Pub Date : 2021-11-01DOI: 10.1109/taai54685.2021.00035
Y. Liu, Min Qi Huang
YouTube has become the largest video sharing site and its recommendation system significantly affects people’s perceptions and behaviors. This study examined whether the Matthew effect exists on YouTube’s recommendation system, and tested how the two factors (views and subscriptions) affect the recommendation results. The data was collected from YouTube by Python program and analyzed by statistical methods. The statistical results confirmed the existence of the Matthew effect and revealed the significant influences of channel views and subscriptions on play counts. The implications for researchers, users, business units and channel owners are discussed.
{"title":"Examining the Matthew Effect on YouTube Recommendation System","authors":"Y. Liu, Min Qi Huang","doi":"10.1109/taai54685.2021.00035","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00035","url":null,"abstract":"YouTube has become the largest video sharing site and its recommendation system significantly affects people’s perceptions and behaviors. This study examined whether the Matthew effect exists on YouTube’s recommendation system, and tested how the two factors (views and subscriptions) affect the recommendation results. The data was collected from YouTube by Python program and analyzed by statistical methods. The statistical results confirmed the existence of the Matthew effect and revealed the significant influences of channel views and subscriptions on play counts. The implications for researchers, users, business units and channel owners are discussed.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"337 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115422806","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 : 2021-11-01DOI: 10.1109/taai54685.2021.00046
Tran Anh Tuan, T. N. Thang, V. Vu, Doãn Dung, Thi Ngoc Anh Nguyen
Logistic regression is one of the regression analysis methods that was studied a long time ago and its applications are widely used in many classification tasks. In this paper, a stochastic model is proposed by our that calls stochastic logistic sigmoid regression. This problem is solved by the new approach that transforms a deterministic problem into a stochastic problem and solves it by a convex programming problem. Besides, to estimate the mean and variance-covariance matrix of random variables, clustering algorithms, and quantile estimation are applied. The effectiveness of the model is evaluated by metrics for evaluating the performance of logistic regression. The results of the proposed algorithms, which are overcome over 1 to 2 percent with an accuracy score on three datasets, include many different fields data. They are also better than the ordinary logistic regression model on the same dataset with evaluation metrics, examples: f1 score, precision score, recall score, confusion matrix, et cetera.
{"title":"A stochastic logistic sigmoid regression using convex programming and clustering","authors":"Tran Anh Tuan, T. N. Thang, V. Vu, Doãn Dung, Thi Ngoc Anh Nguyen","doi":"10.1109/taai54685.2021.00046","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00046","url":null,"abstract":"Logistic regression is one of the regression analysis methods that was studied a long time ago and its applications are widely used in many classification tasks. In this paper, a stochastic model is proposed by our that calls stochastic logistic sigmoid regression. This problem is solved by the new approach that transforms a deterministic problem into a stochastic problem and solves it by a convex programming problem. Besides, to estimate the mean and variance-covariance matrix of random variables, clustering algorithms, and quantile estimation are applied. The effectiveness of the model is evaluated by metrics for evaluating the performance of logistic regression. The results of the proposed algorithms, which are overcome over 1 to 2 percent with an accuracy score on three datasets, include many different fields data. They are also better than the ordinary logistic regression model on the same dataset with evaluation metrics, examples: f1 score, precision score, recall score, confusion matrix, et cetera.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115424926","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}
Different sources of risk factors can happen in sustainable supply chain management due to their complex nature. The telecommunication service firm cannot implement multiple improvement practices altogether to overcome the risk factors with limited resources. The industries should evaluate the relationship between risk factors and explore the determinants of improvement measures. The present study aims to analyses and identifies critical risk factors (CRFs) for enhancing sustainable supply chain management practices in the Indian telecommunication industry using the hybrid approach. The relationship among these CRFs has been analyzed by using fuzzy interpretive structural modelling (FISM) and Fuzzy decision-making trial and evaluation laboratory (FDEMATEL) methods to explore the relationships between them. The common result of the present study is that the risks government policies (laws and regulations) (R13) are the most affecting CRFs of the sustainable supply chain in telecom service. In addition, the risk factors illegal activities (e.g.2G scams) (R3), environmental pollution(R18) are indirectly affected by high driving power CRFs. Based on the results, the government could build justice, fairness, open laws, and certainties to prevent risk in the telecoms supply chain; service providers could monitor the rapidly evolving technologies. The contribution of this study is using a hybrid approach to establish a hierarchical structural model for an effective understanding of CRFs relationships and to explore decisive risk factors.
