Pub Date : 2022-07-27DOI: 10.1109/ISITDI55734.2022.9944482
Muammar Notareza Ramadhan, I. Budi, A. Santoso, Ryan Randy Suryono
Hate speech is an action in the form of communication either directly or through the media performed by groups or individuals with the aim of provoking, inciting, or insulting a group or other individuals. 3, 640 hate speech spread across various social media. 677 KBGO cases, which were dominated by sexual violence cases spread through online media. Our research aims to produce the best classification model with high accuracy by comparing several combinations of machine learning techniques. We collected 9, 035 twitter user opinions to be used as a dataset. From a total of 6, 089 opinions that were successfully annotated, 5, 102 opinions were classified as non-hate speech and 987 opinions as hate speech. We purpose SVM model classification with TF-IDF (Unigram) as feature extraction method and Oversampling method such as ROS and SMOTE to solve imbalance dataset problem and improve the performance of model classification. The classification model with SVM algorithm reach the best accuracy, which is 0.942 with F1-score of 0.940.
{"title":"Sexual Violence Classification as Hate Speech using Indonesian Tweet","authors":"Muammar Notareza Ramadhan, I. Budi, A. Santoso, Ryan Randy Suryono","doi":"10.1109/ISITDI55734.2022.9944482","DOIUrl":"https://doi.org/10.1109/ISITDI55734.2022.9944482","url":null,"abstract":"Hate speech is an action in the form of communication either directly or through the media performed by groups or individuals with the aim of provoking, inciting, or insulting a group or other individuals. 3, 640 hate speech spread across various social media. 677 KBGO cases, which were dominated by sexual violence cases spread through online media. Our research aims to produce the best classification model with high accuracy by comparing several combinations of machine learning techniques. We collected 9, 035 twitter user opinions to be used as a dataset. From a total of 6, 089 opinions that were successfully annotated, 5, 102 opinions were classified as non-hate speech and 987 opinions as hate speech. We purpose SVM model classification with TF-IDF (Unigram) as feature extraction method and Oversampling method such as ROS and SMOTE to solve imbalance dataset problem and improve the performance of model classification. The classification model with SVM algorithm reach the best accuracy, which is 0.942 with F1-score of 0.940.","PeriodicalId":312644,"journal":{"name":"2022 International Symposium on Information Technology and Digital Innovation (ISITDI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123821046","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}
Pub Date : 2022-07-27DOI: 10.1109/ISITDI55734.2022.9944484
Dody Ichwana Putra, Diladia Suarmin, S. Ekariani
This paper presents the fatigue warning system based on heart rate and oxygen saturation monitoring using a non-invasive wearable sensor on the android platform. This study aims to provide an early warning in anticipation of fatigue in real-time during physical exercise. An algorithm to define the level of fatigue when physical exercise is provided in this study. A non-invasive wearable sensor located on the wrist is used to detect the user's heart rate and oxygen saturation and monitor them on the android applications. The user's family gets the notifications and the user's locations when the system detects the indications of the user's fatigue during the physical exercise. The testing is done by jogging on the treadmill under the scenario variations of age, running speed, and running duration to see the effect of physical activity on the heart rates and oxygen saturation. The experiments show heart rate detection, and oxygen saturation accuracies are 93.3% and 91.9%, respectively. The android application warns when the user's heart rate and oxygen saturation are under abnormal conditions. The user's age, running speed, and exercise duration affect the heart rate and oxygen saturation during jogging. The user feels fatigued when reaching above 80% of maximum heart rate and oxygen saturation level under 95%.
