Pub Date : 2023-08-16DOI: 10.33096/ilkom.v15i2.1561.365-372
Ihwana As'ad, Muhammad Arfah Asis, Hariani Ma'tang Pakka, Randi Mursalim, Yusnita binti Muhamad Noor
In order to prevent the spread of COVID-19 in Indonesia, the Government of the Republic of Indonesia has been implementing a booster vaccine program since January 12th, 2022, with priority for the elderly and vulnerable groups as well as those who got the second C-19 vaccine longer than 6 months. The implementation of this program raised many pros and cons among public which were expressed either positively or negatively through social media. Therefore, sentiment analysis is needed to examine these phenomenons. This study aims to determine the positive and negative response from public by employing K-Nearest Neighbor method. A total of 2,000 commentary data were collected to be in turn classified based on positive and negative sentiments. There are 500 comments used as training data and divided equally to positive and negative class, each consists of 250 data. Using the value of K = 9, the results show a positive sentiment of 43% while a negative sentiment of 57%. Based on the validity test using 10-fold cross validation, an accuracy of 82.60% was obtained, a recall value was 82.60% with a precision of 83.89%.
{"title":"K-Nearest Neighbors Analysis for Public Sentiment towards Implementation of Booster Vaccines in Indonesia","authors":"Ihwana As'ad, Muhammad Arfah Asis, Hariani Ma'tang Pakka, Randi Mursalim, Yusnita binti Muhamad Noor","doi":"10.33096/ilkom.v15i2.1561.365-372","DOIUrl":"https://doi.org/10.33096/ilkom.v15i2.1561.365-372","url":null,"abstract":"In order to prevent the spread of COVID-19 in Indonesia, the Government of the Republic of Indonesia has been implementing a booster vaccine program since January 12th, 2022, with priority for the elderly and vulnerable groups as well as those who got the second C-19 vaccine longer than 6 months. The implementation of this program raised many pros and cons among public which were expressed either positively or negatively through social media. Therefore, sentiment analysis is needed to examine these phenomenons. This study aims to determine the positive and negative response from public by employing K-Nearest Neighbor method. A total of 2,000 commentary data were collected to be in turn classified based on positive and negative sentiments. There are 500 comments used as training data and divided equally to positive and negative class, each consists of 250 data. Using the value of K = 9, the results show a positive sentiment of 43% while a negative sentiment of 57%. Based on the validity test using 10-fold cross validation, an accuracy of 82.60% was obtained, a recall value was 82.60% with a precision of 83.89%.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135021648","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 : 2023-08-16DOI: 10.33096/ilkom.v15i2.1510.215-221
Mohamad Jamil, Budi Warsito, Adi Wibowo, Kiswanto Kiswanto
Diabetes Mellitus is a genetically and clinically heterogeneous metabolic disorder with manifestations of loss of carbohydrate tolerance characterized by high blood glucose levels as a result of insulin insufficiency. Public knowledge of diabetes mellitus 39.30% is influenced by public health education and information about diabetes mellitus that the public has ever received. Early detection of diabetes mellitus can prevent the development of chronic complications and allow timely and rapid treatment. The aim of this study is to simulate the early detection of diabetes mellitus with the K-Nearest Neighbors (K-NN) algorithm using Cloud-Base Runtime (COLAB). The highest accuracy is 76% in K=3, the highest precision is 68% in K=3 and the highest recall is 60% in K=3. The researchers used K-NN as a method to classify data from the Pima Indians Diabetes Database and obtained a fairly good accuracy value of 76% with a value of k = 3.
