T. Cerný, Andrew Walker, J. Svacina, Vincent Bushong, Dipta Das, Karel Frajták, Miroslav Bures, Pavel Tisnovsky
Constraint consistency errors in distributed systems can lead to fatal consequences when left unobserved and undetected. The primary goal of quality engineers should be to avoid system inconsistencies in general. However, it is typically a much more straight forward process in monolith-like systems with one codebase than in distributed solutions where heterogeneity occurs across modules. In this paper, we raise the research question of what is the existing state-of-the-art and research literature practice when it comes to consistency checking in distributed systems. We conducted a systematic search for existing work and assess the evidence to categorize the approaches and to identify used techniques. Identified works offer interesting directions and achievements. Often the works share tool prototypes and instruments to build on the top of when performing further research in this direction and we share them in this paper. Finally, we discuss open challenges and gaps in this field to promote the interest of the research audience.
{"title":"Mapping Study on Constraint Consistency Checking in Distributed Enterprise Systems","authors":"T. Cerný, Andrew Walker, J. Svacina, Vincent Bushong, Dipta Das, Karel Frajták, Miroslav Bures, Pavel Tisnovsky","doi":"10.1145/3400286.3418257","DOIUrl":"https://doi.org/10.1145/3400286.3418257","url":null,"abstract":"Constraint consistency errors in distributed systems can lead to fatal consequences when left unobserved and undetected. The primary goal of quality engineers should be to avoid system inconsistencies in general. However, it is typically a much more straight forward process in monolith-like systems with one codebase than in distributed solutions where heterogeneity occurs across modules. In this paper, we raise the research question of what is the existing state-of-the-art and research literature practice when it comes to consistency checking in distributed systems. We conducted a systematic search for existing work and assess the evidence to categorize the approaches and to identify used techniques. Identified works offer interesting directions and achievements. Often the works share tool prototypes and instruments to build on the top of when performing further research in this direction and we share them in this paper. Finally, we discuss open challenges and gaps in this field to promote the interest of the research audience.","PeriodicalId":326100,"journal":{"name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125246252","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}
The technology of deep learning has grown rapidly and been widely used in the industry. In addition to the accuracy of the deep learning (DL) models, system developers are also interested in comprehending their performance aspects to make sure that the hardware design and the systems deployed to meet the application demands. However, developing a performance model to serve the aforementioned purpose needs to take many issues into account, e.g. the DL model, the runtime software, and the system architecture, which is quite complex. In this work, we propose a multi-layer regression network, called PerfNet, to predict the performance of DL models on heterogeneous systems. To train the PerfNet, we develop a tool to collect the performance features and characteristics of DL models on a set of heterogeneous systems, including key hyper-parameters such as loss functions, network shapes, and dataset size, as well as the hardware specifications. Our experiments show that the results of our approach are more accurate than previously published methods. In the case of VGG16 on GTX1080Ti, PerfNet yields a mean absolute percentage error of 20%, while the referenced work constantly overestimates with errors larger than 200%.
{"title":"PerfNet","authors":"Chuan-Chi Wang, Ying-Chiao Liao, Ming-Chang Kao, Wen-Yew Liang, Shih-Hao Hung","doi":"10.1145/3400286.3418245","DOIUrl":"https://doi.org/10.1145/3400286.3418245","url":null,"abstract":"The technology of deep learning has grown rapidly and been widely used in the industry. In addition to the accuracy of the deep learning (DL) models, system developers are also interested in comprehending their performance aspects to make sure that the hardware design and the systems deployed to meet the application demands. However, developing a performance model to serve the aforementioned purpose needs to take many issues into account, e.g. the DL model, the runtime software, and the system architecture, which is quite complex. In this work, we propose a multi-layer regression network, called PerfNet, to predict the performance of DL models on heterogeneous systems. To train the PerfNet, we develop a tool to collect the performance features and characteristics of DL models on a set of heterogeneous systems, including key hyper-parameters such as loss functions, network shapes, and dataset size, as well as the hardware specifications. Our experiments show that the results of our approach are more accurate than previously published methods. In the case of VGG16 on GTX1080Ti, PerfNet yields a mean absolute percentage error of 20%, while the referenced work constantly overestimates with errors larger than 200%.","PeriodicalId":326100,"journal":{"name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114876038","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}
J. Svacina, John E. Raffety, Connor Woodahl, Brooklynn Stone, T. Cerný, Miroslav Bures, Dongwan Shin, Karel Frajták, Pavel Tisnovsky
Log analysis is a technique of deriving knowledge from log files containing records of events in a computer system. A common application of log analysis is to derive critical information about a system's security issues and intrusions, which subsequently leads to being able to identify and potentially stop intruders attacking the system. However, many systems produce a high volume of log data with high frequency, posing serious challenges in analysis. This paper contributes with a systematic literature review and discusses current trends, advancements, and future directions in log security analysis within the past decade. We summarized current research strategies with respect to technology approaches from 34 current publications. We identified limitations that poses challenges to future research and opened discussion on issues towards logging mechanism in the software systems. Findings of this study are relevant for software systems as well as software parts of the Internet of Things (IoT) systems.