{"title":"Fatigue Warning System During Physical Exercise Based on Heart Rate and Oxygen Saturation Using Non-invasive Wearable Sensor","authors":"Dody Ichwana Putra, Diladia Suarmin, S. Ekariani","doi":"10.1109/ISITDI55734.2022.9944484","DOIUrl":"https://doi.org/10.1109/ISITDI55734.2022.9944484","url":null,"abstract":"This paper presents the fatigue warning system based on heart rate and oxygen saturation monitoring using a non-invasive wearable sensor on the android platform. This study aims to provide an early warning in anticipation of fatigue in real-time during physical exercise. An algorithm to define the level of fatigue when physical exercise is provided in this study. A non-invasive wearable sensor located on the wrist is used to detect the user's heart rate and oxygen saturation and monitor them on the android applications. The user's family gets the notifications and the user's locations when the system detects the indications of the user's fatigue during the physical exercise. The testing is done by jogging on the treadmill under the scenario variations of age, running speed, and running duration to see the effect of physical activity on the heart rates and oxygen saturation. The experiments show heart rate detection, and oxygen saturation accuracies are 93.3% and 91.9%, respectively. The android application warns when the user's heart rate and oxygen saturation are under abnormal conditions. The user's age, running speed, and exercise duration affect the heart rate and oxygen saturation during jogging. The user feels fatigued when reaching above 80% of maximum heart rate and oxygen saturation level under 95%.","PeriodicalId":312644,"journal":{"name":"2022 International Symposium on Information Technology and Digital Innovation (ISITDI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130790316","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}
Pub Date : 2022-07-27DOI: 10.1109/ISITDI55734.2022.9944418
Ninon Nurul Faiza, Suhardi, Taufik Iqbal Ramdhani
The implementation of Industry 4.0 drives digital transformation in the industry and public services. The process involves a paradigm shift in the government's business services, such as implementing electronic-based archives organized by ANRI. The archive has a vital role as recorded information and events concerning various fields. As the answer to the digital transformation shift, ANRI published regulation as a foundation in building an electronic-based archive system that involves four architecture principles of integrated, dynamic, compliance, and comprehensive architecture principles. This study uses a combination of service computing system engineering, platform engineering, microservice modeling, and OAIS reference model to design an archival service platform architecture that complies with government regulations and related standards. The model evaluation indicates good results as the coupling factor satisfies the loosely coupled condition, the cohesion factor has a relatively strong relationship, the complexity factor signifies low value, and the reusability factor fulfills the high reusable rate.
{"title":"Designing Service Architecture Platform using SCSE Framework for National Archive System Based on OAIS and Microservice Modeling","authors":"Ninon Nurul Faiza, Suhardi, Taufik Iqbal Ramdhani","doi":"10.1109/ISITDI55734.2022.9944418","DOIUrl":"https://doi.org/10.1109/ISITDI55734.2022.9944418","url":null,"abstract":"The implementation of Industry 4.0 drives digital transformation in the industry and public services. The process involves a paradigm shift in the government's business services, such as implementing electronic-based archives organized by ANRI. The archive has a vital role as recorded information and events concerning various fields. As the answer to the digital transformation shift, ANRI published regulation as a foundation in building an electronic-based archive system that involves four architecture principles of integrated, dynamic, compliance, and comprehensive architecture principles. This study uses a combination of service computing system engineering, platform engineering, microservice modeling, and OAIS reference model to design an archival service platform architecture that complies with government regulations and related standards. The model evaluation indicates good results as the coupling factor satisfies the loosely coupled condition, the cohesion factor has a relatively strong relationship, the complexity factor signifies low value, and the reusability factor fulfills the high reusable rate.","PeriodicalId":312644,"journal":{"name":"2022 International Symposium on Information Technology and Digital Innovation (ISITDI)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128377764","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}
Pub Date : 2022-07-27DOI: 10.1109/ISITDI55734.2022.9944401
Adi Nugroho, P. Santosa, Rudy Hartanto
At this time, mobile devices have an important role because it provides changes for users. Not only making calls, but many features and applications are used to make work easier. Mobile application development brings new challenges to mobile devices, such as usability context when users use mobile applications. Usability is an important factor in mobile applications' role in making them easy to use and efficient. User Interface (UI) and User Experience (UX) has a critical role in software development. It has a function that is one of the keys to the effectiveness of using the software. This study aims to find popular usability evaluation on mobile applications with the help of a Systematic Literature Review (SLR). The usability evaluation process of mobile applications is carried out with a systematic literature review of 22 papers. The results show that 73% of the methods used are usability testing, 23% heuristic evaluations, and 4% are user satisfaction usability evaluations. To conduct usability evaluation on mobile applications, usability testing is carried out in five stages, involves participants, and has the characteristics of Effectiveness, Efficiency, and User Satisfaction. Meanwhile, in heuristic evaluation, experts must be involved in evaluating the user interfaces. This study proposes a mixed method of usability testing and heuristic evaluation in conducting usability evaluation on mobile applications. This method is expected to provide effective and objective usability issues from the perspective of users and experts in improving User Interface (UI) and User Experience (UX).
