Pub Date : 2022-11-14DOI: 10.30595/juita.v10i2.15117
Affi Nizar Suksmawati, Retantyo Wardoyo
The composition of air concentration is not constant. It constantly changes with minor changes at any time, so more than one measurement is needed to represent the air concentration level for a full day. The fuzzy non-stationary method can overcome uncertainty in an environment that is not constant or caused by minor temporal changes based on time variables. This study uses a non-stationary fuzzy method to determine the level of O3 concentration based on the input variables of temperature, humidity, and wind speed. The tests were conducted in September, October, and November using four types of implication process interpretation, namely interpretation 1 (classical logic), interpretation 2 (classical logic), interpretation 3 (algebraic), and interpretation 3 (standard). The test results in September showed a tendency for error percentage using the MAPE amount of 19, October's amount of 25, and November's amount of 18.
{"title":"Prediction of O3 Concentration Level Using Fuzzy Non-Stationary Method","authors":"Affi Nizar Suksmawati, Retantyo Wardoyo","doi":"10.30595/juita.v10i2.15117","DOIUrl":"https://doi.org/10.30595/juita.v10i2.15117","url":null,"abstract":"The composition of air concentration is not constant. It constantly changes with minor changes at any time, so more than one measurement is needed to represent the air concentration level for a full day. The fuzzy non-stationary method can overcome uncertainty in an environment that is not constant or caused by minor temporal changes based on time variables. This study uses a non-stationary fuzzy method to determine the level of O3 concentration based on the input variables of temperature, humidity, and wind speed. The tests were conducted in September, October, and November using four types of implication process interpretation, namely interpretation 1 (classical logic), interpretation 2 (classical logic), interpretation 3 (algebraic), and interpretation 3 (standard). The test results in September showed a tendency for error percentage using the MAPE amount of 19, October's amount of 25, and November's amount of 18.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128521688","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 : 2022-11-14DOI: 10.30595/juita.v10i2.14490
Ahmad Muhariya, I. Riadi, Yudi Prayudi
Social Media, in addition to having a positive impact on society, also has a negative effect. Based on statistics, 95 percent of internet users in Indonesia use the internet to access social networks. Especially for young people, Instagram is more widely used than other social media such as Twitter and Facebook. In terms of cyberbullying cases, cases often occur through social media, Twitter, and Instagram. Several methods are commonly used to analyze cyberbullying cases, such as SVM (Support Vector Machine), NBC (Naïve Bayes Classifier), C45, and K-Nearest Neighbors. Application of a number of these methods is generally implemented on Twitter social media. Meanwhile, young users currently use Instagram more social media than Twitter. For this reason, the research focuses on analyzing cyberbullying on Instagram by applying the K-Mean Clustering algorithm. This algorithm is used to classify cyberbullying actions contained in comments. The dataset used in this study was taken from 2019 to 2021 with 650 records; there were 1827 words and already had labels. This study has successfully classified the tested data with a threshold value of 0.5. The results for grouping words containing bullying on Instagram resulted in the highest accuracy, which is 67.38%, a precision value of 76.70%, and a recall value of 67.48%. These results indicate that the k-means algorithm can make a grouping of comments into two clusters: bullying and non-bullying.