{"title":"Diabetes Mellitus Early Detection Simulation using The K-Nearest Neighbors Algorithm with Cloud-Based Runtime (COLAB)","authors":"Mohamad Jamil, Budi Warsito, Adi Wibowo, Kiswanto Kiswanto","doi":"10.33096/ilkom.v15i2.1510.215-221","DOIUrl":"https://doi.org/10.33096/ilkom.v15i2.1510.215-221","url":null,"abstract":"Diabetes Mellitus is a genetically and clinically heterogeneous metabolic disorder with manifestations of loss of carbohydrate tolerance characterized by high blood glucose levels as a result of insulin insufficiency. Public knowledge of diabetes mellitus 39.30% is influenced by public health education and information about diabetes mellitus that the public has ever received. Early detection of diabetes mellitus can prevent the development of chronic complications and allow timely and rapid treatment. The aim of this study is to simulate the early detection of diabetes mellitus with the K-Nearest Neighbors (K-NN) algorithm using Cloud-Base Runtime (COLAB). The highest accuracy is 76% in K=3, the highest precision is 68% in K=3 and the highest recall is 60% in K=3. The researchers used K-NN as a method to classify data from the Pima Indians Diabetes Database and obtained a fairly good accuracy value of 76% with a value of k = 3.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135021650","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 : 2023-08-16DOI: 10.33096/ilkom.v15i2.1676.373-381
Edi Priyanto, Enny Itje Sela, Luther Alexander Latumakulita, Noourul Islam
Nowadays, information technology especially machine learning has been used to evaluate the feasibility of debtors. One of the challenges in this classification model is the occurrence of imbalanced datasets, especially in the German Credit Dataset. Another challenge is developing an optimal model for evaluating debtor eligibility. Based on these challenges, this study aims to develop an optimal model for evaluating debtor eligibility on the German Credit Dataset, using the decision trees, k-Nearest Neighbor (k-NN) and Synthetic Minority Oversampling Technique (SMOTE). SMOTE and k-NN is used to overcome challenges regarding imbalanced datasets. While the decision tree are applied to produce a debtor classification model. In general, the steps taken are preparing datasets, pre-processing data, dividing datasets, oversampling with SMOTE, and classification models using decision trees, and testing. Model performance evaluation is represented by accuracy values obtained from the confusion matrix and area under curve (AUC) values generated by the Receiver Operating Characteristic (ROC). Based on the tests that have been carried out, the best accuracy value in the test is obtained at 73.00% and the AUC value is 0.708, in parameters k = 3 and Max-Depth = 25. Based on the analysis produced, the proposed model can improve performance compared to if the dataset is not applied SMOTE.
{"title":"Decision Tree C4.5 Performance Improvement using Synthetic Minority Oversampling Technique (SMOTE) and K-Nearest Neighbor for Debtor Eligibility Evaluation","authors":"Edi Priyanto, Enny Itje Sela, Luther Alexander Latumakulita, Noourul Islam","doi":"10.33096/ilkom.v15i2.1676.373-381","DOIUrl":"https://doi.org/10.33096/ilkom.v15i2.1676.373-381","url":null,"abstract":"Nowadays, information technology especially machine learning has been used to evaluate the feasibility of debtors. One of the challenges in this classification model is the occurrence of imbalanced datasets, especially in the German Credit Dataset. Another challenge is developing an optimal model for evaluating debtor eligibility. Based on these challenges, this study aims to develop an optimal model for evaluating debtor eligibility on the German Credit Dataset, using the decision trees, k-Nearest Neighbor (k-NN) and Synthetic Minority Oversampling Technique (SMOTE). SMOTE and k-NN is used to overcome challenges regarding imbalanced datasets. While the decision tree are applied to produce a debtor classification model. In general, the steps taken are preparing datasets, pre-processing data, dividing datasets, oversampling with SMOTE, and classification models using decision trees, and testing. Model performance evaluation is represented by accuracy values obtained from the confusion matrix and area under curve (AUC) values generated by the Receiver Operating Characteristic (ROC). Based on the tests that have been carried out, the best accuracy value in the test is obtained at 73.00% and the AUC value is 0.708, in parameters k = 3 and Max-Depth = 25. Based on the analysis produced, the proposed model can improve performance compared to if the dataset is not applied SMOTE.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135021652","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 : 2023-08-16DOI: 10.33096/ilkom.v15i2.1692.358-364
Lilis Nur Hayati, Anik Nur Handayani, Wahyu Sakti Gunawan Irianto, Rosa Andrie Asmara, Dolly Indra, Muhammad Fahmi
Indonesian Sign Language (BISINDO) is one of the sign languages used in Indonesia. The process of classifying BISINDO can be done by utilizing advances in computer technology such as deep learning. The use of the BISINDO letter classification system with the application of the MobileNet V2 FPNLite SSD model using the TensorFlow object detection API. The purpose of this study is to classify BISINDO letters A-Z and measure the accuracy, precision, recall, and cross-validation performance of the model. The dataset used was 4054 images with a size of consisting of 26 letter classes, which were taken by researchers by applying several research scenarios and limitations. The steps carried out are: dividing the ratio of the simulation dataset 80:20, and applying cross-validation (k-fold = 5). In this study, a real time testing using 2 scenarios was conducted, namely testing with bright light conditions of 500 lux and dim light of 50 lux with an average processing time of 30 frames per second (fps). With a simulation data set ratio of 80:20, 5 iterations were performed, the first iteration yielded a precision result of 0.758 and a recall result of 0.790, and the second iteration yielded a precision result of 0.635 and a recall result of 0.77, then obtained an accuracy score of 0.712, the third iteration provides a recall score of 0.746, the fourth iteration obtains a precision score of 0.713 and a recall score of 0.751, the fifth iteration gives a precision score of 0.742 for a fit score case and the recall score is 0.773. So, the overall average precision score is 0.712 and the overall average recall score is 0.747, indicating that the model built performs very well.