{"title":"Usability Evaluation Methods of Mobile Applications: A Systematic Literature Review","authors":"Adi Nugroho, P. Santosa, Rudy Hartanto","doi":"10.1109/ISITDI55734.2022.9944401","DOIUrl":"https://doi.org/10.1109/ISITDI55734.2022.9944401","url":null,"abstract":"At this time, mobile devices have an important role because it provides changes for users. Not only making calls, but many features and applications are used to make work easier. Mobile application development brings new challenges to mobile devices, such as usability context when users use mobile applications. Usability is an important factor in mobile applications' role in making them easy to use and efficient. User Interface (UI) and User Experience (UX) has a critical role in software development. It has a function that is one of the keys to the effectiveness of using the software. This study aims to find popular usability evaluation on mobile applications with the help of a Systematic Literature Review (SLR). The usability evaluation process of mobile applications is carried out with a systematic literature review of 22 papers. The results show that 73% of the methods used are usability testing, 23% heuristic evaluations, and 4% are user satisfaction usability evaluations. To conduct usability evaluation on mobile applications, usability testing is carried out in five stages, involves participants, and has the characteristics of Effectiveness, Efficiency, and User Satisfaction. Meanwhile, in heuristic evaluation, experts must be involved in evaluating the user interfaces. This study proposes a mixed method of usability testing and heuristic evaluation in conducting usability evaluation on mobile applications. This method is expected to provide effective and objective usability issues from the perspective of users and experts in improving User Interface (UI) and User Experience (UX).","PeriodicalId":312644,"journal":{"name":"2022 International Symposium on Information Technology and Digital Innovation (ISITDI)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127515149","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}
Pub Date : 2022-07-27DOI: 10.1109/ISITDI55734.2022.9944511
Iswan Rina, D. Sulistiowati, Diana RaudhatulOktavi
Subject scheduling is a routine activity carried out by each school before the start of the new school year, so the subject schedule is arranged in such a way, so that there are no identical or conflicting schedules, and no teachers teach at the same time and class. The preparation of the first-semester subject schedule for the 2021/2022 academic year at SMPN 2 Sungai Rumbai, Dharmasraya Regency is one of the problems in graph coloring, this problem will be solved using the Welch-Powell algorithm. This arrangement is done by representing the data in the form of a graph, so that neighboring vertices are obtained. Next, apply the Welch-Powell algorithm to the coloring of graph vertices to obtain chromatic numbers, which means that vertices with the same color can be scheduled together so that the arrangement of the subject schedule can be scheduled on the same day and class.
