Pub Date : 2018-10-01DOI: 10.1109/EECSI.2018.8752821
M. H. Abu Yazid, Muhammad Haikal Satria, Shukor Talib, Novi Azman
Heart Disease are among the leading cause of death worldwide. The application of artificial neural network as decision support tool for heart disease detection. However, artificial neural network required multitude of parameter setting in order to find the optimum parameter setting that produce the best performance. This paper proposed the parameter tuning framework for artificial neural network. Statlog heart disease dataset and Cleveland heart disease dataset is used to evaluate the performance of the proposed framework. The results show that the proposed framework able to produce high classification accuracy where the overall classification accuracy for Cleveland dataset is 90.9% and 90% for Statlog dataset.
{"title":"Artificial Neural Network Parameter Tuning Framework For Heart Disease Classification","authors":"M. H. Abu Yazid, Muhammad Haikal Satria, Shukor Talib, Novi Azman","doi":"10.1109/EECSI.2018.8752821","DOIUrl":"https://doi.org/10.1109/EECSI.2018.8752821","url":null,"abstract":"Heart Disease are among the leading cause of death worldwide. The application of artificial neural network as decision support tool for heart disease detection. However, artificial neural network required multitude of parameter setting in order to find the optimum parameter setting that produce the best performance. This paper proposed the parameter tuning framework for artificial neural network. Statlog heart disease dataset and Cleveland heart disease dataset is used to evaluate the performance of the proposed framework. The results show that the proposed framework able to produce high classification accuracy where the overall classification accuracy for Cleveland dataset is 90.9% and 90% for Statlog dataset.","PeriodicalId":6543,"journal":{"name":"2018 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"31 2 1","pages":"674-679"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77319755","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 : 2018-10-01DOI: 10.1109/EECSI.2018.8752894
A. Wijaya, T. B. Adji, Noor Akhmad Setiawan
Achieving consistent accuracy still big challenge in EEG based Motor Imagery classification since the nature of EEG signal is non-stationary, intra-subject and inter-subject dependent. To address this problems, we propose the feature extraction scheme employing statistical measurements in narrow window with channel instantiation approach. In this study, k-Nearest Neighbor is used and a voting scheme as final decision where the most detection in certain class will be a winner. In this channel instantiation scheme, where EEG channel become instance or record, seventeen EEG channels with motor related activity is used to reduce from 118 channels. We investigate five narrow windows combination in the proposed methods, i.e.: one, two, three, four and five windows. BCI competition III Dataset IVa is used to evaluate our proposed methods. Experimental results show that one window with all channel and a combination of five windows with reduced channel outperform all prior research with highest accuracy and lowest standard deviation. This results indicate that our proposed methods achieve consistent accuracy and promising for reliable BCI systems.
{"title":"Narrow Window Feature Extraction for EEG-Motor Imagery Classification using k-NN and Voting Scheme","authors":"A. Wijaya, T. B. Adji, Noor Akhmad Setiawan","doi":"10.1109/EECSI.2018.8752894","DOIUrl":"https://doi.org/10.1109/EECSI.2018.8752894","url":null,"abstract":"Achieving consistent accuracy still big challenge in EEG based Motor Imagery classification since the nature of EEG signal is non-stationary, intra-subject and inter-subject dependent. To address this problems, we propose the feature extraction scheme employing statistical measurements in narrow window with channel instantiation approach. In this study, k-Nearest Neighbor is used and a voting scheme as final decision where the most detection in certain class will be a winner. In this channel instantiation scheme, where EEG channel become instance or record, seventeen EEG channels with motor related activity is used to reduce from 118 channels. We investigate five narrow windows combination in the proposed methods, i.e.: one, two, three, four and five windows. BCI competition III Dataset IVa is used to evaluate our proposed methods. Experimental results show that one window with all channel and a combination of five windows with reduced channel outperform all prior research with highest accuracy and lowest standard deviation. This results indicate that our proposed methods achieve consistent accuracy and promising for reliable BCI systems.","PeriodicalId":6543,"journal":{"name":"2018 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"190 1","pages":"167-172"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76807698","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 : 2018-10-01DOI: 10.1109/EECSI.2018.8752624
Novi Azman, M. H. Satria, Muhammad Zillullah Mukaram, Mohd Khanapi Abd Ghani
Insomnia is a common health problem in medical field as well as in psychiatry. The measurement of those factors could be collected by using polysomnography as one of the current standards. However, due to the routine of clinical assessment, the polysomnography is impractical and limited to be used in certain place. The rapid progress of electronic sensors to support IoT in health telemonitoring should provide the real time diagnosis of patient at home too. In this research, the development of centralized insomnia system for recording and analysis of patient with chronic-insomnia data is proposed. The system is composed from multi body sensors that connected to main IOT server. The test has been done for 5 patients and the result has been successfully retrieved in real time.