{"title":"Cyberbullying Analysis on Instagram Using K-Means Clustering","authors":"Ahmad Muhariya, I. Riadi, Yudi Prayudi","doi":"10.30595/juita.v10i2.14490","DOIUrl":"https://doi.org/10.30595/juita.v10i2.14490","url":null,"abstract":"Social Media, in addition to having a positive impact on society, also has a negative effect. Based on statistics, 95 percent of internet users in Indonesia use the internet to access social networks. Especially for young people, Instagram is more widely used than other social media such as Twitter and Facebook. In terms of cyberbullying cases, cases often occur through social media, Twitter, and Instagram. Several methods are commonly used to analyze cyberbullying cases, such as SVM (Support Vector Machine), NBC (Naïve Bayes Classifier), C45, and K-Nearest Neighbors. Application of a number of these methods is generally implemented on Twitter social media. Meanwhile, young users currently use Instagram more social media than Twitter. For this reason, the research focuses on analyzing cyberbullying on Instagram by applying the K-Mean Clustering algorithm. This algorithm is used to classify cyberbullying actions contained in comments. The dataset used in this study was taken from 2019 to 2021 with 650 records; there were 1827 words and already had labels. This study has successfully classified the tested data with a threshold value of 0.5. The results for grouping words containing bullying on Instagram resulted in the highest accuracy, which is 67.38%, a precision value of 76.70%, and a recall value of 67.48%. These results indicate that the k-means algorithm can make a grouping of comments into two clusters: bullying and non-bullying.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114669289","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 : 2022-11-14DOI: 10.30595/juita.v10i2.13223
Aditya Salman, Mardhiya Hayaty, Ika Nur Fajri
In face recognition research, detecting several parts of the face becomes a necessary part of the study. The main factor in this work is lighting; some obstacles emerge when the low light's intensity falls in the process of face detection because of some conditions, such as weather, season, and sunlight. This study focuses on detecting faces in dim lighting using the Local Binary Pattern Histogram (LBPH) algorithm assisted by the Classifier Method, which is often used in face detection, namely the Haar Cascade Classifier. Furthermore, It will employ the image enhancement method, namely Histogram Equalization (HE), to improve the image source from the webcam. In the evaluation, different light intensities and various head poses affect the accuracy of the method. As a result, The research reaches 88% accuracy for successful face detection. Some factors such as head accessories, hair covering the face, and several parts of the face, like the eye, mouth, and nose that are invisible, should not be extreme.
{"title":"Facial Images Improvement in the LBPH Algorithm Using the Histogram Equalization Method","authors":"Aditya Salman, Mardhiya Hayaty, Ika Nur Fajri","doi":"10.30595/juita.v10i2.13223","DOIUrl":"https://doi.org/10.30595/juita.v10i2.13223","url":null,"abstract":"In face recognition research, detecting several parts of the face becomes a necessary part of the study. The main factor in this work is lighting; some obstacles emerge when the low light's intensity falls in the process of face detection because of some conditions, such as weather, season, and sunlight. This study focuses on detecting faces in dim lighting using the Local Binary Pattern Histogram (LBPH) algorithm assisted by the Classifier Method, which is often used in face detection, namely the Haar Cascade Classifier. Furthermore, It will employ the image enhancement method, namely Histogram Equalization (HE), to improve the image source from the webcam. In the evaluation, different light intensities and various head poses affect the accuracy of the method. As a result, The research reaches 88% accuracy for successful face detection. Some factors such as head accessories, hair covering the face, and several parts of the face, like the eye, mouth, and nose that are invisible, should not be extreme.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129537190","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 : 2022-11-14DOI: 10.30595/juita.v10i2.14940
W. Andriyani, Lestari Ningsih, I. Sumertajaya, A. Saefuddin
Bi-clustering is a clustering development that aims to group data simultaneously from two directions. The Iterative Signature Algorithm (ISA) is one of the bi-clustering algorithms that work iteratively to find the most correlated bi-cluster. Detecting economic and pandemic vulnerability using bi-cluster analysis is essential to get spatial patterns and an overview of Indonesia's economic and pandemic vulnerability characteristics. Bi-clustering using ISA requires setting the row and column threshold to form seventy combinations of thresholds. The best is chosen based on the average value of mean square residue to volume ratios. In addition, the similarity of the best bi-cluster with the other is also seen based on the Liu and Wang index values. The -1.0 row and -1.0 column threshold combinations were selected and produced the best bi-cluster with the smallest average value of mean square residue to volume ratios (0.00141). Based on Liu and Wang index values, it has more than 95% similarity with the combination of -1.0 row and -0.9 column thresholds and the -0.9 row and -1.0 column thresholds. These selected threshold combinations produce three bi-clusters with five types of spatial patterns and different characteristics because of the overlap between these three bi-clusters.
