Pub Date : 2019-11-01DOI: 10.1109/ICISS48059.2019.8969822
Sumintir, B. Pharmasetiawan
Illicit tobacco is a worldwide issue that not only causes severe losses in the government revenue by tax evasion, but also has a negative impact on public health. Track and trace systems that allow states to monitor the movement of tobacco products from the starting point of production to the endpoints of sale will be key to global efforts to prevent the illicit trade in tobacco. This research proposes a framework and methodological approach for designing interoperable tobacco track and trace system capable of securing the supply chain and facilitating in investigating the illicit trade of tobacco products. The development of the framework is carried out by reviewing published traceability framework in the food industry and pharmaceutical industry sectors, and then adjusting it to the requirements of the WHO FCTC Protocol to Eliminate Illicit Trade in Tobacco Products and GS1 System Standards. The results are the TraceTobacco Framework which consists of seven main principle elements and TraceTobacco Methodology which outlines five important steps, both play an important role in designing an interoperable tobacco track and trace system. An interoperable tobacco track and trace system enables effective and efficient data and information exchange for securing supply chains and preventing illicit trade in tobacco products, which in turn has an impact on reducing the amount of illicit tobacco and improving public health, protecting the government revenues, and protecting legitimate economic operators.
{"title":"TraceTobacco: A Framework and Methodological Approach for Designing Interoperable Tobacco Track and Trace System","authors":"Sumintir, B. Pharmasetiawan","doi":"10.1109/ICISS48059.2019.8969822","DOIUrl":"https://doi.org/10.1109/ICISS48059.2019.8969822","url":null,"abstract":"Illicit tobacco is a worldwide issue that not only causes severe losses in the government revenue by tax evasion, but also has a negative impact on public health. Track and trace systems that allow states to monitor the movement of tobacco products from the starting point of production to the endpoints of sale will be key to global efforts to prevent the illicit trade in tobacco. This research proposes a framework and methodological approach for designing interoperable tobacco track and trace system capable of securing the supply chain and facilitating in investigating the illicit trade of tobacco products. The development of the framework is carried out by reviewing published traceability framework in the food industry and pharmaceutical industry sectors, and then adjusting it to the requirements of the WHO FCTC Protocol to Eliminate Illicit Trade in Tobacco Products and GS1 System Standards. The results are the TraceTobacco Framework which consists of seven main principle elements and TraceTobacco Methodology which outlines five important steps, both play an important role in designing an interoperable tobacco track and trace system. An interoperable tobacco track and trace system enables effective and efficient data and information exchange for securing supply chains and preventing illicit trade in tobacco products, which in turn has an impact on reducing the amount of illicit tobacco and improving public health, protecting the government revenues, and protecting legitimate economic operators.","PeriodicalId":125643,"journal":{"name":"2019 International Conference on ICT for Smart Society (ICISS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123476040","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 : 2019-11-01DOI: 10.1109/ICISS48059.2019.8969818
Novan Zulkarnain, R. Kosala, B. Ranti, S. Supangkat
There have been many studies conducted related to Smart City, IT Governance and Big Data. In this study aims to find out how the relationship between the three and how to form a framework to explain it. The methodology used is qualitative by looking for some literature on smart city framework, IT Governance framework, and a Big Data framework. From these results, an overall picture of the relationship between the three is concluded, where Big Data has a role in IT Governance. and also the relationship of IT Governance to the realization of Smart City. And the final results of this study produce a framework to explain the relationship between Smart City, IT Governance and Big Data.
{"title":"Big Data Governance for Building A Smart Cities","authors":"Novan Zulkarnain, R. Kosala, B. Ranti, S. Supangkat","doi":"10.1109/ICISS48059.2019.8969818","DOIUrl":"https://doi.org/10.1109/ICISS48059.2019.8969818","url":null,"abstract":"There have been many studies conducted related to Smart City, IT Governance and Big Data. In this study aims to find out how the relationship between the three and how to form a framework to explain it. The methodology used is qualitative by looking for some literature on smart city framework, IT Governance framework, and a Big Data framework. From these results, an overall picture of the relationship between the three is concluded, where Big Data has a role in IT Governance. and also the relationship of IT Governance to the realization of Smart City. And the final results of this study produce a framework to explain the relationship between Smart City, IT Governance and Big Data.","PeriodicalId":125643,"journal":{"name":"2019 International Conference on ICT for Smart Society (ICISS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122924248","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 : 2019-11-01DOI: 10.1109/ICISS48059.2019.8969842
Okti Nindyati, I. G. Bagus Baskara Nugraha
To design a qualified training program so that the competence of job seekers can be in line with the industrial needs, Training Need Analysis (TNA) should be conducted before establish a training program. But unfortunately there have been many fraudulent job ads by individuals on behalf of the company. In order to overcome the problem, an employment scam detection is required. This research proposed an employment scam detection using of behavorial context based features to determine whether a job advertisement is legitimate or fraudulent.