{"title":"Development of Embedded System for Centralized Insomnia System","authors":"Novi Azman, M. H. Satria, Muhammad Zillullah Mukaram, Mohd Khanapi Abd Ghani","doi":"10.1109/EECSI.2018.8752624","DOIUrl":"https://doi.org/10.1109/EECSI.2018.8752624","url":null,"abstract":"Insomnia is a common health problem in medical field as well as in psychiatry. The measurement of those factors could be collected by using polysomnography as one of the current standards. However, due to the routine of clinical assessment, the polysomnography is impractical and limited to be used in certain place. The rapid progress of electronic sensors to support IoT in health telemonitoring should provide the real time diagnosis of patient at home too. In this research, the development of centralized insomnia system for recording and analysis of patient with chronic-insomnia data is proposed. The system is composed from multi body sensors that connected to main IOT server. The test has been done for 5 patients and the result has been successfully retrieved in real time.","PeriodicalId":6543,"journal":{"name":"2018 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"45 1","pages":"451-455"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79756157","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 : 2018-10-01DOI: 10.1109/EECSI.2018.8752723
Haposan Yoga, Pradika Napitupulu, C. G. Irianto
Due to harmonics problems generated by converter devices. Currently, passive filter has been widely used in suppressing harmonics distortion. Passive filter which mostly used is double tuned filter. However, double tuned filter doesn't have a damping resistor which can prevent network elements from exposing to harsh condition such as when the system reactance and the filter impedance are conjugated, this condition can cause severe overvoltage harmonics on the filter and other power system components. There is a new configuration of double tuned filter that has damping resistor, called damped-type double tuned filter. Aiming at the question of parameter of damped-type double tuned filter, a new algorithm for designing the parameter of damped-type double tuned filter is proposed based on the relationship between impedance of two single tuned filter and one double tuned filter, and also based on the resonance at tuned frequency one and tuned frequency two are close to zero. Simulation result from MATLAB shows that the impedance of damped-type double tuned filter designed with this algorithm is appropriate. In addition, the simulation result from PSIM shows that damped-type double tuned filter designed with this algorithm works well.
