Pub Date : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979691
Akhiyar Waladi, A. M. Arymurthy, A. Wibisono, P. Mursanto
In a democratic state, General Election (Pemilu) is a procedure for selecting regional heads regulated in Article 1 paragraph 3 of the 1945 Constitution. KPU (Komisi Pemilihan Umum) is a state institution that organizes by prioritize transparency and accountability in each stage of general elections in Indonesia. One form of openness that has always been in the media spotlight is the vote counting process. The manual calculation process carried out by the General Election Commissions (KPU) on form C1 is time-consuming and resourceful because it involves paid volunteers. In this study, the authors used the proposed method to build a numerical handwriting recognition system on the C1 KPU form. Method proposed is a recognition flow including table detection with candidate contour techniques, feature matching, number segmentation, and digit classification with the convolutional neural network (CNN). The datasets used are from the official KPU election websites in 2014 and 2019. We use capsnet to classify each segmented digit with 95.65% accuracy. The trained model was tested using validation form and reach 80.73% document accuracy using 2019 election form.
{"title":"Automatic Counting Based On Scanned Election Form Using Feature Match and Convolutional Neural Network","authors":"Akhiyar Waladi, A. M. Arymurthy, A. Wibisono, P. Mursanto","doi":"10.1109/ICACSIS47736.2019.8979691","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979691","url":null,"abstract":"In a democratic state, General Election (Pemilu) is a procedure for selecting regional heads regulated in Article 1 paragraph 3 of the 1945 Constitution. KPU (Komisi Pemilihan Umum) is a state institution that organizes by prioritize transparency and accountability in each stage of general elections in Indonesia. One form of openness that has always been in the media spotlight is the vote counting process. The manual calculation process carried out by the General Election Commissions (KPU) on form C1 is time-consuming and resourceful because it involves paid volunteers. In this study, the authors used the proposed method to build a numerical handwriting recognition system on the C1 KPU form. Method proposed is a recognition flow including table detection with candidate contour techniques, feature matching, number segmentation, and digit classification with the convolutional neural network (CNN). The datasets used are from the official KPU election websites in 2014 and 2019. We use capsnet to classify each segmented digit with 95.65% accuracy. The trained model was tested using validation form and reach 80.73% document accuracy using 2019 election form.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133793801","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 : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979688
Fakhri Rhizadi, H. Fadhlillah, A. Azurat, Iis Afriyanti, Niken Fitria Apriani
Software product line (SPL) is a methodology to develop application variants with feature variability to accommodate user needs in a specific market. This methodology can be supported by the Abstract Behavioral Specification (ABS) modeling language. With the use of delta-oriented programming (DOP) in ABS, the development process to produce application variants in SPL can be automated. However, feature variability of an application variant could affect the design and implementation of the database schema of the application during product derivation phase in SPL, if the feature is related to the data storage of the application. This crucial thing is not handled by the management technique of variability in SPL which makes database schema might be inconsistent and incompatible with the application requirements. In this study, we successfully implement a tool to generate a compatible relational database schema for an application variant. This tool has also been adopted to support the automation process of our working product line for charity organizations.
{"title":"Database Generator to Support Product Derivation in SPL","authors":"Fakhri Rhizadi, H. Fadhlillah, A. Azurat, Iis Afriyanti, Niken Fitria Apriani","doi":"10.1109/ICACSIS47736.2019.8979688","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979688","url":null,"abstract":"Software product line (SPL) is a methodology to develop application variants with feature variability to accommodate user needs in a specific market. This methodology can be supported by the Abstract Behavioral Specification (ABS) modeling language. With the use of delta-oriented programming (DOP) in ABS, the development process to produce application variants in SPL can be automated. However, feature variability of an application variant could affect the design and implementation of the database schema of the application during product derivation phase in SPL, if the feature is related to the data storage of the application. This crucial thing is not handled by the management technique of variability in SPL which makes database schema might be inconsistent and incompatible with the application requirements. In this study, we successfully implement a tool to generate a compatible relational database schema for an application variant. This tool has also been adopted to support the automation process of our working product line for charity organizations.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130809501","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 : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979912
Farah Agia Ramadhina, H. Santoso, Y. K. Isal
With the growing awareness to learn deeper about Islam and Quran, there is an increasing trend to learn the Arabic language in Indonesia. While many institutions offer onsite learning platform to learn Arabic, the need for technology-based e-learning Arabic course is increasing as technology in Indonesia advances. The e-learning approach has to be based upon the needs of users to ensure the learning is effective. This study aims to design an online e-learning basic Arabic course using user-centered design (UCD) approach. The methodology employed in this study is mixed methods. The study covers requirements gathering, create design solution, prototyping, and evaluation. Gagne's nine instructional events are used as a theoretical basis for designing Instructional design. Evaluation is done by referring to usability testing method. This study results in an e-learning Arabic course interface that stemmed from user needs and instructional design. The final output has 17 features out of 34 identified user needs.