{"title":"Detecting Scam in Online Job Vacancy Using Behavioral Features Extraction","authors":"Okti Nindyati, I. G. Bagus Baskara Nugraha","doi":"10.1109/ICISS48059.2019.8969842","DOIUrl":"https://doi.org/10.1109/ICISS48059.2019.8969842","url":null,"abstract":"To design a qualified training program so that the competence of job seekers can be in line with the industrial needs, Training Need Analysis (TNA) should be conducted before establish a training program. But unfortunately there have been many fraudulent job ads by individuals on behalf of the company. In order to overcome the problem, an employment scam detection is required. This research proposed an employment scam detection using of behavorial context based features to determine whether a job advertisement is legitimate or fraudulent.","PeriodicalId":125643,"journal":{"name":"2019 International Conference on ICT for Smart Society (ICISS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124984300","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 : 2019-11-01DOI: 10.1109/ICISS48059.2019.8969838
D. N. Utama, Calvin Chang
In Indonesia, the issue of waste is definitely challenging. This problem demands an exclusive and prudent treatment to implement; as a destructive consequence practically generated from incorrect strategy implementation in treating is wide-ranging, particularly for human’s life and health and also for environment. This paper offers a generic smart ecological decision support model (ecoDSM) for treating medical waste. The mathematical model based on fuzzy logic conception that combined with the other heuristic optimization method are functioned to measure and justify six alternatives of treating strategy decision. Based on empirical data of two types of medical waste (i.e. sharp and infectious) coming from private hospital; the model’s simulation result shows that the "mechanical processing and chemical disinfectant" treatment strategy is the most objective decision should be implemented by the hospital.
{"title":"A Smart ecoDSM for Treating Medical Waste: A Modified Version","authors":"D. N. Utama, Calvin Chang","doi":"10.1109/ICISS48059.2019.8969838","DOIUrl":"https://doi.org/10.1109/ICISS48059.2019.8969838","url":null,"abstract":"In Indonesia, the issue of waste is definitely challenging. This problem demands an exclusive and prudent treatment to implement; as a destructive consequence practically generated from incorrect strategy implementation in treating is wide-ranging, particularly for human’s life and health and also for environment. This paper offers a generic smart ecological decision support model (ecoDSM) for treating medical waste. The mathematical model based on fuzzy logic conception that combined with the other heuristic optimization method are functioned to measure and justify six alternatives of treating strategy decision. Based on empirical data of two types of medical waste (i.e. sharp and infectious) coming from private hospital; the model’s simulation result shows that the \"mechanical processing and chemical disinfectant\" treatment strategy is the most objective decision should be implemented by the hospital.","PeriodicalId":125643,"journal":{"name":"2019 International Conference on ICT for Smart Society (ICISS)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125970808","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 : 2019-11-01DOI: 10.1109/ICISS48059.2019.8969785
D. Gunawan, Siti Hazizah Harahap, Romi Fadillah Rahmat
The text summarizer reduces unnecessary information by selecting the important sentences. In multi-document summarization, there is a possibility that two or more important sentences share similar information. Including those sentences to the summary result will cause redundant information. This research aims to reduce similar sentences from multi-document that share similar information to obtain a more concise text summary. In order to accomplish the objective, this research uses the combination of several online news articles, divided into six groups. The combined articles are pre-processed to produce a clean text. After obtaining the clean text, this research utilizes the TextRank algorithm to extract the important sentences by using the similarity measurement. This process yields the summarized text. However, the summarized text is still containing similar sentences. The next process is calculating Maximal Marginal Relevance (MMR) to reduce similar sentences. The result of this process is the final text summary. The evaluation uses ROUGE-1 and ROUGE-2 with the average F-score is 0.5103 and 0.4257, respectively.