{"title":"Risk Management Analysis of the Sustainable Supply Chain Using a Fuzzy Hybrid Approach in India","authors":"Venkateswarlu Nalluri, Ching-Torng Lin, Long-Sheng Chen","doi":"10.1109/taai54685.2021.00041","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00041","url":null,"abstract":"Different sources of risk factors can happen in sustainable supply chain management due to their complex nature. The telecommunication service firm cannot implement multiple improvement practices altogether to overcome the risk factors with limited resources. The industries should evaluate the relationship between risk factors and explore the determinants of improvement measures. The present study aims to analyses and identifies critical risk factors (CRFs) for enhancing sustainable supply chain management practices in the Indian telecommunication industry using the hybrid approach. The relationship among these CRFs has been analyzed by using fuzzy interpretive structural modelling (FISM) and Fuzzy decision-making trial and evaluation laboratory (FDEMATEL) methods to explore the relationships between them. The common result of the present study is that the risks government policies (laws and regulations) (R13) are the most affecting CRFs of the sustainable supply chain in telecom service. In addition, the risk factors illegal activities (e.g.2G scams) (R3), environmental pollution(R18) are indirectly affected by high driving power CRFs. Based on the results, the government could build justice, fairness, open laws, and certainties to prevent risk in the telecoms supply chain; service providers could monitor the rapidly evolving technologies. The contribution of this study is using a hybrid approach to establish a hierarchical structural model for an effective understanding of CRFs relationships and to explore decisive risk factors.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116950355","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 : 2021-11-01DOI: 10.1109/taai54685.2021.00057
Rui-Fong Hong, S. Horng, Shieh-Shing Lin
Classification is the procedure to recognize, understand, as well as group ideas and objects into given categories. Classification techniques adopt training data patterns to predict the likelihood that subsequent data will classify into one of the given categories. Classification techniques utilize a variety of algorithms to classify future datasets through training data patterns. In current society, many network attacks continue to carry out various types of attacks. This work performs data pre-processing and uses Python with machine learning algorithms to analyze the NSL-KDD data set. We use various machine learning methods, such as decision trees, random forests, Naïve Bayes, KNN, Gradient Boosted Trees, and SVM to analyze the confusion matrix and predict the accuracy. We also draw the ROC curve and the AUC area. We calculate the ACC accuracy and make a simple assessment of the quality of different algorithms. Test results show that through data pre-processing, machine learning algorithms can be performed with extremely high accuracy.