{"title":"A New Algorithm for Designing the Parameter of Damped-Type Double Tuned Filter","authors":"Haposan Yoga, Pradika Napitupulu, C. G. Irianto","doi":"10.1109/EECSI.2018.8752723","DOIUrl":"https://doi.org/10.1109/EECSI.2018.8752723","url":null,"abstract":"Due to harmonics problems generated by converter devices. Currently, passive filter has been widely used in suppressing harmonics distortion. Passive filter which mostly used is double tuned filter. However, double tuned filter doesn't have a damping resistor which can prevent network elements from exposing to harsh condition such as when the system reactance and the filter impedance are conjugated, this condition can cause severe overvoltage harmonics on the filter and other power system components. There is a new configuration of double tuned filter that has damping resistor, called damped-type double tuned filter. Aiming at the question of parameter of damped-type double tuned filter, a new algorithm for designing the parameter of damped-type double tuned filter is proposed based on the relationship between impedance of two single tuned filter and one double tuned filter, and also based on the resonance at tuned frequency one and tuned frequency two are close to zero. Simulation result from MATLAB shows that the impedance of damped-type double tuned filter designed with this algorithm is appropriate. In addition, the simulation result from PSIM shows that damped-type double tuned filter designed with this algorithm works well.","PeriodicalId":6543,"journal":{"name":"2018 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"45 2 1","pages":"193-197"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82691712","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 : 2018-10-01DOI: 10.1109/EECSI.2018.8752851
E. B. Setiawan, D. H. Widyantoro, K. Surendro
The community's need for social media is increasing, since the media can be used to express their opinion, especially the Twitter. Sentiment analysis can be used to understand public opinion a topic where the accuracy can be measured and improved by several methods. In this paper, we introduce a hybrid method that combines: (a) basic features and feature expansion based on Term Frequency–Inverse Document Frequency (TF-IDF) and (b) basic features and feature expansion based on tweet-based features. We train three most common classifiers for this field, i.e., Support Vector Machine (SVM), Logistic Regression (Logit), and Naïve Bayes (NB). From those two feature expansions, we do notice a significant increase in feature expansion with tweet-based features rather than based on TF-IDF, where the highest accuracy of 98.81% is achieved in Logistic Regression Classifier.
{"title":"Feature Expansion for Sentiment Analysis in Twitter","authors":"E. B. Setiawan, D. H. Widyantoro, K. Surendro","doi":"10.1109/EECSI.2018.8752851","DOIUrl":"https://doi.org/10.1109/EECSI.2018.8752851","url":null,"abstract":"The community's need for social media is increasing, since the media can be used to express their opinion, especially the Twitter. Sentiment analysis can be used to understand public opinion a topic where the accuracy can be measured and improved by several methods. In this paper, we introduce a hybrid method that combines: (a) basic features and feature expansion based on Term Frequency–Inverse Document Frequency (TF-IDF) and (b) basic features and feature expansion based on tweet-based features. We train three most common classifiers for this field, i.e., Support Vector Machine (SVM), Logistic Regression (Logit), and Naïve Bayes (NB). From those two feature expansions, we do notice a significant increase in feature expansion with tweet-based features rather than based on TF-IDF, where the highest accuracy of 98.81% is achieved in Logistic Regression Classifier.","PeriodicalId":6543,"journal":{"name":"2018 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"7 1","pages":"509-513"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83087295","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 : 2018-10-01DOI: 10.1109/EECSI.2018.8752912
Kevin Situmorang, A. Hidayanto, A. Wicaksono, A. Yuliawati
Customer satisfaction becomes a key influencer for people’s habits or daily activities. One of the examples is in the decision-making process about whether they will use specific products or services. People often need other’s review or rating about what they are going to use or consume. In this research, by using customer’s online review that available from Airbnb website, we try to extract what are the most talked factors about peer-to-peer accommodation, and how customer sentiment about them. We use Latent Dirichlet Allocation (LDA) to extract that factors and conduct sentiment analysis by utilizing semantic analyzer from Google Cloud NLP. We analyze which factors that has more effect on customer satisfaction, not only in general but more specific based on customer gender and tourism destination object. The result shows that factors related to social benefit and service quality have impact on customer satisfaction, moreover different customer gender and different tourism object destination bring different sentiment among customer. We also find several factors that can be improved by the owner of the accommodation to improve customer satisfaction toward their services.