{"title":"Classifying BISINDO Alphabet using TensorFlow Object Detection API","authors":"Lilis Nur Hayati, Anik Nur Handayani, Wahyu Sakti Gunawan Irianto, Rosa Andrie Asmara, Dolly Indra, Muhammad Fahmi","doi":"10.33096/ilkom.v15i2.1692.358-364","DOIUrl":"https://doi.org/10.33096/ilkom.v15i2.1692.358-364","url":null,"abstract":"Indonesian Sign Language (BISINDO) is one of the sign languages used in Indonesia. The process of classifying BISINDO can be done by utilizing advances in computer technology such as deep learning. The use of the BISINDO letter classification system with the application of the MobileNet V2 FPNLite SSD model using the TensorFlow object detection API. The purpose of this study is to classify BISINDO letters A-Z and measure the accuracy, precision, recall, and cross-validation performance of the model. The dataset used was 4054 images with a size of consisting of 26 letter classes, which were taken by researchers by applying several research scenarios and limitations. The steps carried out are: dividing the ratio of the simulation dataset 80:20, and applying cross-validation (k-fold = 5). In this study, a real time testing using 2 scenarios was conducted, namely testing with bright light conditions of 500 lux and dim light of 50 lux with an average processing time of 30 frames per second (fps). With a simulation data set ratio of 80:20, 5 iterations were performed, the first iteration yielded a precision result of 0.758 and a recall result of 0.790, and the second iteration yielded a precision result of 0.635 and a recall result of 0.77, then obtained an accuracy score of 0.712, the third iteration provides a recall score of 0.746, the fourth iteration obtains a precision score of 0.713 and a recall score of 0.751, the fifth iteration gives a precision score of 0.742 for a fit score case and the recall score is 0.773. So, the overall average precision score is 0.712 and the overall average recall score is 0.747, indicating that the model built performs very well.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135021654","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 : 2023-08-16DOI: 10.33096/ilkom.v15i2.1558.283-289
Bayu Aji, Sutikno Sutikno
The industrial world has been increasingly using robots for production purposes. One type of robot used is a line follower robot for the purposes of transportation of production materials. Various researches and competitions of line follower robots were held to improve its performance. This study proposed a fuzzy logic algorithm using Sugeno method for a line follower mobile robot. This algorithm received input from the readings of 8 sensors mounted on the bottom of the robot and generated the speed of each left and right motor. This speed was used to keep the robot on track. The performance of this algorithm was compared with the fuzzy logic algorithm of the Mamdani method. The proposed fuzzy logic algorithm was better in terms of speed. The results of this study can be used as material to study the application of fuzzy logic algorithm in real time.