{"title":"Machine Learning in Cyber Security Analytics using NSL-KDD Dataset","authors":"Rui-Fong Hong, S. Horng, Shieh-Shing Lin","doi":"10.1109/taai54685.2021.00057","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00057","url":null,"abstract":"Classification is the procedure to recognize, understand, as well as group ideas and objects into given categories. Classification techniques adopt training data patterns to predict the likelihood that subsequent data will classify into one of the given categories. Classification techniques utilize a variety of algorithms to classify future datasets through training data patterns. In current society, many network attacks continue to carry out various types of attacks. This work performs data pre-processing and uses Python with machine learning algorithms to analyze the NSL-KDD data set. We use various machine learning methods, such as decision trees, random forests, Naïve Bayes, KNN, Gradient Boosted Trees, and SVM to analyze the confusion matrix and predict the accuracy. We also draw the ROC curve and the AUC area. We calculate the ACC accuracy and make a simple assessment of the quality of different algorithms. Test results show that through data pre-processing, machine learning algorithms can be performed with extremely high accuracy.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123268566","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 : 2021-11-01DOI: 10.1109/taai54685.2021.00017
Chia-Fen Hsieh, Che-Min Su
The rapid development of network technology and related services has led to an increase in data traffic. Although some researches use machine learning (ML)-based intrusion detection schemes to detect intrusion. For network attacks, the changes in network traffic may lead to lower accuracy of machine learning-based models. It focuses on feature values ineffective learning materials, machine learning, and human learning similarly, and classifying data to analyze understanding, and take actions. The neural networks in deep learning used artificial neural network (ANNs) that imitate the functions of the human brain. Deep learning is a type of machine learning. The difference lies in inexperienced. In this paper, we proposed an intrusion detection architecture that based on a multi-layer neural network (MLNN). It processes data traffic and build a reliable intrusion detection model based on deep learning (DL). Compared with other machine learning or algorithms, Deep learning has the function of automatically extracting features and uses TensorFlow to execute Keras to analyze data. Through Keras, an open-source neural network library, intrusion detection targets can be achieved in a faster and more effective way. The main contribution of this paper includes considering various factors to evaluate and select, and let the integrated method perform intrusion detection.
{"title":"MLNN: A Novel Network Intrusion Detection Based on Multilayer Neural Network","authors":"Chia-Fen Hsieh, Che-Min Su","doi":"10.1109/taai54685.2021.00017","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00017","url":null,"abstract":"The rapid development of network technology and related services has led to an increase in data traffic. Although some researches use machine learning (ML)-based intrusion detection schemes to detect intrusion. For network attacks, the changes in network traffic may lead to lower accuracy of machine learning-based models. It focuses on feature values ineffective learning materials, machine learning, and human learning similarly, and classifying data to analyze understanding, and take actions. The neural networks in deep learning used artificial neural network (ANNs) that imitate the functions of the human brain. Deep learning is a type of machine learning. The difference lies in inexperienced. In this paper, we proposed an intrusion detection architecture that based on a multi-layer neural network (MLNN). It processes data traffic and build a reliable intrusion detection model based on deep learning (DL). Compared with other machine learning or algorithms, Deep learning has the function of automatically extracting features and uses TensorFlow to execute Keras to analyze data. Through Keras, an open-source neural network library, intrusion detection targets can be achieved in a faster and more effective way. The main contribution of this paper includes considering various factors to evaluate and select, and let the integrated method perform intrusion detection.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115096820","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 : 2021-11-01DOI: 10.1109/taai54685.2021.00064
Y. Cheng, Hui-Ting Chang, Chia-Yu Lin, Heng-Yu Chang
Peer-to-peer (P2P) lending provides borrowers with relatively low borrowing interest rates and gives lenders a channel for investment on an online platform. Since most P2P lending does not require any guarantees, the overdue payment of borrowers results in a massive loss of lending platforms and lenders. Many risk prediction models are proposed to predict credit risk. However, these works build models with more than 50 features, which causes a lot of computation time. Besides, in most P2P lending datasets, the number of non-default data far exceeds the number of default data. These researches ignore the data imbalance issue, leading to inaccurate predictions. Therefore, this study proposes a credit risk prediction system (CRPS) for P2P lending to solve data imbalance issues and only require few features to build the models. We implement a data preprocessing module, a feature selection module, a data synthesis module, and five risk prediction models in CRPS. In experiments, we evaluate CRPS based on the de-identified personal loan dataset of the LendingClub platform. The accuracy of the CRPS can achieve 99%, the recall reaches 0.95, and the F1-Score is 0.97. CRPS can accurately predict credit risk with less than 10 features and tackle data imbalance issues.