{"title":"Analysis on Customer Satisfaction Dimensions in Peer-to-Peer Accommodation using Latent Dirichlet Allocation: A Case Study of Airbnb","authors":"Kevin Situmorang, A. Hidayanto, A. Wicaksono, A. Yuliawati","doi":"10.1109/EECSI.2018.8752912","DOIUrl":"https://doi.org/10.1109/EECSI.2018.8752912","url":null,"abstract":"Customer satisfaction becomes a key influencer for people’s habits or daily activities. One of the examples is in the decision-making process about whether they will use specific products or services. People often need other’s review or rating about what they are going to use or consume. In this research, by using customer’s online review that available from Airbnb website, we try to extract what are the most talked factors about peer-to-peer accommodation, and how customer sentiment about them. We use Latent Dirichlet Allocation (LDA) to extract that factors and conduct sentiment analysis by utilizing semantic analyzer from Google Cloud NLP. We analyze which factors that has more effect on customer satisfaction, not only in general but more specific based on customer gender and tourism destination object. The result shows that factors related to social benefit and service quality have impact on customer satisfaction, moreover different customer gender and different tourism object destination bring different sentiment among customer. We also find several factors that can be improved by the owner of the accommodation to improve customer satisfaction toward their services.","PeriodicalId":6543,"journal":{"name":"2018 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"13 1","pages":"542-547"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87582310","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 : 2018-10-01DOI: 10.1109/EECSI.2018.8752818
S. Sugianto, Azwar Al Anhar, R. Harwahyu, R. F. Sari
LoRa is a viable connectivity technology for smart electricity meter. In addition to measuring electricity usage, a smart electricity meter enables many features for smart grid, safety, etc. LoRa is advertised to be capable in very long range transmission and low power consumption. However, LoRa uses sub 1 GHz unlicensed spectrum. In the era of connected smart things, this spectrum is very crowded and will be even more crowded. In this paper we propose the use of mobile LoRa gateway for smart electricity meter. With mobile LoRa gateway, the transmission range can be decreased. Thus, LoRa end devices can save more power and nearby systems can reuse the same band with less interference. We study the performance via simulation using modified LoRaSim. The result shows that the performance of LoRa mobile gateway can be achieved.
{"title":"Simulation of Mobile LoRa Gateway for Smart Electricity Meter","authors":"S. Sugianto, Azwar Al Anhar, R. Harwahyu, R. F. Sari","doi":"10.1109/EECSI.2018.8752818","DOIUrl":"https://doi.org/10.1109/EECSI.2018.8752818","url":null,"abstract":"LoRa is a viable connectivity technology for smart electricity meter. In addition to measuring electricity usage, a smart electricity meter enables many features for smart grid, safety, etc. LoRa is advertised to be capable in very long range transmission and low power consumption. However, LoRa uses sub 1 GHz unlicensed spectrum. In the era of connected smart things, this spectrum is very crowded and will be even more crowded. In this paper we propose the use of mobile LoRa gateway for smart electricity meter. With mobile LoRa gateway, the transmission range can be decreased. Thus, LoRa end devices can save more power and nearby systems can reuse the same band with less interference. We study the performance via simulation using modified LoRaSim. The result shows that the performance of LoRa mobile gateway can be achieved.","PeriodicalId":6543,"journal":{"name":"2018 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"46 1","pages":"292-297"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89454787","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 : 2018-10-01DOI: 10.1109/EECSI.2018.8752759
Nanda Avianto Wicaksono, Bernadeta Wuri Harini, F. Yusivar
This paper is intended to design a controller and an observer of a sensorless PMSM (permanent magnet synchronous motor) in electric vehicle application. The controller uses the field orientation control (FOC) method and the observer type is the fifth order extended Kalman filter (EKF). The designed controller and observer are tested by varying the elevation angle of the route that is several times abruptly changed. The simulation result shows that the designed controller and observer can respond to the elevation angles given.