{"title":"Online Learning Design for Fundamental Arabic Language with User-Centered Design Approach","authors":"Farah Agia Ramadhina, H. Santoso, Y. K. Isal","doi":"10.1109/ICACSIS47736.2019.8979912","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979912","url":null,"abstract":"With the growing awareness to learn deeper about Islam and Quran, there is an increasing trend to learn the Arabic language in Indonesia. While many institutions offer onsite learning platform to learn Arabic, the need for technology-based e-learning Arabic course is increasing as technology in Indonesia advances. The e-learning approach has to be based upon the needs of users to ensure the learning is effective. This study aims to design an online e-learning basic Arabic course using user-centered design (UCD) approach. The methodology employed in this study is mixed methods. The study covers requirements gathering, create design solution, prototyping, and evaluation. Gagne's nine instructional events are used as a theoretical basis for designing Instructional design. Evaluation is done by referring to usability testing method. This study results in an e-learning Arabic course interface that stemmed from user needs and instructional design. The final output has 17 features out of 34 identified user needs.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133048208","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 : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979911
M. R. Safira, I. Irwansyah
The following study examines the social humanism dimension in digital empowerment in the context of society of Indonesia. A research was conducted in two stages, First, qualitatively with interviews and observations, Second, quantitatively for factors testing. Qualitative research with thematic design was conducted with interviews and observations on individuals involved in Kampung Blogger in Menowo Village, Magelang, Central Java. The interviews and observations results gave indicators on social humanism and the usage of digital technology, which were then tested on grade X and XI students of SMAN 1 Magelang. The result of this research suggests the need to look at digital technology usage from the context of society to enable programs which suit the needs of each society in the future. On top of that, the testing of digital empowerment and social humanism factor in the context of Indonesia can serve as a beneficial input in measuring the digital empowerment level in the society.
{"title":"The Social Humanism Factor in Digital Empowerment in Indonesia Study on Kampung Blogger, Menowo Village, Central Java : Study on Kampung Blogger, Menowo Village, Central Java","authors":"M. R. Safira, I. Irwansyah","doi":"10.1109/ICACSIS47736.2019.8979911","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979911","url":null,"abstract":"The following study examines the social humanism dimension in digital empowerment in the context of society of Indonesia. A research was conducted in two stages, First, qualitatively with interviews and observations, Second, quantitatively for factors testing. Qualitative research with thematic design was conducted with interviews and observations on individuals involved in Kampung Blogger in Menowo Village, Magelang, Central Java. The interviews and observations results gave indicators on social humanism and the usage of digital technology, which were then tested on grade X and XI students of SMAN 1 Magelang. The result of this research suggests the need to look at digital technology usage from the context of society to enable programs which suit the needs of each society in the future. On top of that, the testing of digital empowerment and social humanism factor in the context of Indonesia can serve as a beneficial input in measuring the digital empowerment level in the society.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122249795","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 : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979832
Jorgie Bartelsi Permana, Muhammad Arzaki, Yanti Rusmawati
We construct a Prolog script that models the financial network which has the capability to simulate the spread of financial loss due to bankruptcy. Our focus is in the construction of Prolog script that simulates the cascading failure for a previously constructed model pertaining to Sariwangi AEA and Indorub bankruptcy case. The script is capable of finding bankrupt nodes, the amount of financial loss the entire model suffers, and nodes that are vulnerable to bankruptcy. A simulation is run multiple times under different financial failure threshold. From the simulation results, we obtain seven classifications regarding bankrupt nodes associated to a particular failure threshold.