{"title":"Predicting Credit Risk in Peer-to-Peer Lending: A Machine Learning Approach with Few Features","authors":"Y. Cheng, Hui-Ting Chang, Chia-Yu Lin, Heng-Yu Chang","doi":"10.1109/taai54685.2021.00064","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00064","url":null,"abstract":"Peer-to-peer (P2P) lending provides borrowers with relatively low borrowing interest rates and gives lenders a channel for investment on an online platform. Since most P2P lending does not require any guarantees, the overdue payment of borrowers results in a massive loss of lending platforms and lenders. Many risk prediction models are proposed to predict credit risk. However, these works build models with more than 50 features, which causes a lot of computation time. Besides, in most P2P lending datasets, the number of non-default data far exceeds the number of default data. These researches ignore the data imbalance issue, leading to inaccurate predictions. Therefore, this study proposes a credit risk prediction system (CRPS) for P2P lending to solve data imbalance issues and only require few features to build the models. We implement a data preprocessing module, a feature selection module, a data synthesis module, and five risk prediction models in CRPS. In experiments, we evaluate CRPS based on the de-identified personal loan dataset of the LendingClub platform. The accuracy of the CRPS can achieve 99%, the recall reaches 0.95, and the F1-Score is 0.97. CRPS can accurately predict credit risk with less than 10 features and tackle data imbalance issues.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128365241","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 : 2021-11-01DOI: 10.1109/taai54685.2021.00044
T. Hong, Hao Chang, Shu-Min Li, Yu-Chuan Tsai
Erasable-itemset mining is often utilized by factories in production planning to find combinations of materials which could cause an acceptable loss if all items in the combination are not available. However, product databases can change over time: new materials or products may be introduced and out-of-date materials or products eliminated. Traditional erasable-itemset mining algorithms do not account for this. Thus, when mining erasable itemsets, we take such additional time information into account. Various temporal constraints (itemset lifespan definitions) are also discussed in this paper. We propose a general temporal erasable itemset mining approach, which, can successfully mine the desired results under different constraints. The experimental performance about the execution time and memory consumption of the proposed method is also shown.
{"title":"A Unified Temporal Erasable Itemset Mining Approach","authors":"T. Hong, Hao Chang, Shu-Min Li, Yu-Chuan Tsai","doi":"10.1109/taai54685.2021.00044","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00044","url":null,"abstract":"Erasable-itemset mining is often utilized by factories in production planning to find combinations of materials which could cause an acceptable loss if all items in the combination are not available. However, product databases can change over time: new materials or products may be introduced and out-of-date materials or products eliminated. Traditional erasable-itemset mining algorithms do not account for this. Thus, when mining erasable itemsets, we take such additional time information into account. Various temporal constraints (itemset lifespan definitions) are also discussed in this paper. We propose a general temporal erasable itemset mining approach, which, can successfully mine the desired results under different constraints. The experimental performance about the execution time and memory consumption of the proposed method is also shown.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126365923","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}
Topics regarding user behavior on online mobile games were widely discussed by scholars nowadays. As a relatively new topic, it is challenging for scholars to contributes theoretically and practically according to the user behavior in an online mobile game environment. Therefore, we investigate user behavior of online mobile games to understand the user in apps purchase intention. We conducted an online survey to 439 participants who have played online mobile games and experience purchase a game's features. Structural Equation Modelling was employed to test the research framework using Smart-PLS 3.0. The results show that user addiction behavior of online mobile games positively and significantly influences in-app purchase intention. We contribute to the addiction behavior of users regarding online mobile game use that generated purchase games features intention. Furthermore, the contributions are discussed in detail accordingly in the article.