{"title":"Sensorless PMSM Control using Fifth Order EKF in Electric Vehicle Application","authors":"Nanda Avianto Wicaksono, Bernadeta Wuri Harini, F. Yusivar","doi":"10.1109/EECSI.2018.8752759","DOIUrl":"https://doi.org/10.1109/EECSI.2018.8752759","url":null,"abstract":"This paper is intended to design a controller and an observer of a sensorless PMSM (permanent magnet synchronous motor) in electric vehicle application. The controller uses the field orientation control (FOC) method and the observer type is the fifth order extended Kalman filter (EKF). The designed controller and observer are tested by varying the elevation angle of the route that is several times abruptly changed. The simulation result shows that the designed controller and observer can respond to the elevation angles given.","PeriodicalId":6543,"journal":{"name":"2018 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"25 1","pages":"254-259"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90319963","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 : 2018-10-01DOI: 10.1109/EECSI.2018.8752749
Y. M. Hamdani, U. Khayam
Partial discharge (PD) is a local electrification phenomenon that partially connects insulation between the conductors and occurs either on the surface of the conductor or inside the insulation (void). During the PD there are several phenomena that accompany the occurrence of PD, such as impulse currents, heat radiation, electromagnetic waves, mechanical waves and chemical processes. This phenomenon is detected and measured to know the existence of PD. One of the PD measurements is ultra high frequency (UHF) method, by measuring the waves generated by PD using antenna. One of antenna having good characteristics is UWB double layer printed antenna. In this paper the application of ultra-wideband double layer printed antenna for partial discharge detection is reported. The application of antenna on PD measurement, shows that the antenna is able to detect PD. The characteristics of PD: PDIV, PDEV, PD waveform are measured using this antenna. Ultra-wideband (UWB) double layer printed antenna is an antenna developed from a square microstrip antenna with symmetrical T-shaped tethering. The proposed antenna is implemented on Epoxy FR-4 substrate with permittivity of 4.3, thickness of 1.6mm, and 72.8mm x 60.0mm in size. The VNA testing of the antenna shows that the antenna bandwidth is from 50MHz to 2.30GHz. The measured results of PD wave are PDIV, PD waveform and PDEV.
局部放电(PD)是一种局部带电现象，它使导体之间的绝缘部分接通，发生在导体表面或绝缘(空隙)内部。在PD过程中，伴随PD发生的现象有脉冲电流、热辐射、电磁波、机械波和化学过程等。对这种现象进行检测和测量，以了解PD的存在。超高频(UHF)法是局部放电测量的一种方法，利用天线测量局部放电产生的波。超宽带双层印刷天线是一种具有良好性能的天线。本文报道了超宽带双层印刷天线在局部放电检测中的应用。该天线在局部放电测量中的应用表明，该天线能够检测到局部放电。利用该天线测量了PD的特性:PDIV、PDEV、PD波形。超宽带(UWB)双层印刷天线是由对称t型系带的方形微带天线发展而来的天线。该天线采用介电常数为4.3、厚度为1.6mm、尺寸为72.8mm x 60.0mm的环氧FR-4基板实现。天线VNA测试表明，天线带宽在50MHz ~ 2.30GHz之间。PD波的测量结果为PDIV、PD波形和PDEV。
{"title":"Application of Ultra-Wideband Double Layer Printed Antenna for Partial Discharge Detection","authors":"Y. M. Hamdani, U. Khayam","doi":"10.1109/EECSI.2018.8752749","DOIUrl":"https://doi.org/10.1109/EECSI.2018.8752749","url":null,"abstract":"Partial discharge (PD) is a local electrification phenomenon that partially connects insulation between the conductors and occurs either on the surface of the conductor or inside the insulation (void). During the PD there are several phenomena that accompany the occurrence of PD, such as impulse currents, heat radiation, electromagnetic waves, mechanical waves and chemical processes. This phenomenon is detected and measured to know the existence of PD. One of the PD measurements is ultra high frequency (UHF) method, by measuring the waves generated by PD using antenna. One of antenna having good characteristics is UWB double layer printed antenna. In this paper the application of ultra-wideband double layer printed antenna for partial discharge detection is reported. The application of antenna on PD measurement, shows that the antenna is able to detect PD. The characteristics of PD: PDIV, PDEV, PD waveform are measured using this antenna. Ultra-wideband (UWB) double layer printed antenna is an antenna developed from a square microstrip antenna with symmetrical T-shaped tethering. The proposed antenna is implemented on Epoxy FR-4 substrate with permittivity of 4.3, thickness of 1.6mm, and 72.8mm x 60.0mm in size. The VNA testing of the antenna shows that the antenna bandwidth is from 50MHz to 2.30GHz. The measured results of PD wave are PDIV, PD waveform and PDEV.","PeriodicalId":6543,"journal":{"name":"2018 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"16 1","pages":"373-378"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88031147","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 : 2018-10-01DOI: 10.1109/EECSI.2018.8752687