{"title":"Reasoning about the Cascading Failure of Financial Network Using Prolog","authors":"Jorgie Bartelsi Permana, Muhammad Arzaki, Yanti Rusmawati","doi":"10.1109/ICACSIS47736.2019.8979832","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979832","url":null,"abstract":"We construct a Prolog script that models the financial network which has the capability to simulate the spread of financial loss due to bankruptcy. Our focus is in the construction of Prolog script that simulates the cascading failure for a previously constructed model pertaining to Sariwangi AEA and Indorub bankruptcy case. The script is capable of finding bankrupt nodes, the amount of financial loss the entire model suffers, and nodes that are vulnerable to bankruptcy. A simulation is run multiple times under different financial failure threshold. From the simulation results, we obtain seven classifications regarding bankrupt nodes associated to a particular failure threshold.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122286873","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 : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979920
Anita Safitri, Mahendrawathi Er
Some researchers have linked the social software usage like social media, wikis, blogs, instant messaging, forums and corporate social networks with the process of knowledge sharing. They also found that the application of social software that can provide positive results in the knowledge sharing process. The purpose of this research is to provide insights into state-of-the-art research on the use of social software to support the knowledge sharing process. This research is conducted to answer (i) how the general description of the knowledge sharing process is and (ii) how social software helps the process of knowledge sharing. The method used in this research is the Systematic Literature Review (SLR) where synthesizing related papers sourced from the ScienceDirect journal database. Searching related papers using certain keywords obtained 865 papers. Then 85 papers were selected after applying the inclusion and exclusion criteria. Following a more rigorous papers quality assessment, 20 papers are selected for further analyses. Based on the analysis, we found a general description of knowledge sharing. This paper also describes how social software can support the process of sharing knowledge, and some influencing factors. That factors influencing the level of orientation and knowledge sharing activities on social media, and divided into individual and social factors. Besides that, there are several other factors related but have not been clearly classified yet. Also, we found Social Networking Sites (SNS) as the type of social software that often used and this topic frequently discussed in organization scope.
{"title":"Social Software and Knowledge Sharing: A Systematic Literature Review","authors":"Anita Safitri, Mahendrawathi Er","doi":"10.1109/ICACSIS47736.2019.8979920","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979920","url":null,"abstract":"Some researchers have linked the social software usage like social media, wikis, blogs, instant messaging, forums and corporate social networks with the process of knowledge sharing. They also found that the application of social software that can provide positive results in the knowledge sharing process. The purpose of this research is to provide insights into state-of-the-art research on the use of social software to support the knowledge sharing process. This research is conducted to answer (i) how the general description of the knowledge sharing process is and (ii) how social software helps the process of knowledge sharing. The method used in this research is the Systematic Literature Review (SLR) where synthesizing related papers sourced from the ScienceDirect journal database. Searching related papers using certain keywords obtained 865 papers. Then 85 papers were selected after applying the inclusion and exclusion criteria. Following a more rigorous papers quality assessment, 20 papers are selected for further analyses. Based on the analysis, we found a general description of knowledge sharing. This paper also describes how social software can support the process of sharing knowledge, and some influencing factors. That factors influencing the level of orientation and knowledge sharing activities on social media, and divided into individual and social factors. Besides that, there are several other factors related but have not been clearly classified yet. Also, we found Social Networking Sites (SNS) as the type of social software that often used and this topic frequently discussed in organization scope.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116942092","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 : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979883
T. Faisal, K. Junus, H. Santoso
Universitas Indonesia has implemented a Learning Management System (LMS) known as Student-Centered E-Learning Environment (SCeLE). The SCeLE facilitates collaborative learning through an online discussion forum. Collaborative learning can promote critical thinking. However, students will have difficulties contributing and understanding discussions when the discussion process is fast, lengthy and when diverse ideas arise. This could lead to uncertainty and demotivation among the students. On the other hand, teachers have difficulties in monitoring students’ understanding and the discussion progress. Consequently, providing constructive feedback promptly becomes challenging. This study proposed an online collaborative summarizing feature to be integrated with the online discussion forum to facilitate the construction of a discussion summary. The tool was developed using the User-Centered Design (UCD) approach and tested using the usability evaluation. The participants (both students and lecturers) found that the usability of the developed system was good. This was indicated by the fact that more than 80% of the students and more than 80% of the lecturers were able to finish the tasks given easily. Furthermore, the SUS score exceeded the average score, meaning that students and lecturers found that the developed system had a good usability.
