Claim Missing Document
Check
Articles

Found 9 Documents
Search

Sentiment Analysis Of Instagram Social Media Users For BPJS Health Services Using Support Vector Machine Algorithm Hsb, Dinda Umami; Furqan, Mhd; Armansyah, A
IJISTECH (International Journal of Information System and Technology) Vol 8, No 1 (2024): The June edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v8i1.349

Abstract

Health services are an important aspect of people's quality of life, and BPJS as a public health service provider in Indonesia is often the subject of discussion on social media platforms. The SVM method has proven effective in sentiment analysis in various domains, including social media. In this study, data in the form of user comments and uploads on BPJS Instagram accounts were collected and processed to identify Positive, Negative or Neutral sentiments regarding the health services provided by BPJS. with the government's efforts to improve access and quality of health services for pregnant women as well as provide financial protection in order to reduce maternal and infant mortality in Indonesia and has the aim of reducing the burden of childbirth costs for people with low and middle incomes. This information can be input for BPJS in improving quality according to public expectations. In this research with a data set of 600 comments, the research was carried out with the support vector machine classification and the highest accuracy results in the first test experiment on 80% training data and 20% test data with 97% precision, 64% recall and 77% F1-Score obtained accuracy by 83%.
Determination of The Closest Path Using The Greedy Algorithm Furqan, Mhd.; Adha, Rifki Mahsyaf; Armansyah, A
IJISTECH (International Journal of Information System and Technology) Vol 7, No 5 (2024): The February edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v7i5.332

Abstract

Several alternate routes are displayed by the greedy algorithm, which is widely used in the closest travel route search application. This study employs the greedy method, which sets up a route map to quickly determine the shortest path. The goal of this study is to find the shortest path using a greedy algorithm. By using a greedy algorithm system to find the closest point to which the user's selection is made, the study's eight times with different points on the graph can be seen in the user's position. In an attempt to find the best solution, the greedy algorithm—which is renowned for its simplicity and effectiveness—iteratively chooses the best option available at each step. The greedy algorithm frequently gives priority to proximity when it comes to travel route optimization, and it might not always produce the shortest path overall. However, it's a well-liked option for some applications due to its quickness and simplicity of implementation. Notwithstanding its drawbacks, the greedy algorithm can offer insightful solutions for optimization and route planning issues. Users can make decisions more quickly and possibly find alternate routes they might not have otherwise thought of by using this algorithm to find the closest point in a travel route search application. The study's conclusions also emphasize how crucial it is to take user convenience and preferences into account when developing route planning systems. Future studies could look into ways to improve the greedy algorithm's performance and fix its drawbacks, like adding more heuristics or combining it with other optimization strategies. Overall, this study's findings validate the greedy algorithm's efficacy as a workable choice for locating the closest point in travel route search applications, providing consumers with a dependable and approachable navigational aid.
Determination of The Closest Path Using The Greedy Algorithm Furqan, Mhd.; Adha, Rifki Mahsyaf; Armansyah, A
IJISTECH (International Journal of Information System and Technology) Vol 7, No 5 (2024): The February edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v7i5.332

Abstract

Several alternate routes are displayed by the greedy algorithm, which is widely used in the closest travel route search application. This study employs the greedy method, which sets up a route map to quickly determine the shortest path. The goal of this study is to find the shortest path using a greedy algorithm. By using a greedy algorithm system to find the closest point to which the user's selection is made, the study's eight times with different points on the graph can be seen in the user's position. In an attempt to find the best solution, the greedy algorithm—which is renowned for its simplicity and effectiveness—iteratively chooses the best option available at each step. The greedy algorithm frequently gives priority to proximity when it comes to travel route optimization, and it might not always produce the shortest path overall. However, it's a well-liked option for some applications due to its quickness and simplicity of implementation. Notwithstanding its drawbacks, the greedy algorithm can offer insightful solutions for optimization and route planning issues. Users can make decisions more quickly and possibly find alternate routes they might not have otherwise thought of by using this algorithm to find the closest point in a travel route search application. The study's conclusions also emphasize how crucial it is to take user convenience and preferences into account when developing route planning systems. Future studies could look into ways to improve the greedy algorithm's performance and fix its drawbacks, like adding more heuristics or combining it with other optimization strategies. Overall, this study's findings validate the greedy algorithm's efficacy as a workable choice for locating the closest point in travel route search applications, providing consumers with a dependable and approachable navigational aid.
Sentiment Analysis Of Instagram Social Media Users For BPJS Health Services Using Support Vector Machine Algorithm Hsb, Dinda Umami; Furqan, Mhd; Armansyah, A
IJISTECH (International Journal of Information System and Technology) Vol 8, No 1 (2024): The June edition
Publisher : Sekolah Tinggi Ilmu Komputer (STIKOM) Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/ijistech.v8i1.349