{"title":"On Vulnerability and Security Log analysis: A Systematic Literature Review on Recent Trends","authors":"J. Svacina, John E. Raffety, Connor Woodahl, Brooklynn Stone, T. Cerný, Miroslav Bures, Dongwan Shin, Karel Frajták, Pavel Tisnovsky","doi":"10.1145/3400286.3418261","DOIUrl":"https://doi.org/10.1145/3400286.3418261","url":null,"abstract":"Log analysis is a technique of deriving knowledge from log files containing records of events in a computer system. A common application of log analysis is to derive critical information about a system's security issues and intrusions, which subsequently leads to being able to identify and potentially stop intruders attacking the system. However, many systems produce a high volume of log data with high frequency, posing serious challenges in analysis. This paper contributes with a systematic literature review and discusses current trends, advancements, and future directions in log security analysis within the past decade. We summarized current research strategies with respect to technology approaches from 34 current publications. We identified limitations that poses challenges to future research and opened discussion on issues towards logging mechanism in the software systems. Findings of this study are relevant for software systems as well as software parts of the Internet of Things (IoT) systems.","PeriodicalId":326100,"journal":{"name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132232041","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}
Sentiment transfer has been explored as non-parallel transfer tasks in natural language processing. Previous works depend on a single encoder to disentangle either positive or negative style from its content and rely on a style representation to transfer the style attributes. Utilizing a single encoder to learn disentanglement in both styles might not sufficient due to the different characteristics of each sentiment represented by various vocabularies in the corresponding style. To this end, we propose a sequence to sequence CycleGAN which trains different text generators (encoder-decoder) for each style transfer direction. Learning disentangled latent representations leads previous works to high sentiment accuracy but suffer to preserve the content of the original sentences. In order to manage the content preservation, we pretrained our text generator as autoencoder using the identity loss. The model shows an improvement in sentiment accuracy and BLEU score which indicates better content preservation. It leads our model to a better overall performance compared to baselines.
{"title":"Sequence to Sequence CycleGAN for Non-Parallel Sentiment Transfer with Identity Loss Pretraining","authors":"Ida Ayu Putu Ari Crisdayanti, Jee-Hyong Lee","doi":"10.1145/3400286.3418249","DOIUrl":"https://doi.org/10.1145/3400286.3418249","url":null,"abstract":"Sentiment transfer has been explored as non-parallel transfer tasks in natural language processing. Previous works depend on a single encoder to disentangle either positive or negative style from its content and rely on a style representation to transfer the style attributes. Utilizing a single encoder to learn disentanglement in both styles might not sufficient due to the different characteristics of each sentiment represented by various vocabularies in the corresponding style. To this end, we propose a sequence to sequence CycleGAN which trains different text generators (encoder-decoder) for each style transfer direction. Learning disentangled latent representations leads previous works to high sentiment accuracy but suffer to preserve the content of the original sentences. In order to manage the content preservation, we pretrained our text generator as autoencoder using the identity loss. The model shows an improvement in sentiment accuracy and BLEU score which indicates better content preservation. It leads our model to a better overall performance compared to baselines.","PeriodicalId":326100,"journal":{"name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133915753","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}
Live migration is the process of moving an application of a running virtual machine between physical machines without disconnecting the client or application. In recent years, as cloud computing has developed at a rapid pace, numerous virtual systems have been developed, and container-type operating system level virtualization technology, which is attracting attention at a higher speed and lower resource consumption rate than a virtual machine which use Hypervisor. The tool that deploys and manages these containers is called a container orchestration tool, and the most widely used orchestration framework is Kubernetes. Currently, there is no function for live migration in Kubernetes. In this paper, we developed an environment where containers can be live migration in Kubernetes, and research was conducted to reduce downtime of live migration.