{"title":"Pattern Detection of Economic and Pandemic Vulnerability Index in Indonesia Using Bi-Cluster Analysis","authors":"W. Andriyani, Lestari Ningsih, I. Sumertajaya, A. Saefuddin","doi":"10.30595/juita.v10i2.14940","DOIUrl":"https://doi.org/10.30595/juita.v10i2.14940","url":null,"abstract":"Bi-clustering is a clustering development that aims to group data simultaneously from two directions. The Iterative Signature Algorithm (ISA) is one of the bi-clustering algorithms that work iteratively to find the most correlated bi-cluster. Detecting economic and pandemic vulnerability using bi-cluster analysis is essential to get spatial patterns and an overview of Indonesia's economic and pandemic vulnerability characteristics. Bi-clustering using ISA requires setting the row and column threshold to form seventy combinations of thresholds. The best is chosen based on the average value of mean square residue to volume ratios. In addition, the similarity of the best bi-cluster with the other is also seen based on the Liu and Wang index values. The -1.0 row and -1.0 column threshold combinations were selected and produced the best bi-cluster with the smallest average value of mean square residue to volume ratios (0.00141). Based on Liu and Wang index values, it has more than 95% similarity with the combination of -1.0 row and -0.9 column thresholds and the -0.9 row and -1.0 column thresholds. These selected threshold combinations produce three bi-clusters with five types of spatial patterns and different characteristics because of the overlap between these three bi-clusters.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"63 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134033684","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 : 2022-11-14DOI: 10.30595/juita.v10i2.13262
M. I. Alfarizi, L. Syafaah, Merinda Lestandy
Humans in carrying out communication activities can express their feelings either verbally or non-verbally. Verbal communication can be in the form of oral or written communication. A person's feelings or emotions can usually be seen by their behavior, tone of voice, and expression. Not everyone can see emotion only through writing, whether in the form of words, sentences, or paragraphs. Therefore, a classification system is needed to help someone determine the emotions contained in a piece of writing. The novelty of this study is a development of previous research using a similar method, namely LSTM but improved on the word weighting process using the TF-IDF method as a further process of LSTM classification. The method proposed in this research is called Natural Language Processing (NLP). The purpose of this study was to compare the classification method with the LSTM (Long Short-Term Memory) model by adding the word weighting TF-IDF (Term Frequency–Inverse Document Frequency) and the LinearSVC model, as well to increase accuracy in determining an emotion (sadness, anger, fear, love, joy, and surprise) contained in the text. The dataset used is 18000, which is divided into 16000 training data and 2000 test data with 6 classifications of emotion classes, namely sadness, anger, fear, love, joy, and surprise. The results of the classification accuracy of emotions using the LSTM method yielded a 97.50% accuracy while using the LinearSVC method resulted in an accuracy value of 89%.
人类在进行交际活动时，既可以用语言表达感情，也可以用非语言表达感情。言语交际可以分为口头和书面两种形式。一个人的感觉或情绪通常可以从他们的行为、语调和表情中看出。不是每个人都能通过文字看到情感，无论是以单词、句子还是段落的形式。因此，需要一个分类系统来帮助人们确定一篇文章中包含的情绪。本研究的新颖之处在于发展了先前的研究，使用了类似的方法，即LSTM，但使用TF-IDF方法改进了单词加权过程，作为LSTM分类的进一步过程。本研究提出的方法被称为自然语言处理(NLP)。本研究的目的是通过添加单词加权TF-IDF (Term Frequency - inverse Document Frequency)和线性svc模型，将该分类方法与LSTM(长短期记忆)模型进行比较，并提高确定文本中包含的情绪(悲伤、愤怒、恐惧、爱、喜悦和惊讶)的准确性。使用的数据集为18000个，分为16000个训练数据和2000个测试数据，分为6类情绪，分别是悲伤、愤怒、恐惧、爱、喜悦、惊喜。使用LSTM方法的情绪分类准确率为97.50%，而使用线性svc方法的准确率为89%。
{"title":"Emotional Text Classification Using TF-IDF (Term Frequency-Inverse Document Frequency) And LSTM (Long Short-Term Memory)","authors":"M. I. Alfarizi, L. Syafaah, Merinda Lestandy","doi":"10.30595/juita.v10i2.13262","DOIUrl":"https://doi.org/10.30595/juita.v10i2.13262","url":null,"abstract":"Humans in carrying out communication activities can express their feelings either verbally or non-verbally. Verbal communication can be in the form of oral or written communication. A person's feelings or emotions can usually be seen by their behavior, tone of voice, and expression. Not everyone can see emotion only through writing, whether in the form of words, sentences, or paragraphs. Therefore, a classification system is needed to help someone determine the emotions contained in a piece of writing. The novelty of this study is a development of previous research using a similar method, namely LSTM but improved on the word weighting process using the TF-IDF method as a further process of LSTM classification. The method proposed in this research is called Natural Language Processing (NLP). The purpose of this study was to compare the classification method with the LSTM (Long Short-Term Memory) model by adding the word weighting TF-IDF (Term Frequency–Inverse Document Frequency) and the LinearSVC model, as well to increase accuracy in determining an emotion (sadness, anger, fear, love, joy, and surprise) contained in the text. The dataset used is 18000, which is divided into 16000 training data and 2000 test data with 6 classifications of emotion classes, namely sadness, anger, fear, love, joy, and surprise. The results of the classification accuracy of emotions using the LSTM method yielded a 97.50% accuracy while using the LinearSVC method resulted in an accuracy value of 89%.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122587677","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 : 2022-11-14DOI: 10.30595/juita.v10i2.15030