Abstract

Health services are an important aspect of people's quality of life, and BPJS as a public health service provider in Indonesia is often the subject of discussion on social media platforms. The SVM method has proven effective in sentiment analysis in various domains, including social media. In this study, data in the form of user comments and uploads on BPJS Instagram accounts were collected and processed to identify Positive, Negative or Neutral sentiments regarding the health services provided by BPJS. with the government's efforts to improve access and quality of health services for pregnant women as well as provide financial protection in order to reduce maternal and infant mortality in Indonesia and has the aim of reducing the burden of childbirth costs for people with low and middle incomes. This information can be input for BPJS in improving quality according to public expectations. In this research with a data set of 600 comments, the research was carried out with the support vector machine classification and the highest accuracy results in the first test experiment on 80% training data and 20% test data with 97% precision, 64% recall and 77% F1-Score obtained accuracy by 83%.
Algoritma Genetika Untuk Perancangan Aplikasi Penjadwalan Mata Pelajaran Furqan, Mhd; Armansyah, A; Ananda, Rizki
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 6, No 2 (2022): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v6i2.476

Abstract

The schedule is one of the important activities to help the teaching and learning process in schools, the schedule planning process is still done manually so there are still conflicting schedules between classes. because of the large number of classes and a lot of time ordering a certain day so that sometimes up to 3 times the revision schedule, and the implementation of learning becomes late. To overcome this, one of the appropriate ones is used so that the scheduling process can run well. One of the algorithms used for scheduling the genetic algorithm is one of the improvement algorithms that can be used in various types of problems such as scheduling, the schedule will be tested on classes that clash, which are selected randomly. random or random in each class, the test will be asked to input or fill in the crossover probability number = 0.70 and mutation probability = 0.40 and the number of generations = 1000, then executed. After that it will occur and program execution in the form of selection, crossover, and mutation that will occur in the background of the screen, so that the results of applying 17 classes and 1 laboratory room using the genetic algorithm method can be used to compile a list of lessons.
Optimasi Sentimen Analisis Informatif dan Tidak Informatif dari Tweet di BMKG Menggunakan Algoritma Naive Bayes dan Metode Teknik Pengambilan Sampel Minoritas Sintetis Hidayatulloh, Muhammad Yusuf; Sunanto, Anto; Armansyah, A; Gevin, Muhammad Farrell Afelino; Saputra, Dedi Dwi
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 1 (2023): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i1.565

Abstract

The emergence of computer-based and mobile-based social networks seems to have received high attention from the public. Evidenced by the increasing number of social networks that appear. Friendster, Facebook, Twitter, Linkd In and many others. Twitter is one of the social media used to find information, Twitter users generally report every activity. They are even more helped by the existence of increasingly sophisticated cellphones. The system created in this study to optimize the analysis of informative and uninformative sentiment using a rapid miner application with the Naïve Bayes, Naïve Bayes + Adaboost, SVM, and SVM PSO methods using data taken from twitter @infoBMKG. The research method used is the collection of tweet data from twitter taken by the Crawling method. The data taken is tweets in Indonesian with a total of 1,000 tweets from the @infoBMKG twitter account. The results of the nave Bayes algorithm test carried out in this study were to measure the performance of accuracy, precision, recall, AUC from the results of the training and submission of datasets that had gone through the data preprocessing process. From the results of the research that has been done, it is proven that the optimization of informative and uninformative sentiment analysis from tweets on BMKG's twitter gets good results using the Support Machine Vector method with higher Accuracy, Recall, and AUC values than other methods.
Algoritma Genetika Untuk Perancangan Aplikasi Penjadwalan Mata Pelajaran Furqan, Mhd; Armansyah, A; Ananda, Rizki
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 6, No 2 (2022): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v6i2.476