{"title":"Design and Implementation of Migration Manager between Cloud Edge Platforms","authors":"Taehyuk Heo, J. An, Younghwan Kim","doi":"10.1145/3400286.3418279","DOIUrl":"https://doi.org/10.1145/3400286.3418279","url":null,"abstract":"Live migration is the process of moving an application of a running virtual machine between physical machines without disconnecting the client or application. In recent years, as cloud computing has developed at a rapid pace, numerous virtual systems have been developed, and container-type operating system level virtualization technology, which is attracting attention at a higher speed and lower resource consumption rate than a virtual machine which use Hypervisor. The tool that deploys and manages these containers is called a container orchestration tool, and the most widely used orchestration framework is Kubernetes. Currently, there is no function for live migration in Kubernetes. In this paper, we developed an environment where containers can be live migration in Kubernetes, and research was conducted to reduce downtime of live migration.","PeriodicalId":326100,"journal":{"name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126975721","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}
Wireless Body Area Network(WBAN) has developed as a technique for healthcare systems. In WBAN, patients can be remotely and constantly monitored by tiny wearable and portable sensors. The sensors collect patients' vital activity and movement data. Afterwards the data is sent via short-range wireless communication techniques to a data reader device which is called as a server. Since it is using shared wireless network, it may have chances to be attacked by unexpected adversaries. Therefore, security issues of WBAN are rapidly growing in the field of healthcare. Moreover, we need to care about the sensors' battery consumption and computation power because of resource-constrained WBAN. The sensors should be small and compact since they are located in, on, and around the patient's body for a long time. As a result, it is difficult to give a large battery capacity and strong computational power to the sensors. Thus, this paper proposes an authentication protocol which provides high level security and requires significantly low computation power on sensors for WBAN by using Elliptic Curves Cryptography(ECC) and two-dimensional hash chain techniques. The authentication procedure is very simple especially on the sensor side and 2D hash chain's key pool generation is also simple and efficient. Therefore, our protocol can be easily implemented in the power and resource constrained sensor nodes in WBAN.
{"title":"Secure and low computation authentication protocol for Wireless Body Area Network with ECC and 2D hash chain","authors":"Soohyeon Choi, Sangwon Shin, Xiaozhu Jin, Sung Shin","doi":"10.1145/3400286.3418256","DOIUrl":"https://doi.org/10.1145/3400286.3418256","url":null,"abstract":"Wireless Body Area Network(WBAN) has developed as a technique for healthcare systems. In WBAN, patients can be remotely and constantly monitored by tiny wearable and portable sensors. The sensors collect patients' vital activity and movement data. Afterwards the data is sent via short-range wireless communication techniques to a data reader device which is called as a server. Since it is using shared wireless network, it may have chances to be attacked by unexpected adversaries. Therefore, security issues of WBAN are rapidly growing in the field of healthcare. Moreover, we need to care about the sensors' battery consumption and computation power because of resource-constrained WBAN. The sensors should be small and compact since they are located in, on, and around the patient's body for a long time. As a result, it is difficult to give a large battery capacity and strong computational power to the sensors. Thus, this paper proposes an authentication protocol which provides high level security and requires significantly low computation power on sensors for WBAN by using Elliptic Curves Cryptography(ECC) and two-dimensional hash chain techniques. The authentication procedure is very simple especially on the sensor side and 2D hash chain's key pool generation is also simple and efficient. Therefore, our protocol can be easily implemented in the power and resource constrained sensor nodes in WBAN.","PeriodicalId":326100,"journal":{"name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115843557","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}
Neural Architecture Search (NAS) is a technique for finding suitable neural network architecture models for given applications. Previously, such search methods are usually based on reinforcement learning, with a recurrent neural network to generate neural network models. However, most NAS methods aim to find a set of candidates with best cost-performance ratios, e.g. high accuracy and low computing time, based on rough estimates derived from the workload generically. As today's deep learning chips accelerate neural network operations with a variety of hardware tricks such as vectors and low-precision data formats, the estimated metrics derived from generic computing operations such as float-point operations (FLOPS) would be very different from the actual latency, throughput, power consumption, etc., which are highly sensitive to the hardware design and even the software optimization in edge AI applications. Thus, instead of taking a long time to pick and train so called good candidates repeatedly based on unreliable estimates, we propose a NAS framework which accelerates the search process by including the actual performance measurements in the search process. The inclusion of actual measurements enables the proposed NAS framework to find candidates based on correct information and reduce the possibility of selecting wrong candidates and wasting search time on wrong candidates. To illustrate the effectiveness of our framework, we prototyped the framework to work with Intel OpenVINO and Field Programmable Gate Arrays (FPGA) to meet the accuracy and latency required by the user. The framework takes the dataset, accuracy and latency requirements from the user and automatically search for candidates to meet the requirements. Case studies and experimental results are presented in this paper to evaluate the effectiveness of our framework for Edge AI applications in real-time image classification.