{"title":"Development of the Online Collaborative Summarizing Feature on Student-Centered E-Learning Environment","authors":"T. Faisal, K. Junus, H. Santoso","doi":"10.1109/ICACSIS47736.2019.8979883","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979883","url":null,"abstract":"Universitas Indonesia has implemented a Learning Management System (LMS) known as Student-Centered E-Learning Environment (SCeLE). The SCeLE facilitates collaborative learning through an online discussion forum. Collaborative learning can promote critical thinking. However, students will have difficulties contributing and understanding discussions when the discussion process is fast, lengthy and when diverse ideas arise. This could lead to uncertainty and demotivation among the students. On the other hand, teachers have difficulties in monitoring students’ understanding and the discussion progress. Consequently, providing constructive feedback promptly becomes challenging. This study proposed an online collaborative summarizing feature to be integrated with the online discussion forum to facilitate the construction of a discussion summary. The tool was developed using the User-Centered Design (UCD) approach and tested using the usability evaluation. The participants (both students and lecturers) found that the usability of the developed system was good. This was indicated by the fact that more than 80% of the students and more than 80% of the lecturers were able to finish the tasks given easily. Furthermore, the SUS score exceeded the average score, meaning that students and lecturers found that the developed system had a good usability.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114196401","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 : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979737
Arfinda Ilmania, A. Purwarianti
Inspired by some research on entity level and aspect level sentiment analysis, we build a two-step classification system to tackle the challenges of targeted aspect-based sentiment analysis (TABSA). The system consists of aspect categorization and sentiment classification. We employ a Bi-LSTM network, position features i.e. context representation and positional embedding on both classifiers, and one-hot aspect vectors in sentiment classifier to give additional information. We conducted experiments using 900 Indonesian reviews related to automotive. Despite not using complex feature because of limitation in low-resource language, the system can still make decent prediction. We found that the use of positional embedding and context representation in our model is proven to be able to capture the relation between entity and aspect-sentiment. The use of one-hot aspect vectors was also found to be slightly helpful for sentiment classifier to capture polarity related to a specific aspect. Experiment results showed that our approach outperformed the self-training baseline in terms of F1 and accuracy scores.
{"title":"Positional Embedding and Context Representation for Indonesian Targeted Aspect-based Sentiment Analysis","authors":"Arfinda Ilmania, A. Purwarianti","doi":"10.1109/ICACSIS47736.2019.8979737","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979737","url":null,"abstract":"Inspired by some research on entity level and aspect level sentiment analysis, we build a two-step classification system to tackle the challenges of targeted aspect-based sentiment analysis (TABSA). The system consists of aspect categorization and sentiment classification. We employ a Bi-LSTM network, position features i.e. context representation and positional embedding on both classifiers, and one-hot aspect vectors in sentiment classifier to give additional information. We conducted experiments using 900 Indonesian reviews related to automotive. Despite not using complex feature because of limitation in low-resource language, the system can still make decent prediction. We found that the use of positional embedding and context representation in our model is proven to be able to capture the relation between entity and aspect-sentiment. The use of one-hot aspect vectors was also found to be slightly helpful for sentiment classifier to capture polarity related to a specific aspect. Experiment results showed that our approach outperformed the self-training baseline in terms of F1 and accuracy scores.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122666615","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 : 2019-10-01DOI: 10.1109/ICACSIS47736.2019.8979843
Bella Nadhifah Agustina, H. Santoso, S. Fadhilah
In this era, buying and selling transactions can be done through e-Commerce platforms. Because of the high demand, various types of e-Commerce companies began to appear. Some of the leading e-Commerce companies in Indonesia are Shopee, Tokopedia, and Bukalapak. The process of purchasing goods is essential in e-Commerce, making the system design of the process as a major concern. Therefore, this study aims to improve the usability of goods purchasing activity flow on the mobile version of the three leading e-Commerce platforms. Usability evaluation was done using mixed methods by combining quantitative and qualitative data. The quantitative data were obtained using online questionnaires, while the qualitative data were obtained using usability tests by mapping the results to Schneiderman’s Eight Golden Rules of the Interface Design. Online questionnaires were distributed to validate and to find problems that commonly occur in the process of purchasing goods. Usability testing was done to find the problems more deeply. From the overall study, 13 usability problems were found and an alternative design was devised to solve them and to improve the usability. Finally, the alternative design had also been evaluated with a 83-100% success rate for each task.