{"title":"Fuzzy Logic Algorithm of Sugeno Method for Controlling Line Follower Mobile Robot","authors":"Bayu Aji, Sutikno Sutikno","doi":"10.33096/ilkom.v15i2.1558.283-289","DOIUrl":"https://doi.org/10.33096/ilkom.v15i2.1558.283-289","url":null,"abstract":"The industrial world has been increasingly using robots for production purposes. One type of robot used is a line follower robot for the purposes of transportation of production materials. Various researches and competitions of line follower robots were held to improve its performance. This study proposed a fuzzy logic algorithm using Sugeno method for a line follower mobile robot. This algorithm received input from the readings of 8 sensors mounted on the bottom of the robot and generated the speed of each left and right motor. This speed was used to keep the robot on track. The performance of this algorithm was compared with the fuzzy logic algorithm of the Mamdani method. The proposed fuzzy logic algorithm was better in terms of speed. The results of this study can be used as material to study the application of fuzzy logic algorithm in real time.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135021656","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 : 2023-08-16DOI: 10.33096/ilkom.v15i2.1234.240-249
Aris Martono, Henderi Henderi, Giandari Maulani
This study aims to measure the prediction of survival of covid-19 patients with the best algorithm based on RMSE(Root Mean Square Error). The Covid-19 pandemic has lasted from December 2019 until now and is full of uncertainty about when this pandemic will end, so this research was carried out. In this study, the knowledge discovery database method was used by extracting data sets from Covid-19 patients from March 2020 to March 2021 for each province in Indonesia (Dataset from Kawal Covid-19 SintaRistekbrin) to predict survival during this pandemic as measured by the best algorithms include k-NN (k-Nearest Neighbor), SVM (Support Vector Machine), and/or Deep Learning. The measurement results using cross-validation and the optimal number of folds is 3 in the form of RSME, showing that the k-NN algorithm is an algorithm with RSME 0.101 +/-0.23 where the error rate is the lowest compared to the two algorithms above. Therefore, the k-NN algorithm was chosen as the algorithm for the predictive measurement of surviving Covid-19 patients.
{"title":"The Effect of The Prediction of The K-Nearest Neighbor Algorithm on Surviving COVID-19 Patients in Indonesia","authors":"Aris Martono, Henderi Henderi, Giandari Maulani","doi":"10.33096/ilkom.v15i2.1234.240-249","DOIUrl":"https://doi.org/10.33096/ilkom.v15i2.1234.240-249","url":null,"abstract":"This study aims to measure the prediction of survival of covid-19 patients with the best algorithm based on RMSE(Root Mean Square Error). The Covid-19 pandemic has lasted from December 2019 until now and is full of uncertainty about when this pandemic will end, so this research was carried out. In this study, the knowledge discovery database method was used by extracting data sets from Covid-19 patients from March 2020 to March 2021 for each province in Indonesia (Dataset from Kawal Covid-19 SintaRistekbrin) to predict survival during this pandemic as measured by the best algorithms include k-NN (k-Nearest Neighbor), SVM (Support Vector Machine), and/or Deep Learning. The measurement results using cross-validation and the optimal number of folds is 3 in the form of RSME, showing that the k-NN algorithm is an algorithm with RSME 0.101 +/-0.23 where the error rate is the lowest compared to the two algorithms above. Therefore, the k-NN algorithm was chosen as the algorithm for the predictive measurement of surviving Covid-19 patients.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135021657","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}
Indonesia is a tropical country with a diverse range of plants that ancient people used for traditional medicines. However, the similarity in shape of the leaves became an obstacle to distinguishing them. Therefore, technological advancements are expected to help identify the herbal leaves to use them right on target according to their efficacy. In this research, image classification of katuk (Sauropus Androgynus) and kelor (Moringa Oleifera) leaves is applied using 3 different algorithms i.e hybrid of Gray Level Co-Occurrence Matrix (GLCM) feature extraction and Support Vector Machine (SVM) implementing 4 kernels namely linear, RBF, polynomial, and sigmoid; hybrid of GLCM and Convolutional Neural Network (CNN); and pure CNN. A dataset of 480 images has been collected with 2 different scenarios, including bright and dark intensities. Based on the result, a hybrid of GLCM and SVM showed the highest accuracy of 96% in the dark intensity test using a linear kernel, while sigmoid obtained the lowest accuracy of 35%. On the other hand, it has been discovered that CNN obtained the highest performance in the bright intensity test with an accuracy of 98%. While in the dark intensity test, a hybrid of GLCM and CNN is superior, obtaining 96% accuracy. In conclusion, CNN is more powerful for image classification with bright intensity. For dark intensity images, both the hybrid of GLCM+SVM (linear) and the hybrid of GLCM+CNN are fairly recommended.