{"title":"Toward Fast Platform-Aware Neural Architecture Search for FPGA-Accelerated Edge AI Applications","authors":"Yi-Chuan Liang, Ying-Chiao Liao, Chen-Ching Lin, Shih-Hao Hung","doi":"10.1145/3400286.3418240","DOIUrl":"https://doi.org/10.1145/3400286.3418240","url":null,"abstract":"Neural Architecture Search (NAS) is a technique for finding suitable neural network architecture models for given applications. Previously, such search methods are usually based on reinforcement learning, with a recurrent neural network to generate neural network models. However, most NAS methods aim to find a set of candidates with best cost-performance ratios, e.g. high accuracy and low computing time, based on rough estimates derived from the workload generically. As today's deep learning chips accelerate neural network operations with a variety of hardware tricks such as vectors and low-precision data formats, the estimated metrics derived from generic computing operations such as float-point operations (FLOPS) would be very different from the actual latency, throughput, power consumption, etc., which are highly sensitive to the hardware design and even the software optimization in edge AI applications. Thus, instead of taking a long time to pick and train so called good candidates repeatedly based on unreliable estimates, we propose a NAS framework which accelerates the search process by including the actual performance measurements in the search process. The inclusion of actual measurements enables the proposed NAS framework to find candidates based on correct information and reduce the possibility of selecting wrong candidates and wasting search time on wrong candidates. To illustrate the effectiveness of our framework, we prototyped the framework to work with Intel OpenVINO and Field Programmable Gate Arrays (FPGA) to meet the accuracy and latency required by the user. The framework takes the dataset, accuracy and latency requirements from the user and automatically search for candidates to meet the requirements. Case studies and experimental results are presented in this paper to evaluate the effectiveness of our framework for Edge AI applications in real-time image classification.","PeriodicalId":326100,"journal":{"name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115634818","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 aims to learn task-agnostic representations of narrative multimedia. The existing studies focused on only stories in the narrative multimedia without considering their physical features. We propose a method for incorporating multi-modal features of the narrative multimedia into a unified vector representation. For narrative features, we embed character networks as with the existing studies. Textual features can be represented using the LSTM (Long-Short Term Memory) autoencoder. We apply the convolutional autoencoder to visual features. The convolutional autoencoder also can be used for the spectrograms of audible features. To combine these features, we propose two methods: early fusion and late fusion. The early fusion method composes representations of features on each scene. Then, we learn representations of a narrative work by predicting time-sequential changes in the features. The late fusion method concatenates feature vectors that are trained for allover the narrative work. Finally, we apply the proposed methods on webtoons (i.e., comics that are serially published through the web). The proposed methods have been evaluated by applying the vector representations to predicting the preferences of users for the webtoons.
{"title":"Learning Multi-modal Representations of Narrative Multimedia: a Case Study of Webtoons","authors":"O-Joun Lee, Jin-Taek Kim","doi":"10.1145/3400286.3418216","DOIUrl":"https://doi.org/10.1145/3400286.3418216","url":null,"abstract":"This study aims to learn task-agnostic representations of narrative multimedia. The existing studies focused on only stories in the narrative multimedia without considering their physical features. We propose a method for incorporating multi-modal features of the narrative multimedia into a unified vector representation. For narrative features, we embed character networks as with the existing studies. Textual features can be represented using the LSTM (Long-Short Term Memory) autoencoder. We apply the convolutional autoencoder to visual features. The convolutional autoencoder also can be used for the spectrograms of audible features. To combine these features, we propose two methods: early fusion and late fusion. The early fusion method composes representations of features on each scene. Then, we learn representations of a narrative work by predicting time-sequential changes in the features. The late fusion method concatenates feature vectors that are trained for allover the narrative work. Finally, we apply the proposed methods on webtoons (i.e., comics that are serially published through the web). The proposed methods have been evaluated by applying the vector representations to predicting the preferences of users for the webtoons.","PeriodicalId":326100,"journal":{"name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124921332","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}
Identity verification, security and confidentiality are the most important topics in computer system security. Many solutions have been proposed to users to enhance the security of authentication methods based on login passwords. Mainly through the use of two-factor authentication methods. Complex systems are difficult to build and to manage, one of the major problems for cyber-physical systems is the vulnerability of authentication and provide a high efficient tunnel to transmit the program or service data. Using more features for identification will increase the difficulty of fraud. The vigorous development of biometric identification technology in recent years has also made the identification of multiple traits more feasible. This paper presents a three-factor authentication with key agreement scheme for cyber-physical systems. The proposed mechanism integrates biometrics information, IMSI identifier and identity-based remote mutual authentication scheme on elliptic curve cryptography (ECC). It supports flawless three-factor and mutual authentication of participants and agreement of session key. The proposed mechanism does not require modifying the software of clients; thus, it is highly flexible. We believe the proposed mechanism is usable for cyber-physical systems applications.