在这个时代，买卖交易可以通过电子商务平台来完成。由于高需求，各种类型的电子商务公司开始出现。印尼一些领先的电子商务公司是Shopee、Tokopedia和Bukalapak。在电子商务中，商品的购买过程是必不可少的，使得该过程的系统设计成为人们关注的重点。因此，本研究旨在提高三大领先电商平台移动版商品购买活动流程的可用性。可用性评价采用定量与定性相结合的方法进行。定量数据采用在线问卷的方式获取，定性数据采用可用性测试的方式获取，将结果映射到Schneiderman’s Eight Golden Rules of The Interface Design。发放在线调查问卷，以验证和发现在购买商品过程中常见的问题。可用性测试是为了更深入地发现问题。从整体研究中，发现了13个可用性问题，并设计了替代设计来解决这些问题并提高可用性。最后，备选设计也被评估为每个任务的83-100%的成功率。
{"title":"Usability Evaluation of Purchasing Activity Flow on Three Leading E-Commerce Platforms9 Mobile Version in Indonesia: Case Studies Shopee,Tokopedia, and Bukalapak","authors":"Bella Nadhifah Agustina, H. Santoso, S. Fadhilah","doi":"10.1109/ICACSIS47736.2019.8979843","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979843","url":null,"abstract":"In this era, buying and selling transactions can be done through e-Commerce platforms. Because of the high demand, various types of e-Commerce companies began to appear. Some of the leading e-Commerce companies in Indonesia are Shopee, Tokopedia, and Bukalapak. The process of purchasing goods is essential in e-Commerce, making the system design of the process as a major concern. Therefore, this study aims to improve the usability of goods purchasing activity flow on the mobile version of the three leading e-Commerce platforms. Usability evaluation was done using mixed methods by combining quantitative and qualitative data. The quantitative data were obtained using online questionnaires, while the qualitative data were obtained using usability tests by mapping the results to Schneiderman’s Eight Golden Rules of the Interface Design. Online questionnaires were distributed to validate and to find problems that commonly occur in the process of purchasing goods. Usability testing was done to find the problems more deeply. From the overall study, 13 usability problems were found and an alternative design was devised to solve them and to improve the usability. Finally, the alternative design had also been evaluated with a 83-100% success rate for each task.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125417370","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}
This study stems from actual challenges that we face in building a recommender system at Bukalapak. Our existing recommendation system, which is an item-to-item collaborative filtering based on co-view method has helped users during their shopping journey by offering them similar items recommendation in the product detail page. However, our baseline system has not utilized the information on how the user perceives the recommendation offered in our recommendation widget. This paper discusses how we improve our recommendation system with point-wise Learning-to-Rank (LTR) method. We also present specific features that support the LTR performance. Finally, we evaluate the LTR model by offline evaluation metrics and online A/B test, where we compare our baseline by using the model to rerank the candidates item before presenting them as recommendation sets. By calculating the Click Through Rate (CTR), it shows that the LTR method can outperform the baseline by 1.63%.
{"title":"Toward Improving Similar Item Recommendation for a C2C Marketplace","authors":"Lisbeth Evalina, Aditya Iftikar Riaddy, Septiviana Savitri, Reza Aditya Permadi","doi":"10.1109/ICACSIS47736.2019.8979770","DOIUrl":"https://doi.org/10.1109/ICACSIS47736.2019.8979770","url":null,"abstract":"This study stems from actual challenges that we face in building a recommender system at Bukalapak. Our existing recommendation system, which is an item-to-item collaborative filtering based on co-view method has helped users during their shopping journey by offering them similar items recommendation in the product detail page. However, our baseline system has not utilized the information on how the user perceives the recommendation offered in our recommendation widget. This paper discusses how we improve our recommendation system with point-wise Learning-to-Rank (LTR) method. We also present specific features that support the LTR performance. Finally, we evaluate the LTR model by offline evaluation metrics and online A/B test, where we compare our baseline by using the model to rerank the candidates item before presenting them as recommendation sets. By calculating the Click Through Rate (CTR), it shows that the LTR method can outperform the baseline by 1.63%.","PeriodicalId":165090,"journal":{"name":"2019 International Conference on Advanced Computer Science and information Systems (ICACSIS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130402952","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：