学科排班是每个学校在新学年开始前进行的一项例行活动，所以学科排班是这样安排的，没有相同或冲突的排班，没有老师同时上课。在准备2021/2022学年的第一学期课程计划时，在Dharmasraya Regency Sungai Rumbai, SMPN 2是图形着色的问题之一，这个问题将使用Welch-Powell算法来解决。这种排列是通过以图的形式表示数据来完成的，以便获得相邻的顶点。接下来，将Welch-Powell算法应用到图顶点的着色上，得到着色数，这意味着可以将颜色相同的顶点安排在一起，从而将主题日程安排在同一天和同一天上课。
{"title":"Graph Coloring Applications in Scheduling Courses using Welch-Powell Algorithm - A Case Study","authors":"Iswan Rina, D. Sulistiowati, Diana RaudhatulOktavi","doi":"10.1109/ISITDI55734.2022.9944511","DOIUrl":"https://doi.org/10.1109/ISITDI55734.2022.9944511","url":null,"abstract":"Subject scheduling is a routine activity carried out by each school before the start of the new school year, so the subject schedule is arranged in such a way, so that there are no identical or conflicting schedules, and no teachers teach at the same time and class. The preparation of the first-semester subject schedule for the 2021/2022 academic year at SMPN 2 Sungai Rumbai, Dharmasraya Regency is one of the problems in graph coloring, this problem will be solved using the Welch-Powell algorithm. This arrangement is done by representing the data in the form of a graph, so that neighboring vertices are obtained. Next, apply the Welch-Powell algorithm to the coloring of graph vertices to obtain chromatic numbers, which means that vertices with the same color can be scheduled together so that the arrangement of the subject schedule can be scheduled on the same day and class.","PeriodicalId":312644,"journal":{"name":"2022 International Symposium on Information Technology and Digital Innovation (ISITDI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122173542","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}
Pub Date : 2022-07-27DOI: 10.1109/ISITDI55734.2022.9944524
Maya Sari Syahrul, Nurweni Putri, Rizki Azmirwan
A mathematical model can describe a problem of spreading of a disease outbreak and can further predict the number of cases for the future. As we have faced COVID-19 outbreak since Desember 2019, the mathematics formula can be used by the authorities to prevent and as well as prepare the spreading of the disease. This paper uses the SEIRV method to simulate the data of COVID-19 in West Sumatera Province. Runge-Kutta 4th Order numeric method was used to simulate the model due to its higher accuracy compared to other numeric methods. The simulation also compares the cases between tha vaccines that available in West Sumatera Province. In conclusion, the simulation has shown that the number of COVID-19 patients has sharply decreased compared to without having the vaccination. Furthermore, moderna and pfizer which are having high efficacy, has been proved in the simulation can sharply decrease COVID-19 cases number compared to sinovac
{"title":"COVID-19 SEIRV Model Simulation In West Sumatera Province Using Runge Kutta 4th Order","authors":"Maya Sari Syahrul, Nurweni Putri, Rizki Azmirwan","doi":"10.1109/ISITDI55734.2022.9944524","DOIUrl":"https://doi.org/10.1109/ISITDI55734.2022.9944524","url":null,"abstract":"A mathematical model can describe a problem of spreading of a disease outbreak and can further predict the number of cases for the future. As we have faced COVID-19 outbreak since Desember 2019, the mathematics formula can be used by the authorities to prevent and as well as prepare the spreading of the disease. This paper uses the SEIRV method to simulate the data of COVID-19 in West Sumatera Province. Runge-Kutta 4th Order numeric method was used to simulate the model due to its higher accuracy compared to other numeric methods. The simulation also compares the cases between tha vaccines that available in West Sumatera Province. In conclusion, the simulation has shown that the number of COVID-19 patients has sharply decreased compared to without having the vaccination. Furthermore, moderna and pfizer which are having high efficacy, has been proved in the simulation can sharply decrease COVID-19 cases number compared to sinovac","PeriodicalId":312644,"journal":{"name":"2022 International Symposium on Information Technology and Digital Innovation (ISITDI)","volume":"13 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130520252","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}
Pub Date : 2022-07-27DOI: 10.1109/ISITDI55734.2022.9944460
Mochamad Yazid Gupron, Umaisaroh Umaisaroh, Agung Wicaksono
The use of command-line interface (CLI) terminals on network equipment such as routers is ubiquitous, however manually inputting commands into CLI terminals is prone to human mistake. Many devices, such as customer edge (CE) routers, are difficult to operate in a multiprotocol label switching-virtual private network (MPLS-VPN) due to manual processes that the user must perform in a CLI terminal. The network automation process in MPLS-VPN networks is difficult due to the large number of routing tables that must be managed. The route leakage approach is described in this study to bypass these limitations and allow the network automation program to be implemented directly to CE routers. The results suggest a small increase in time efficiency of up to 15 seconds and a 40-second increase in time efficiency.
