangan Alat Absensi Berbasis Internet of Things dan Notifikasi Smartphone Menggunakan App Inventor Warman, Aziz; Jufrizel, Jufrizel; Ullah, Aulia; Zarory, Hilman
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7720

Abstract

Technological developments have become a major focus when it comes to improving everyday productivity and innovation. Intelligent tools are created to facilitate and assist human work in life. Smart attendance machines are designed to replace the role of manual paper attendance and switch to an automated system. The problem with manual attendance is that there is potential for fraud in attendance and attendance data is vulnerable to damage and loss of data because it only uses paper media for storage and the use of manual attendance also has disadvantages related to attendance data that can be known by student guardians every day. This paper discusses the design of an attendance system using a Radio Frequency Identification (RFID) card as an identity used for the attendance process. The use of Liquid Crystal Display (LCD) to display information from card readings. ESP8266 microcontroller is used to run commands according to the program and access to Wifi that can connect to the internet. To store attendance data using application software that can be accessed by the admin. To monitor attendance, App Inventor is used which can be connected to a smartphone. The results of testing the tool show that the attendance machine can operate in accordance with the design and provide satisfactory results, the tool works by attaching the identity card to the card reader and the data will appear on the LCD in the form of card ID and attendance information, the time it takes to read the card until it appears on the LCD is 2-3 seconds.   Attendance data in the form of names, hours in, hours out and attendance information is successfully sent to the website application via an internet connection with the average time required of 4.43 seconds. Data in the form of sample photos was successfully sent by ESPcam to the website application via an internet connection with an average delivery time of 9.36 seconds. The attendance message was successfully sent to the Smartphone using App Inventor. 
Optimasi Algoritma KNN dengan Parameter K dan PSO Untuk Klasifikasi Status Gizi Balita Rochman, Bagus Fathur; Rahim, Abdul; Siswa, Taghfirul Azhima Yoga
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7841

Abstract

The toddler years are a crucial phase that requires constant nutritional monitoring, because rapid growth and development require optimal nutritional intake. Nutritional problems in toddlers can hinder physical growth and can even be fatal. In assessing the nutritional status of toddlers, it is important to use efficient methods. One approach that can be used is machine learning, which can help determine the nutritional status of toddlers. K-Nearest Neighbors (KNN) is an algorithm commonly used in object classification based on nearest neighbors. Even though it is simple, determining the correct K value is very important because it can significantly influence KNN performance. This research emphasizes the importance of choosing the right parameters to increase the accuracy of the KNN model in classifying the nutritional status of toddlers. The test results show that the optimal combination for KNN is at K=4, using the 'distance' weight and distance metric p=1, producing the highest accuracy of 91.15% on the test data. Furthermore, the research applied Particle Swarm Optimization (PSO) to optimize KNN parameters, and it was found that the optimal combination was with K=6, 'distance' weight, and distance metric p=1, achieving a mean accuracy of 93.44% and a test accuracy of 93.98%. PSO is proven to be effective in finding the best parameters that increase model generalization to test data. Test results with a training data ratio of 80% and testing 20% show the best accuracy of 93.98%. .The use of PSO for parameter optimization succeeded in increasing model accuracy by 3.10% compared to the model without optimization
Analisis Perbandingan Metode Teorema Bayes dan Certainty Factor Pada Diagnosis Gangguan Kecemasan Gobel, Citra Yustitya; Lasena, Marlin; Puspa, Misrawati Aprilyana; Utiarahman, Siti Andini
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7683

Abstract

Anxiety disorders are a mental health problem that is increasing in prevalence, but the lack of public knowledge about anxiety disorders means that many people are not aware of anxiety disorders, so information technology is needed to understand symptoms and diagnosis using more relevant methods in intelligent systems. Intelligent systems are able to help in analyzing various symptoms and identifying initial diagnosis results with wider accessibility, but the problem of this research is focused on selecting the most effective method for intelligent systems as a basis for clinical data analysis, so in this research we will compare the level of accuracy of applying the method, namely Bayes' theorem and Certanty factor for the diagnosis of anxiety disorders. Bayes' Theorem is a classic statistical approach, offering a structured and measurable framework for calculating the probability of disease based on clinical evidence, while the Certainty Factor is a method for proving the certainty value of a fact in the form of a metric in an intelligent system. The aim of this research is to analyze the performance of the Bayes Theorem method and certainty factor by examining the percentage results obtained by applying the two methods. that the percentage result of the Bayes Theorem calculation method is higher, namely 84%, compared to the percentage result of the certainty factor, namely 70%, so it can be concluded that the application of Bayes' theorem is better than the certainty factor, especially in the diagnosis of people with anxiety disorders.

Page 114 of 119 | Total Record : 1182

 112   113   114   115   116 

Filter by Year

2017 2024


Reset
Filter By Issues
All Issue Vol 8, No 3 (2024): Juli 2024 Vol 8, No 2 (2024): April 2024 Vol 8, No 1 (2024): Januari 2024 Vol 7, No 4 (2023): Oktober 2023 Vol 7, No 3 (2023): Juli 2023 Vol 7, No 2 (2023): April 2023 Vol 7, No 1 (2023): Januari 2023 Vol 6, No 4 (2022): Oktober 2022 Vol 6, No 3 (2022): Juli 2022 Vol 6, No 2 (2022): April 2022 Vol 6, No 1 (2022): Januari 2022 Vol 5, No 4 (2021): Oktober 2021 Vol 5, No 3 (2021): Juli 2021 Vol 5, No 2 (2021): April 2021 Vol 5, No 1 (2021): Januari 2021 Vol 4, No 4 (2020): Oktober 2020 Vol 4, No 3 (2020): Juli 2020 Vol 4, No 2 (2020): April 2020 Vol 4, No 1 (2020): Januari 2020 Vol 3, No 4 (2019): Oktober 2019 Vol 3, No 3 (2019): Juli 2019 Vol 3, No 2 (2019): April 2019 Vol 3, No 1 (2019): Januari 2019 Vol 2, No 4 (2018): Oktober 2018 Vol 2, No 3 (2018): Juli 2018 Vol 2, No 2 (2018): Apriil 2018 Vol 2, No 1 (2018): Januari 2018 Vol 1, No 3 (2017): September 2017 Vol 1, No 2 (2017): Juni 2017 Vol 1, No 1 (2017): Maret 2017 More Issue