Fata Nidaul Khasanah, Sugeng Murdowo, D. Untari, David Nurmanto, Wafi Arifin
Quality research will not be separated from controlling systems that require a review mechanism. This demand considers it necessary to form an assessment committee or reviewer that ensures that all processes proceed towards the target target. The internal reviewer selection process is carried out by looking at several requirements of each prospective reviewer. The selection process is carried out by looking at the requirements files one by one. For this reason, it is necessary to optimize the method that is able to manage the assessment data of prospective reviewers who have the highest rating value from the results of weight calculations. Decision making in determining internal reviewers requires a method that can provide optimal decision results in terms of relatively fast processing time. The decision support method applied in determining internal reviewers is Simple Additive Weighting (SAW). The reason for choosing the SAW method in this study, the method has a basic concept that is used to find weight values on the performance rating of each alternative on all attributes. The SAW method is commonly known as the weighted summation method. There are six criteria used and fifty-five records for alternatives used. The results of the SAW method ranking obtained by A20 have the highest preference value of 0.77. This study shows the optimality of the SAW method in providing decision results based on an accuracy test value of 80%.
{"title":"Optimization of Simple Additive Weighting Method in Assessment of Research Reviewer Selection","authors":"Fata Nidaul Khasanah, Sugeng Murdowo, D. Untari, David Nurmanto, Wafi Arifin","doi":"10.30595/juita.v10i2.15030","DOIUrl":"https://doi.org/10.30595/juita.v10i2.15030","url":null,"abstract":"Quality research will not be separated from controlling systems that require a review mechanism. This demand considers it necessary to form an assessment committee or reviewer that ensures that all processes proceed towards the target target. The internal reviewer selection process is carried out by looking at several requirements of each prospective reviewer. The selection process is carried out by looking at the requirements files one by one. For this reason, it is necessary to optimize the method that is able to manage the assessment data of prospective reviewers who have the highest rating value from the results of weight calculations. Decision making in determining internal reviewers requires a method that can provide optimal decision results in terms of relatively fast processing time. The decision support method applied in determining internal reviewers is Simple Additive Weighting (SAW). The reason for choosing the SAW method in this study, the method has a basic concept that is used to find weight values on the performance rating of each alternative on all attributes. The SAW method is commonly known as the weighted summation method. There are six criteria used and fifty-five records for alternatives used. The results of the SAW method ranking obtained by A20 have the highest preference value of 0.77. This study shows the optimality of the SAW method in providing decision results based on an accuracy test value of 80%.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117218178","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}
Queue management for product certification of perishable goods is a major problem faced by the Surabaya Industrial Standardization and Research Institute (BARISTAND). The purpose of this study is to combine the use of the First in first out (FIFO), First Expired First Out (FEFO) and Least Shelf Life First Out (LSFO) methods into an automatic queuing system that can ensure effective service performance in queue management. This research was conducted using qualitative methods with observations to collect data and processes about how the product certification queue process flow at the Surabaya Industrial Standardization and Research Institute (BARISTRAN). The results show that the service only requires an average service completion time of 0.14 products per minute, meaning that every hour it can serve approximately 8.4 products. The conclusion of the research system has succeeded in determining the queue based on the use of the First in first out (FIFO), First Expired First Out (FEFO) and Least Shelf Life First Out (LSFO) methods, and customers can perform the tracking process to find out the certification process for the registered products.