{"title":"Multi-document Summarization by using TextRank and Maximal Marginal Relevance for Text in Bahasa Indonesia","authors":"D. Gunawan, Siti Hazizah Harahap, Romi Fadillah Rahmat","doi":"10.1109/ICISS48059.2019.8969785","DOIUrl":"https://doi.org/10.1109/ICISS48059.2019.8969785","url":null,"abstract":"The text summarizer reduces unnecessary information by selecting the important sentences. In multi-document summarization, there is a possibility that two or more important sentences share similar information. Including those sentences to the summary result will cause redundant information. This research aims to reduce similar sentences from multi-document that share similar information to obtain a more concise text summary. In order to accomplish the objective, this research uses the combination of several online news articles, divided into six groups. The combined articles are pre-processed to produce a clean text. After obtaining the clean text, this research utilizes the TextRank algorithm to extract the important sentences by using the similarity measurement. This process yields the summarized text. However, the summarized text is still containing similar sentences. The next process is calculating Maximal Marginal Relevance (MMR) to reduce similar sentences. The result of this process is the final text summary. The evaluation uses ROUGE-1 and ROUGE-2 with the average F-score is 0.5103 and 0.4257, respectively.","PeriodicalId":125643,"journal":{"name":"2019 International Conference on ICT for Smart Society (ICISS)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125044537","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 : 2019-11-01DOI: 10.1109/ICISS48059.2019.8969828
A. Alamsyah, Earlyan Abdiel Bernatapi
Customer experience is of crucial significance to the constant growth of a business. It is necessary to ensure great customer experience, thus maintaining customer loyalty and satisfaction. An approach that intended to develop and improve customer experience is called Customer Experience Management (CEM). CEM is a strategy practiced to track, supervise, and arrange all synergy to help a business focal point on the needs of its customers. This research uses sentiment analysis and topic modeling to analyze the experience of Internet Service Provider customers. The output of this research expected to drive the strategies change in CEM. This research uses data taken from customer tweets on Twitter. It is considering that the data on social media is enormous and unstructured. Therefore, classification using Naive Bayes Classifier applied to assist and expedite in the sentiment analysis process. The classification for sentiment analysis using NBC gained accuracy above 82%. Hence, the classification models using NBC achieve excellent capability for sentiment analysis. To determining topics that often discussed by customers, this research uses the Latent Dirichlet Allocation models for Topic Modeling.
{"title":"Evolving Customer Experience Management in Internet Service Provider Company using Text Analytics","authors":"A. Alamsyah, Earlyan Abdiel Bernatapi","doi":"10.1109/ICISS48059.2019.8969828","DOIUrl":"https://doi.org/10.1109/ICISS48059.2019.8969828","url":null,"abstract":"Customer experience is of crucial significance to the constant growth of a business. It is necessary to ensure great customer experience, thus maintaining customer loyalty and satisfaction. An approach that intended to develop and improve customer experience is called Customer Experience Management (CEM). CEM is a strategy practiced to track, supervise, and arrange all synergy to help a business focal point on the needs of its customers. This research uses sentiment analysis and topic modeling to analyze the experience of Internet Service Provider customers. The output of this research expected to drive the strategies change in CEM. This research uses data taken from customer tweets on Twitter. It is considering that the data on social media is enormous and unstructured. Therefore, classification using Naive Bayes Classifier applied to assist and expedite in the sentiment analysis process. The classification for sentiment analysis using NBC gained accuracy above 82%. Hence, the classification models using NBC achieve excellent capability for sentiment analysis. To determining topics that often discussed by customers, this research uses the Latent Dirichlet Allocation models for Topic Modeling.","PeriodicalId":125643,"journal":{"name":"2019 International Conference on ICT for Smart Society (ICISS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125111145","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 : 2019-11-01DOI: 10.1109/ICISS48059.2019.8969811
Oktariani Nurul Pratiwi, Y. Syukriyah
Along with the use of e-learning, the collection of questions in the database is also increasing. The questions that have been uploaded to the e-learning system can certainly be used repeatedly. The use of repetitive questions will be easy to do with the process of reinvention if the questions have been grouped properly. Unfortunately, grouping questions based on subjects to details on grouping per topic is rarely done in e-learning. This makes the process of tracking the existing problems difficult.In addition, the state of the educational curriculum in Indonesia is often changing. Changes can be changes in whole or in part. This change can make the material content in the subject change order or be eliminated. When these changes occur, the previous problems that can still be used will be difficult to use when curriculum changes occur.Therefore, the large amount of question data and the difficulty in finding the questions again made the researcher to conduct this research. E-learning systems must have machine learning capabilities that are able to classify questions automatically based on topics to sub topics. Examined deeper, each question can have a classification in the form of subject categories, topics, sub topics to the level of difficulty of the questions. In this study, researchers focused on grouping questions based on subject categories and topics.The purpose of this study is to find the right method in building machine learning models in classifying questions according to topic categories and subtopics accurately and quickly. So, the questions in e-learning can be called back exactly as needed automatically.