{"title":"Network Automation for CE Router with Route Leaking in MPLS-VPN Network","authors":"Mochamad Yazid Gupron, Umaisaroh Umaisaroh, Agung Wicaksono","doi":"10.1109/ISITDI55734.2022.9944460","DOIUrl":"https://doi.org/10.1109/ISITDI55734.2022.9944460","url":null,"abstract":"The use of command-line interface (CLI) terminals on network equipment such as routers is ubiquitous, however manually inputting commands into CLI terminals is prone to human mistake. Many devices, such as customer edge (CE) routers, are difficult to operate in a multiprotocol label switching-virtual private network (MPLS-VPN) due to manual processes that the user must perform in a CLI terminal. The network automation process in MPLS-VPN networks is difficult due to the large number of routing tables that must be managed. The route leakage approach is described in this study to bypass these limitations and allow the network automation program to be implemented directly to CE routers. The results suggest a small increase in time efficiency of up to 15 seconds and a 40-second increase in time efficiency.","PeriodicalId":312644,"journal":{"name":"2022 International Symposium on Information Technology and Digital Innovation (ISITDI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116707466","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}
Pub Date : 2022-07-27DOI: 10.1109/ISITDI55734.2022.9944502
Rian Ferdian, Tiara Permata Sari
This paper proposes a system that can detect vehicle license plates for motorcycle riders who violate traffic regulations using the YOLO algorithm. This detector will be placed at a traffic light junction. The system has two main video processes: helmet and rearview glass detection and license plate reading. Furthermore, a warning to that specific violator will be sounded through the speaker. The system's three main components are a camera, computing unit, and speaker. This system is built using the YOLO algorithm, Optical Character Recognition (OCR), and Text-to-Speech. For the system to meet real-time requirements, the video data captured by the webcam is sent to a computer device for image processing and identifying motorists who violate traffic without wearing a helmet. Suppose the driver is identified as committing a violation. The OCR system will extract the license plate into text form. Then, the Text-to-Speech system will produce sound output containing license plate information. The data obtained from the system testing shows that the value generated by the YOLO darknet system can detect all categories with an accuracy of 93%. The OCR system for reading the letters and numbers on the license plate has a 95% success rate. The Text-to-Speech system has an accuracy rate of 100%.
{"title":"Identification of Motorcycle Traffic Violations with Deep Learning Method","authors":"Rian Ferdian, Tiara Permata Sari","doi":"10.1109/ISITDI55734.2022.9944502","DOIUrl":"https://doi.org/10.1109/ISITDI55734.2022.9944502","url":null,"abstract":"This paper proposes a system that can detect vehicle license plates for motorcycle riders who violate traffic regulations using the YOLO algorithm. This detector will be placed at a traffic light junction. The system has two main video processes: helmet and rearview glass detection and license plate reading. Furthermore, a warning to that specific violator will be sounded through the speaker. The system's three main components are a camera, computing unit, and speaker. This system is built using the YOLO algorithm, Optical Character Recognition (OCR), and Text-to-Speech. For the system to meet real-time requirements, the video data captured by the webcam is sent to a computer device for image processing and identifying motorists who violate traffic without wearing a helmet. Suppose the driver is identified as committing a violation. The OCR system will extract the license plate into text form. Then, the Text-to-Speech system will produce sound output containing license plate information. The data obtained from the system testing shows that the value generated by the YOLO darknet system can detect all categories with an accuracy of 93%. The OCR system for reading the letters and numbers on the license plate has a 95% success rate. The Text-to-Speech system has an accuracy rate of 100%.","PeriodicalId":312644,"journal":{"name":"2022 International Symposium on Information Technology and Digital Innovation (ISITDI)","volume":"678 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116106913","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}
Pub Date : 2022-07-27DOI: 10.1109/ISITDI55734.2022.9944521
Farrel Octavianus, Albert Wihardi, Muhamad Keenan Ario, Derwin Suhartono
With a large amount of news consumed by the public, it is impossible to digest all the available news. This paper developed an automated text summarization and topic detection algorithm for news articles, allowing the public to read summarized news without losing the essential points of the news. The algorithm will then be used to build and develop a system that has news aggregation technology. First, the system will scrape news articles from various sources, then topic detection and text summarization will be applied to each article before finally being displayed. The methodology used in this research can be divided into data gathering, topic detection, text summarization, and system development. The result of this research shows that the Support Vector Machine performed exceptionally well in topic detection tasks, better than other supervised learning algorithms used in this research, whereas Bidirectional and Auto-Regressive Transformer (BART) with the appropriate parameters performed relatively well in text summarization. To conclude, topic detection and automated text summarization can both be combined and used to develop a news aggregation system, with Support Vector Machine and BART both performing well in their respective tasks.