{"title":"User Addiction Behavior Towards Online Mobile Games Influences In Apps Purchase Behavior","authors":"Andri Dayarana Kristanta Silalahi, Teguh Indra Bayu","doi":"10.1109/TAAI54685.2021.00066","DOIUrl":"https://doi.org/10.1109/TAAI54685.2021.00066","url":null,"abstract":"Topics regarding user behavior on online mobile games were widely discussed by scholars nowadays. As a relatively new topic, it is challenging for scholars to contributes theoretically and practically according to the user behavior in an online mobile game environment. Therefore, we investigate user behavior of online mobile games to understand the user in apps purchase intention. We conducted an online survey to 439 participants who have played online mobile games and experience purchase a game's features. Structural Equation Modelling was employed to test the research framework using Smart-PLS 3.0. The results show that user addiction behavior of online mobile games positively and significantly influences in-app purchase intention. We contribute to the addiction behavior of users regarding online mobile game use that generated purchase games features intention. Furthermore, the contributions are discussed in detail accordingly in the article.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"456 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125796812","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 : 2021-11-01DOI: 10.1109/taai54685.2021.00036
Fanchao Xu, Tomoyuki Kaneko
This paper studies cooperative multi-agent reinforcement learning problems where agents pursue a common goal through their cooperation. Because each agent needs to act individually on the basis on its local observation, the difficulty of learning depends on to what extent information can be exchanged among agents. We extend value-decomposition networks (VDN), a framework requiring the least communication, by allowing information exchange within a local group and present residual group VDN (RGV). We empirically show that the performance of RGV is better than VDN and other state-of-the-art methods in the predator-prey game. Also, on three tasks in the StarCraft Multi-Agent Challenge, RGV showed comparable performance with more sophisticated methods utilizing more information or communication. Therefore, our RGV is an alternative method worth further research.
{"title":"Local Coordination in Multi-Agent Reinforcement Learning","authors":"Fanchao Xu, Tomoyuki Kaneko","doi":"10.1109/taai54685.2021.00036","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00036","url":null,"abstract":"This paper studies cooperative multi-agent reinforcement learning problems where agents pursue a common goal through their cooperation. Because each agent needs to act individually on the basis on its local observation, the difficulty of learning depends on to what extent information can be exchanged among agents. We extend value-decomposition networks (VDN), a framework requiring the least communication, by allowing information exchange within a local group and present residual group VDN (RGV). We empirically show that the performance of RGV is better than VDN and other state-of-the-art methods in the predator-prey game. Also, on three tasks in the StarCraft Multi-Agent Challenge, RGV showed comparable performance with more sophisticated methods utilizing more information or communication. Therefore, our RGV is an alternative method worth further research.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131889350","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 purpose of this study is to apply the Innovation Diffusion Theory (IDT) to explore various factors affecting behavioral intentions among Vlog viewers, moreover, to understand related impacts on behavioral intentions of the Innovation Diffusion Theory with different background variables. This study uses online survey questionnaires for data collection and analysis. A total of 255 questionnaires of Vlog viewers across Taiwan were collected to test the hypothesized research model. A data analysis was performed using structural equation modelling(SEM). The results of the analysis fully supported the hypotheses and have revealed that the IDT has a direct and significant influence on the behavioral intention of Vlog Viewers. Further discussion of practical applications and future research is included.
{"title":"Factors Affecting Vlog Viewers' Behavioral Intentions: An Empirical Study Based on Innovation Diffusion Theory","authors":"Hsiao-Kuang Kao, Su-Nan Tsai, Wan-Ling Chang, Jui-Hsiu Chang","doi":"10.1109/taai54685.2021.00039","DOIUrl":"https://doi.org/10.1109/taai54685.2021.00039","url":null,"abstract":"The purpose of this study is to apply the Innovation Diffusion Theory (IDT) to explore various factors affecting behavioral intentions among Vlog viewers, moreover, to understand related impacts on behavioral intentions of the Innovation Diffusion Theory with different background variables. This study uses online survey questionnaires for data collection and analysis. A total of 255 questionnaires of Vlog viewers across Taiwan were collected to test the hypothesized research model. A data analysis was performed using structural equation modelling(SEM). The results of the analysis fully supported the hypotheses and have revealed that the IDT has a direct and significant influence on the behavioral intention of Vlog Viewers. Further discussion of practical applications and future research is included.","PeriodicalId":343821,"journal":{"name":"2021 International Conference on Technologies and Applications of Artificial Intelligence (TAAI)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124039099","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：