{"title":"Question Classification for e-Learning Using Machine Learning Approach","authors":"Oktariani Nurul Pratiwi, Y. Syukriyah","doi":"10.1109/ICISS48059.2019.8969811","DOIUrl":"https://doi.org/10.1109/ICISS48059.2019.8969811","url":null,"abstract":"Along with the use of e-learning, the collection of questions in the database is also increasing. The questions that have been uploaded to the e-learning system can certainly be used repeatedly. The use of repetitive questions will be easy to do with the process of reinvention if the questions have been grouped properly. Unfortunately, grouping questions based on subjects to details on grouping per topic is rarely done in e-learning. This makes the process of tracking the existing problems difficult.In addition, the state of the educational curriculum in Indonesia is often changing. Changes can be changes in whole or in part. This change can make the material content in the subject change order or be eliminated. When these changes occur, the previous problems that can still be used will be difficult to use when curriculum changes occur.Therefore, the large amount of question data and the difficulty in finding the questions again made the researcher to conduct this research. E-learning systems must have machine learning capabilities that are able to classify questions automatically based on topics to sub topics. Examined deeper, each question can have a classification in the form of subject categories, topics, sub topics to the level of difficulty of the questions. In this study, researchers focused on grouping questions based on subject categories and topics.The purpose of this study is to find the right method in building machine learning models in classifying questions according to topic categories and subtopics accurately and quickly. So, the questions in e-learning can be called back exactly as needed automatically.","PeriodicalId":125643,"journal":{"name":"2019 International Conference on ICT for Smart Society (ICISS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131344169","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 : 2019-11-01DOI: 10.1109/ICISS48059.2019.8969791
Mogi Jordan Christ, Rahmanto Nikolaus Permana Tri, Wiranto Chandra, W. Gunawan
Healthcare is a crucial industry because it contains sensitive information of human health condition history then security and privacy are the main concern. Currently, Internet enables sharing of those records possible, but it poses a new risk like misuse of patient data as it is shared. Meanwhile in Indonesia one of the main problems that faced in healthcare industry is hospital integration of electronic medical recording. At the age of internet era, one of the hottest technology, that arise is blockchain due to it is astonishing features such as security, transparency, and traceability. Blockchain comes out as a holy grail technology that have great opportunity in the future and already implemented in several business industry. Many previous studies have implemented blockchain in Healthcare. The article examines the use of blockchain in healthcare system, that have been studied and reviewed intensively to see how this technology can be implemented in healthcare system in Indonesia, and to solve several Electronic Medical Record (EMR) problems such as security, privacy and interoperability.
{"title":"Exploring Blockchain in Healthcare Industry","authors":"Mogi Jordan Christ, Rahmanto Nikolaus Permana Tri, Wiranto Chandra, W. Gunawan","doi":"10.1109/ICISS48059.2019.8969791","DOIUrl":"https://doi.org/10.1109/ICISS48059.2019.8969791","url":null,"abstract":"Healthcare is a crucial industry because it contains sensitive information of human health condition history then security and privacy are the main concern. Currently, Internet enables sharing of those records possible, but it poses a new risk like misuse of patient data as it is shared. Meanwhile in Indonesia one of the main problems that faced in healthcare industry is hospital integration of electronic medical recording. At the age of internet era, one of the hottest technology, that arise is blockchain due to it is astonishing features such as security, transparency, and traceability. Blockchain comes out as a holy grail technology that have great opportunity in the future and already implemented in several business industry. Many previous studies have implemented blockchain in Healthcare. The article examines the use of blockchain in healthcare system, that have been studied and reviewed intensively to see how this technology can be implemented in healthcare system in Indonesia, and to solve several Electronic Medical Record (EMR) problems such as security, privacy and interoperability.","PeriodicalId":125643,"journal":{"name":"2019 International Conference on ICT for Smart Society (ICISS)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134026819","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 : 2019-11-01DOI: 10.1109/ICISS48059.2019.8969796
Yudha Saintika, Fauzan Romadlon
Recently, smart city is a popular discussion. In Indonesia, some cities have been implemented to follow Government Information Communication and Technology (ICT) development program. One of smart city domain is society and it has transportation as the component. One of the approaches to encounter the urban complexities are developed public transportation. As case study, Purwokerto and Purbalingga has been implemented Bus Rapid Transit (BRT) as new public transportation. The concept is similar with others BRT. Operational of BRT shall be supported by society to guarantee the sustainability. As information, both cities are developing cities that will implement smart city design and society become critical element to develop city to be planned smart city. This study measures the readiness of both cities initiative to implement smart city concept, specifically at transportation component through BRT Purwokerto-Purbalingga operation. The used methods are quantitative and qualitative analysis. Quantitative analysis is using statistical method to find correlation between socioeconomic or demographics and BRT ridership perceptions. The result is there is significantly difference BRT perception as reliable transportation for residences and routines of BRT use. Moreover, there is statistically difference between perception of BRT as alternative mass transportation with ridership residence and gender. As smart city initiative measurement using qualitative methods, supported smart city in BRT operation gain readiness of ICT, governance and human or society. By this finding, BRT operation shall improve governance and ICT enablers to come up with smart city initiative.