{"title":"New Selection Algorithm on Priority Service for Certification Queue Service Information System in BARISTRAND","authors":"Rizky Dwi Nugroho, Anjik Sukmaaji, Endra Rahmawati, Arifin Pujiwidodo, Teguh Sutanto","doi":"10.30595/juita.v10i2.13728","DOIUrl":"https://doi.org/10.30595/juita.v10i2.13728","url":null,"abstract":"Queue management for product certification of perishable goods is a major problem faced by the Surabaya Industrial Standardization and Research Institute (BARISTAND). The purpose of this study is to combine the use of the First in first out (FIFO), First Expired First Out (FEFO) and Least Shelf Life First Out (LSFO) methods into an automatic queuing system that can ensure effective service performance in queue management. This research was conducted using qualitative methods with observations to collect data and processes about how the product certification queue process flow at the Surabaya Industrial Standardization and Research Institute (BARISTRAN). The results show that the service only requires an average service completion time of 0.14 products per minute, meaning that every hour it can serve approximately 8.4 products. The conclusion of the research system has succeeded in determining the queue based on the use of the First in first out (FIFO), First Expired First Out (FEFO) and Least Shelf Life First Out (LSFO) methods, and customers can perform the tracking process to find out the certification process for the registered products.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121873688","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 : 2022-11-14DOI: 10.30595/juita.v10i2.13833
Dadang Iskandar Mulyana, Vika Vitaloka Pramansah
Japan has many entertaining and unique artworks, especially its signature animation, called anime. Anime is an animation art that is unique in that the characterizations, characters, and storylines are made to resemble human life. The characters have 2 genders called male and female with unique visuals and are the characteristics of each anime character to entertain the audience. Training large-scale data and complex textures because not all of the anime images owned are of high quality, making classification by Machine Learning Algorithms low in accuracy. This study will describe an experiment using an anime face image dataset to classify the gender, namely male or female. From this problem, this research implements feature extraction to produce unique features of anime images with Gray-Level Cooccurrence Matrix (GLCM) and uses the Random Forest Classifier which is a classification algorithm in Machine Learning to classify gender. The results of this study get a good accuracy value of 95%, using 3,612 images where the test data used is 723 images and Homogeneity5 feature being the most relevant feature in increasing the accuracy value with a value of 0.06378389.
{"title":"Gender Classification for Anime Character Face Image Using Random Forest Classifier Method and GLCM Feature Extraction","authors":"Dadang Iskandar Mulyana, Vika Vitaloka Pramansah","doi":"10.30595/juita.v10i2.13833","DOIUrl":"https://doi.org/10.30595/juita.v10i2.13833","url":null,"abstract":"Japan has many entertaining and unique artworks, especially its signature animation, called anime. Anime is an animation art that is unique in that the characterizations, characters, and storylines are made to resemble human life. The characters have 2 genders called male and female with unique visuals and are the characteristics of each anime character to entertain the audience. Training large-scale data and complex textures because not all of the anime images owned are of high quality, making classification by Machine Learning Algorithms low in accuracy. This study will describe an experiment using an anime face image dataset to classify the gender, namely male or female. From this problem, this research implements feature extraction to produce unique features of anime images with Gray-Level Cooccurrence Matrix (GLCM) and uses the Random Forest Classifier which is a classification algorithm in Machine Learning to classify gender. The results of this study get a good accuracy value of 95%, using 3,612 images where the test data used is 723 images and Homogeneity5 feature being the most relevant feature in increasing the accuracy value with a value of 0.06378389.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128820967","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 : 2022-11-14DOI: 10.30595/juita.v10i2.13500
Theresia Ratih Dewi Saputri, Caecilia Citra Lestari, S. Siahaan
To end the COVID-19 pandemics, the government attempted to accelerate the vaccination through various programs and collaboration. Unfortunately, the number is still relatively small compared to the number of populations in Indonesia. There are some reasons attributed to this challenge, one of them being the reluctance of citizens to accept the COVID-19 vaccine due to various factors. Knowing this factor to increase public compliance, the vaccination program can be speed-up. Unfortunately, traditionally acquiring the knowledge related to COVID-19 vaccine rejection can be challenging. One of the ways to capture the knowledge is by conducting a survey or interview related to COVID-19 vaccine acceptance. This method can be inefficient in terms of cost and resources. To address those problem, we propose a novel method for analyzing the topics related to the COVID-19 Indonesians’ opinions on Twitter by implementing topic modeling algorithm called Latent Dirichlet Allocation. We gathered more than 22000 tweets related to the COVID-19 vaccine. By applying the algorithm to the collected dataset, we can capture the what is general opinion and topic when people discuss about COVID-19 vaccine. The result was validated using the labeled dataset that have been gathered in the previous research. Once we have the important term, the strategy based on can be determined by the medical professional who are responsible to administer the COVID-19 vaccine.