Abstract

The schedule is one of the important activities to help the teaching and learning process in schools, the schedule planning process is still done manually so there are still conflicting schedules between classes. because of the large number of classes and a lot of time ordering a certain day so that sometimes up to 3 times the revision schedule, and the implementation of learning becomes late. To overcome this, one of the appropriate ones is used so that the scheduling process can run well. One of the algorithms used for scheduling the genetic algorithm is one of the improvement algorithms that can be used in various types of problems such as scheduling, the schedule will be tested on classes that clash, which are selected randomly. random or random in each class, the test will be asked to input or fill in the crossover probability number = 0.70 and mutation probability = 0.40 and the number of generations = 1000, then executed. After that it will occur and program execution in the form of selection, crossover, and mutation that will occur in the background of the screen, so that the results of applying 17 classes and 1 laboratory room using the genetic algorithm method can be used to compile a list of lessons.
Optimasi Sentimen Analisis Informatif dan Tidak Informatif dari Tweet di BMKG Menggunakan Algoritma Naive Bayes dan Metode Teknik Pengambilan Sampel Minoritas Sintetis Hidayatulloh, Muhammad Yusuf; Sunanto, Anto; Armansyah, A; Gevin, Muhammad Farrell Afelino; Saputra, Dedi Dwi
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 1 (2023): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i1.565

Abstract

The emergence of computer-based and mobile-based social networks seems to have received high attention from the public. Evidenced by the increasing number of social networks that appear. Friendster, Facebook, Twitter, Linkd In and many others. Twitter is one of the social media used to find information, Twitter users generally report every activity. They are even more helped by the existence of increasingly sophisticated cellphones. The system created in this study to optimize the analysis of informative and uninformative sentiment using a rapid miner application with the Naïve Bayes, Naïve Bayes + Adaboost, SVM, and SVM PSO methods using data taken from twitter @infoBMKG. The research method used is the collection of tweet data from twitter taken by the Crawling method. The data taken is tweets in Indonesian with a total of 1,000 tweets from the @infoBMKG twitter account. The results of the nave Bayes algorithm test carried out in this study were to measure the performance of accuracy, precision, recall, AUC from the results of the training and submission of datasets that had gone through the data preprocessing process. From the results of the research that has been done, it is proven that the optimization of informative and uninformative sentiment analysis from tweets on BMKG's twitter gets good results using the Support Machine Vector method with higher Accuracy, Recall, and AUC values than other methods.
Analisis Algoritma Sequential Search Pada Aplikasi Pencarian Berita Furqan, Mhd; Armansyah, A; Kurniawan, Riski Askia
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 8, No 2 (2023): Edisi Agustus
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v8i2.622

Abstract

The algorithm is an approach to be able to compile and manage data efficiently. The Sequential Search algorithm is used to build a mobile-based news search application. The search function is used to validate the data itself. The Sequential Search algorithm has 2 possibilities, namely the best possibility (best case) and the worst case (worst case). In determining a possibility, it takes the complexity of the time algorithm. This study will analyze the Sequential Search algorithm in determining the 2 possibilities that occur in mobile applications. Data is one of the things needed in the development of an application. There are 100 data used by researchers as keywords and researchers will take 5 keywords, namely Earthquake, PDI, Indonesian Education, Floods, and Online Sales to determine the best case and worst case from the Sequential Search algorithm. In determining the speed of time required running time program in units of milliseconds (ms). So that the average time for the earthquake keyword is 0.014189 ms, the PDI keyword is 0.073763 ms, the Indonesian Education keyword is 0.169640 ms, the Flood keyword is 0.206307 ms, and the Online Selling keyword is 0.284086 ms. By obtaining the time from the test, the results of the complexity are also obtained, namely Tmin(n) = 0.014189 ms so that the best case is found in the Earthquake keyword and Tmax(n) = 0.284086 ms so that the worst case is found in the Online Selling keyword. And Tavg(n) = 0.1491375 ms. News API is HTTP REST API which is used to access news after keywords are found