{"title":"Readiness of Operating Bus Rapid Transit (BRT) Purwokerto-Purbalingga towards Smart City Concept","authors":"Yudha Saintika, Fauzan Romadlon","doi":"10.1109/ICISS48059.2019.8969796","DOIUrl":"https://doi.org/10.1109/ICISS48059.2019.8969796","url":null,"abstract":"Recently, smart city is a popular discussion. In Indonesia, some cities have been implemented to follow Government Information Communication and Technology (ICT) development program. One of smart city domain is society and it has transportation as the component. One of the approaches to encounter the urban complexities are developed public transportation. As case study, Purwokerto and Purbalingga has been implemented Bus Rapid Transit (BRT) as new public transportation. The concept is similar with others BRT. Operational of BRT shall be supported by society to guarantee the sustainability. As information, both cities are developing cities that will implement smart city design and society become critical element to develop city to be planned smart city. This study measures the readiness of both cities initiative to implement smart city concept, specifically at transportation component through BRT Purwokerto-Purbalingga operation. The used methods are quantitative and qualitative analysis. Quantitative analysis is using statistical method to find correlation between socioeconomic or demographics and BRT ridership perceptions. The result is there is significantly difference BRT perception as reliable transportation for residences and routines of BRT use. Moreover, there is statistically difference between perception of BRT as alternative mass transportation with ridership residence and gender. As smart city initiative measurement using qualitative methods, supported smart city in BRT operation gain readiness of ICT, governance and human or society. By this finding, BRT operation shall improve governance and ICT enablers to come up with smart city initiative.","PeriodicalId":125643,"journal":{"name":"2019 International Conference on ICT for Smart Society (ICISS)","volume":"51 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132071271","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 : 2019-11-01DOI: 10.1109/ICISS48059.2019.8969850
P. Telnoni, Reza Budiawan, Mutia Qana’a
As Artificial Intelligence (AI) and Machine Learning (ML) gaining momentum on industry and academic field, a deeper understanding for AI and ML are highly required. One of the most popular sub-field in this field is text analysis. This paper will discuss the performance of classification methods for text-based data and give the best choices of classification method in term of accuracy and training time, so that will help ML enthusiast to build ML project that does not require high computational cost. This paper aimed to give recommendation to practitioner and academic about which classifier best for text classification. This paper will limit its study in supervised learning only. The tested algorithm will be Support Vector Machine, Logistic Regression, Naive Bayes, Random Forest, and K-Nearest Neighbor. To simplify the project, text will be labelled into single-label data, not multi-label. The test shows that SVM gives best result, in term of accuracy and training time among other methods.
{"title":"Comparison of Machine Learning Classification Method on Text-based Case in Twitter","authors":"P. Telnoni, Reza Budiawan, Mutia Qana’a","doi":"10.1109/ICISS48059.2019.8969850","DOIUrl":"https://doi.org/10.1109/ICISS48059.2019.8969850","url":null,"abstract":"As Artificial Intelligence (AI) and Machine Learning (ML) gaining momentum on industry and academic field, a deeper understanding for AI and ML are highly required. One of the most popular sub-field in this field is text analysis. This paper will discuss the performance of classification methods for text-based data and give the best choices of classification method in term of accuracy and training time, so that will help ML enthusiast to build ML project that does not require high computational cost. This paper aimed to give recommendation to practitioner and academic about which classifier best for text classification. This paper will limit its study in supervised learning only. The tested algorithm will be Support Vector Machine, Logistic Regression, Naive Bayes, Random Forest, and K-Nearest Neighbor. To simplify the project, text will be labelled into single-label data, not multi-label. The test shows that SVM gives best result, in term of accuracy and training time among other methods.","PeriodicalId":125643,"journal":{"name":"2019 International Conference on ICT for Smart Society (ICISS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128900092","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：