{"title":"Comparative Study of Herbal Leaves Classification using Hybrid of GLCM-SVM and GLCM-CNN","authors":"Purnawansyah Purnawansyah, Aji Prasetya Wibawa, Triyanna Widyaningtyas, Haviluddin Haviluddin, Cholisah Erman Hasihi, Ming Foey Teng, Herdianti Darwis","doi":"10.33096/ilkom.v15i2.1759.382-389","DOIUrl":"https://doi.org/10.33096/ilkom.v15i2.1759.382-389","url":null,"abstract":"Indonesia is a tropical country with a diverse range of plants that ancient people used for traditional medicines. However, the similarity in shape of the leaves became an obstacle to distinguishing them. Therefore, technological advancements are expected to help identify the herbal leaves to use them right on target according to their efficacy. In this research, image classification of katuk (Sauropus Androgynus) and kelor (Moringa Oleifera) leaves is applied using 3 different algorithms i.e hybrid of Gray Level Co-Occurrence Matrix (GLCM) feature extraction and Support Vector Machine (SVM) implementing 4 kernels namely linear, RBF, polynomial, and sigmoid; hybrid of GLCM and Convolutional Neural Network (CNN); and pure CNN. A dataset of 480 images has been collected with 2 different scenarios, including bright and dark intensities. Based on the result, a hybrid of GLCM and SVM showed the highest accuracy of 96% in the dark intensity test using a linear kernel, while sigmoid obtained the lowest accuracy of 35%. On the other hand, it has been discovered that CNN obtained the highest performance in the bright intensity test with an accuracy of 98%. While in the dark intensity test, a hybrid of GLCM and CNN is superior, obtaining 96% accuracy. In conclusion, CNN is more powerful for image classification with bright intensity. For dark intensity images, both the hybrid of GLCM+SVM (linear) and the hybrid of GLCM+CNN are fairly recommended.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135021651","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 : 2023-08-16DOI: 10.33096/ilkom.v15i2.1529.222-228
Sasa Ani Arnomo, Yulia Yulia, Ukas Ukas
To get a large profit in a company or business is to determine sales predictions for the next period. Prediction or forecasting is one of the keys to the success of sales because the predicted value of sales can be used as a reference to determine the order of goods, so there is no loss. Exponential smoothing method is a fairly superior forecasting method in long-term, medium-term and short-term forecasting. The data to be processed is sales data for the 2020-2022 period. The single exponential smoothing method was chosen because it can determine sales predictions for the next period with the smallest error value. The evaluation method used is MAPE, ME, MAD and MSE where this forecasting method is used to find the smallest error value. Based on the calculation results, the smallest error value obtained is ME at 62.8, MAD at 179.9, MSE at 55564.5, and MAPE at 9.20%. The value is at alpha 0.3. The next stage is to design a prediction system using the out-systems platform version 11.14.1 as a place to design the system. The test results of the system that has been designed to assist business owners in making decisions on product inventory estimates.
{"title":"Building The Prediction of Sales Evaluation on Exponential Smoothing using The OutSystems Platform","authors":"Sasa Ani Arnomo, Yulia Yulia, Ukas Ukas","doi":"10.33096/ilkom.v15i2.1529.222-228","DOIUrl":"https://doi.org/10.33096/ilkom.v15i2.1529.222-228","url":null,"abstract":"To get a large profit in a company or business is to determine sales predictions for the next period. Prediction or forecasting is one of the keys to the success of sales because the predicted value of sales can be used as a reference to determine the order of goods, so there is no loss. Exponential smoothing method is a fairly superior forecasting method in long-term, medium-term and short-term forecasting. The data to be processed is sales data for the 2020-2022 period. The single exponential smoothing method was chosen because it can determine sales predictions for the next period with the smallest error value. The evaluation method used is MAPE, ME, MAD and MSE where this forecasting method is used to find the smallest error value. Based on the calculation results, the smallest error value obtained is ME at 62.8, MAD at 179.9, MSE at 55564.5, and MAPE at 9.20%. The value is at alpha 0.3. The next stage is to design a prediction system using the out-systems platform version 11.14.1 as a place to design the system. The test results of the system that has been designed to assist business owners in making decisions on product inventory estimates.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135021653","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 : 2023-08-16DOI: 10.33096/ilkom.v15i2.1590.290-302
M. Khairul Anam, Triyani Arita Fitri, Agustin Agustin, Lusiana Lusiana, Muhammad Bambang Firdaus, Agus Tri Nurhuda
The pros and cons regarding online learning has been a hot topic in society, both on social media and in the real world. Indonesian netizens still post opinions about online learning on social media such as Twitter. This study aims to analyze public comments to determine whether the trend of the comments is positive, negative, or neutral. The classification of netizen opinions is called sentiment analysis. This study applies 2 ways of carrying out sentiment analysis. The first stage employs the SVM algorithm with data labeling automatically obtained from the Emprit Academy drone portal while the second stage is still using the SVM algorithm but the data labeling with lexicon-based method. The results of this study are comparisons of labels obtained automatically from the Emprit Academy drone portal and labeling using lexicon based. The SVM algorithm obtains an accuracy of 90%, while the use of lexicon-based increases the accuracy value by 5% to 95%. It can be concluded that labeling data using a lexicon-based method can improve the accuracy of the SVM algorithm.