{"title":"Automated Text Summarization and Topic Detection on News Aggregation System Using BART and SVM","authors":"Farrel Octavianus, Albert Wihardi, Muhamad Keenan Ario, Derwin Suhartono","doi":"10.1109/ISITDI55734.2022.9944521","DOIUrl":"https://doi.org/10.1109/ISITDI55734.2022.9944521","url":null,"abstract":"With a large amount of news consumed by the public, it is impossible to digest all the available news. This paper developed an automated text summarization and topic detection algorithm for news articles, allowing the public to read summarized news without losing the essential points of the news. The algorithm will then be used to build and develop a system that has news aggregation technology. First, the system will scrape news articles from various sources, then topic detection and text summarization will be applied to each article before finally being displayed. The methodology used in this research can be divided into data gathering, topic detection, text summarization, and system development. The result of this research shows that the Support Vector Machine performed exceptionally well in topic detection tasks, better than other supervised learning algorithms used in this research, whereas Bidirectional and Auto-Regressive Transformer (BART) with the appropriate parameters performed relatively well in text summarization. To conclude, topic detection and automated text summarization can both be combined and used to develop a news aggregation system, with Support Vector Machine and BART both performing well in their respective tasks.","PeriodicalId":312644,"journal":{"name":"2022 International Symposium on Information Technology and Digital Innovation (ISITDI)","volume":"202 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116169843","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}
Pub Date : 2022-07-27DOI: 10.1109/ISITDI55734.2022.9944485
D. Sulistiowati, Iswan Rina, Nadia Febrian
The Covid-19 pandemic has changed all aspects of life, including the world of education globally. The learning methods provided are adapted to existing conditions (online learning). This condition has an impact on student learning outcomes. Besides, another factor that affects student learning outcomes is the gender of students, which impacts student behavior in learning. This study aims to see the effect of the learning methods provided (online and offline) and gender differences on the learning outcomes obtained and the interaction of the two factors. The research design used is a two-way multivariate analysis of variance, with the dependent variable (study exam score in Bahasa Indonesia, Mathematics, and natural science subjects). The results showed that the learning method and gender significantly affected test results in all subjects. However, there is no interaction between these two factors.
{"title":"Two-Way Multivariate Analysis of Variance in Comparative Analysis of Study Exam Scores Based on Learning Methods and Student Gender","authors":"D. Sulistiowati, Iswan Rina, Nadia Febrian","doi":"10.1109/ISITDI55734.2022.9944485","DOIUrl":"https://doi.org/10.1109/ISITDI55734.2022.9944485","url":null,"abstract":"The Covid-19 pandemic has changed all aspects of life, including the world of education globally. The learning methods provided are adapted to existing conditions (online learning). This condition has an impact on student learning outcomes. Besides, another factor that affects student learning outcomes is the gender of students, which impacts student behavior in learning. This study aims to see the effect of the learning methods provided (online and offline) and gender differences on the learning outcomes obtained and the interaction of the two factors. The research design used is a two-way multivariate analysis of variance, with the dependent variable (study exam score in Bahasa Indonesia, Mathematics, and natural science subjects). The results showed that the learning method and gender significantly affected test results in all subjects. However, there is no interaction between these two factors.","PeriodicalId":312644,"journal":{"name":"2022 International Symposium on Information Technology and Digital Innovation (ISITDI)","volume":"1 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116792366","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：