{"title":"A Three-Factor Mutual Authentication Scheme for Cyber-Physical Systems","authors":"Yung-Feng Lu, Chin-Fu Kuo, Hung-Ming Chen, Hsueh-Wen Tseng, Shih-Chun Chou, Yu-Ming Liao","doi":"10.1145/3400286.3418236","DOIUrl":"https://doi.org/10.1145/3400286.3418236","url":null,"abstract":"Identity verification, security and confidentiality are the most important topics in computer system security. Many solutions have been proposed to users to enhance the security of authentication methods based on login passwords. Mainly through the use of two-factor authentication methods. Complex systems are difficult to build and to manage, one of the major problems for cyber-physical systems is the vulnerability of authentication and provide a high efficient tunnel to transmit the program or service data. Using more features for identification will increase the difficulty of fraud. The vigorous development of biometric identification technology in recent years has also made the identification of multiple traits more feasible. This paper presents a three-factor authentication with key agreement scheme for cyber-physical systems. The proposed mechanism integrates biometrics information, IMSI identifier and identity-based remote mutual authentication scheme on elliptic curve cryptography (ECC). It supports flawless three-factor and mutual authentication of participants and agreement of session key. The proposed mechanism does not require modifying the software of clients; thus, it is highly flexible. We believe the proposed mechanism is usable for cyber-physical systems applications.","PeriodicalId":326100,"journal":{"name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129457202","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}
Giang T. C. Tran, Luong Vuong Nguyen, Jason J. Jung, Jeonghun Han
In this paper, we propose a model based on user loyalty to understand user behavior. User loyalty is defined based on three factors, which are coverage, duration, and enthusiasm. In particular, we focus on a case study of user loyalty involving South Korean politics in online social networks. Our purpose is to understand user behaviors to help governments and politicians in decision-making. We deploy a web-based system (called TubePlunger) to collect information from Youtube videos and corresponding comments. Our system collects approximately 3M comments of more than 300K users from six channels for the initial dataset and 23 channels for testing the model. Firstly, we separate six channels into two sides: left-wing and right-wing. Based on their comments information in videos of the channel, we recognize the loyalty distribution of users who engaged in online political platforms is sharply polarized. In this step, we only consider the usernames instead of video and comment contents. Secondly, we apply the user loyalty model not only to define which channels of 23 testing channels belong to left-wing or right-wing but also to present the user loyalty distribution. The experimental results show the absolute consistency in user loyalty distribution with left-wing and right-wing in all three mentioned factors.
{"title":"Modeling User Loyalty for Korean Political YouTube Channels","authors":"Giang T. C. Tran, Luong Vuong Nguyen, Jason J. Jung, Jeonghun Han","doi":"10.1145/3400286.3418254","DOIUrl":"https://doi.org/10.1145/3400286.3418254","url":null,"abstract":"In this paper, we propose a model based on user loyalty to understand user behavior. User loyalty is defined based on three factors, which are coverage, duration, and enthusiasm. In particular, we focus on a case study of user loyalty involving South Korean politics in online social networks. Our purpose is to understand user behaviors to help governments and politicians in decision-making. We deploy a web-based system (called TubePlunger) to collect information from Youtube videos and corresponding comments. Our system collects approximately 3M comments of more than 300K users from six channels for the initial dataset and 23 channels for testing the model. Firstly, we separate six channels into two sides: left-wing and right-wing. Based on their comments information in videos of the channel, we recognize the loyalty distribution of users who engaged in online political platforms is sharply polarized. In this step, we only consider the usernames instead of video and comment contents. Secondly, we apply the user loyalty model not only to define which channels of 23 testing channels belong to left-wing or right-wing but also to present the user loyalty distribution. The experimental results show the absolute consistency in user loyalty distribution with left-wing and right-wing in all three mentioned factors.","PeriodicalId":326100,"journal":{"name":"Proceedings of the International Conference on Research in Adaptive and Convergent Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2020-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127952571","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：