{"title":"Sentiment Analysis for Online Learning using The Lexicon-Based Method and The Support Vector Machine Algorithm","authors":"M. Khairul Anam, Triyani Arita Fitri, Agustin Agustin, Lusiana Lusiana, Muhammad Bambang Firdaus, Agus Tri Nurhuda","doi":"10.33096/ilkom.v15i2.1590.290-302","DOIUrl":"https://doi.org/10.33096/ilkom.v15i2.1590.290-302","url":null,"abstract":"The pros and cons regarding online learning has been a hot topic in society, both on social media and in the real world. Indonesian netizens still post opinions about online learning on social media such as Twitter. This study aims to analyze public comments to determine whether the trend of the comments is positive, negative, or neutral. The classification of netizen opinions is called sentiment analysis. This study applies 2 ways of carrying out sentiment analysis. The first stage employs the SVM algorithm with data labeling automatically obtained from the Emprit Academy drone portal while the second stage is still using the SVM algorithm but the data labeling with lexicon-based method. The results of this study are comparisons of labels obtained automatically from the Emprit Academy drone portal and labeling using lexicon based. The SVM algorithm obtains an accuracy of 90%, while the use of lexicon-based increases the accuracy value by 5% to 95%. It can be concluded that labeling data using a lexicon-based method can improve the accuracy of the SVM algorithm.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135023336","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}
One crucial issue affecting the performance of sentiment analysis tasks is negation. Handling negation involves determining the negation scope and negation cue. Feature space augmentation is one approach used to address negation. Feature space augmentation has been carried out by some previous researchers using a negation flag with the rule that the negation scope includes all words from the explicit negation cue to the punctuation mark. This study aimed to analyze the classifier's performance when negation handling was applied by adding a new rule for the negation scope. The new rule for determining the negation scope no longer took all words from the negation cue to the punctuation mark, but only considered or ignored words with certain POS tags. The results of this study showed that using the new rule for negation scope contributed to improving the performance of the classifier in sentiment analysis tasks. The proposed approach for negation handling was better than the previous approach in terms of accuracy, precision, recall, and f1-score.
{"title":"Feature Space Augmentation for Negation Handling on Sentiment Analysis","authors":"Lutfi Budi Ilmawan, Muladi Muladi, Didik Dwi Prasetya","doi":"10.33096/ilkom.v15i2.1695.353-357","DOIUrl":"https://doi.org/10.33096/ilkom.v15i2.1695.353-357","url":null,"abstract":"One crucial issue affecting the performance of sentiment analysis tasks is negation. Handling negation involves determining the negation scope and negation cue. Feature space augmentation is one approach used to address negation. Feature space augmentation has been carried out by some previous researchers using a negation flag with the rule that the negation scope includes all words from the explicit negation cue to the punctuation mark. This study aimed to analyze the classifier's performance when negation handling was applied by adding a new rule for the negation scope. The new rule for determining the negation scope no longer took all words from the negation cue to the punctuation mark, but only considered or ignored words with certain POS tags. The results of this study showed that using the new rule for negation scope contributed to improving the performance of the classifier in sentiment analysis tasks. The proposed approach for negation handling was better than the previous approach in terms of accuracy, precision, recall, and f1-score.","PeriodicalId":33690,"journal":{"name":"Ilkom Jurnal Ilmiah","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135021649","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：