Fransiska Pinem, R. Andreswari, M. A. Hasibuan
Celebrity endorsement is a phenomenon in which companies advertises their products by using celebrity services, and celebrities take advantage of their popularity to promote a brand or product of the company through social media. In this study, KFC did a celebrity endorsement to make their menu more popular. KFC choose to work with Raditya Dika to promote their latest menu, KFC Salted Egg Chicken. This study will examine whether in such cases there is a change in public sentiment towards the product after the celebrity endorsement. It can be done using text mining and sentiment analysis. There are several algorithms that can be used to perform sentiment analysis, one of them is Support Vector Machine. Support Vector Machine (SVM) was chosen because this method is quite accurate in various studies. SVM also takes into account various features of the document, including features that often do not appear on the document, so it can reduce the loss of information from the data. The data used in this research are taken from YouTube and Twitter comment about KFC Salted Egg Chicken. Several step was done in this sentiment analysis research, that are preprocessing text, feature extraction, classification, and evaluation. The result model is tested and evaluated before and after endorsement by looking at the value of accuracy, precision, recall, and f1-measure. The test result of accuracy, precision, recall, and f-measure before endorsement were 67,83%, 69%, 68%, and 66%. After the endorsement, the test results were 74.06%, 74%, 74%, and 74% respectively. The results of this study indicate that SVM has an accurate measurement in sentiment analysis studies. Moreover, this study found that there was not significant change in public sentiment regarding the product before and after the celebrity endorsement.
{"title":"Sentiment Analysis to Measure Celebrity Endorsment’s Effect using Support Vector Machine Algorithm","authors":"Fransiska Pinem, R. Andreswari, M. A. Hasibuan","doi":"10.1109/EECSI.2018.8752687","DOIUrl":"https://doi.org/10.1109/EECSI.2018.8752687","url":null,"abstract":"Celebrity endorsement is a phenomenon in which companies advertises their products by using celebrity services, and celebrities take advantage of their popularity to promote a brand or product of the company through social media. In this study, KFC did a celebrity endorsement to make their menu more popular. KFC choose to work with Raditya Dika to promote their latest menu, KFC Salted Egg Chicken. This study will examine whether in such cases there is a change in public sentiment towards the product after the celebrity endorsement. It can be done using text mining and sentiment analysis. There are several algorithms that can be used to perform sentiment analysis, one of them is Support Vector Machine. Support Vector Machine (SVM) was chosen because this method is quite accurate in various studies. SVM also takes into account various features of the document, including features that often do not appear on the document, so it can reduce the loss of information from the data. The data used in this research are taken from YouTube and Twitter comment about KFC Salted Egg Chicken. Several step was done in this sentiment analysis research, that are preprocessing text, feature extraction, classification, and evaluation. The result model is tested and evaluated before and after endorsement by looking at the value of accuracy, precision, recall, and f1-measure. The test result of accuracy, precision, recall, and f-measure before endorsement were 67,83%, 69%, 68%, and 66%. After the endorsement, the test results were 74.06%, 74%, 74%, and 74% respectively. The results of this study indicate that SVM has an accurate measurement in sentiment analysis studies. Moreover, this study found that there was not significant change in public sentiment regarding the product before and after the celebrity endorsement.","PeriodicalId":6543,"journal":{"name":"2018 5th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)","volume":"15 1","pages":"690-695"},"PeriodicalIF":0.0,"publicationDate":"2018-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82026626","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：