{"title":"What do Indonesians talk when they talk about COVID-19 Vaccine: A Topic Modeling Approach with LDA","authors":"Theresia Ratih Dewi Saputri, Caecilia Citra Lestari, S. Siahaan","doi":"10.30595/juita.v10i2.13500","DOIUrl":"https://doi.org/10.30595/juita.v10i2.13500","url":null,"abstract":"To end the COVID-19 pandemics, the government attempted to accelerate the vaccination through various programs and collaboration. Unfortunately, the number is still relatively small compared to the number of populations in Indonesia. There are some reasons attributed to this challenge, one of them being the reluctance of citizens to accept the COVID-19 vaccine due to various factors. Knowing this factor to increase public compliance, the vaccination program can be speed-up. Unfortunately, traditionally acquiring the knowledge related to COVID-19 vaccine rejection can be challenging. One of the ways to capture the knowledge is by conducting a survey or interview related to COVID-19 vaccine acceptance. This method can be inefficient in terms of cost and resources. To address those problem, we propose a novel method for analyzing the topics related to the COVID-19 Indonesians’ opinions on Twitter by implementing topic modeling algorithm called Latent Dirichlet Allocation. We gathered more than 22000 tweets related to the COVID-19 vaccine. By applying the algorithm to the collected dataset, we can capture the what is general opinion and topic when people discuss about COVID-19 vaccine. The result was validated using the labeled dataset that have been gathered in the previous research. Once we have the important term, the strategy based on can be determined by the medical professional who are responsible to administer the COVID-19 vaccine. ","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121186810","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 : 2022-11-14DOI: 10.30595/juita.v10i2.12308
Aniq Noviciatie Ulfah, M. Anam, Novi Yona, Sidratul Munti, Saleh Yaakub, Muhammad Bambang Firdaus
Coronavirus Disease-19 (Covid-19) is an infectious disease caused by the SARS-CoV-2 virus. The rapid spread of this disease has affected 216 other countries and regions, including Indonesia. In minimizing the spread and increasing losses, it is necessary to have several policies made by the Indonesian government in dealing with this. One of the policies taken by the government is the Convict Assimilation Program to prevent the spread of the virus in prisons. The Prisoner Assimilation Program fosters inmates by integrating prisoners into social life. Many media reported on the assimilation program in various media, including news portals, so that it became a forum for the public to express their opinions. News portals can be a source for getting public opinion. Therefore, sentiment analysis can be done to determine the sentiment of any existing public opinion. In this study, the analysis was carried out by applying one of the data mining methods, namely the Support Vector Machine, with positive, negative, and neutral sentiment labeling. The data used is audience comments in Indonesian with a dataset of 404 comments and then resampled so that the number of data becomes 669. The analysis uses the kernel Radial Basis Function (RBF), RBF with Grid Search, Polynomials, and Polynomials with grid search. Kernel RBF and Kernel Polynomial with Grid Search comparing test and training data 80%:20% with the highest accuracy of 95%.
{"title":"Sentiment Analysis of the Convict Assimilation Program on Handling Covid-19","authors":"Aniq Noviciatie Ulfah, M. Anam, Novi Yona, Sidratul Munti, Saleh Yaakub, Muhammad Bambang Firdaus","doi":"10.30595/juita.v10i2.12308","DOIUrl":"https://doi.org/10.30595/juita.v10i2.12308","url":null,"abstract":"Coronavirus Disease-19 (Covid-19) is an infectious disease caused by the SARS-CoV-2 virus. The rapid spread of this disease has affected 216 other countries and regions, including Indonesia. In minimizing the spread and increasing losses, it is necessary to have several policies made by the Indonesian government in dealing with this. One of the policies taken by the government is the Convict Assimilation Program to prevent the spread of the virus in prisons. The Prisoner Assimilation Program fosters inmates by integrating prisoners into social life. Many media reported on the assimilation program in various media, including news portals, so that it became a forum for the public to express their opinions. News portals can be a source for getting public opinion. Therefore, sentiment analysis can be done to determine the sentiment of any existing public opinion. In this study, the analysis was carried out by applying one of the data mining methods, namely the Support Vector Machine, with positive, negative, and neutral sentiment labeling. The data used is audience comments in Indonesian with a dataset of 404 comments and then resampled so that the number of data becomes 669. The analysis uses the kernel Radial Basis Function (RBF), RBF with Grid Search, Polynomials, and Polynomials with grid search. Kernel RBF and Kernel Polynomial with Grid Search comparing test and training data 80%:20% with the highest accuracy of 95%.","PeriodicalId":151254,"journal":{"name":"JUITA : Jurnal Informatika","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123437972","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：