Pub Date : 2021-06-28DOI: 10.1108/idd-12-2020-0160
Mingyan Zhang, Xu Du, K. Rice, Jui-Long Hung, Hao Li
Purpose This study aims to propose a learning pattern analysis method which can improve a predictive model’s performance, as well as discover hidden insights into micro-level learning pattern. Analyzing student’s learning patterns can help instructors understand how their course design or activities shape learning behaviors; depict students’ beliefs about learning and their motivation; and predict learning performance by analyzing individual students’ learning patterns. Although time-series analysis is one of the most feasible predictive methods for learning pattern analysis, literature-indicated current approaches cannot provide holistic insights about learning patterns for personalized intervention. This study identified at-risk students by micro-level learning pattern analysis and detected pattern types, especially at-risk patterns that existed in the case study. The connections among students’ learning patterns, corresponding self-regulated learning (SRL) strategies and learning performance were finally revealed. Design/methodology/approach The method used long short-term memory (LSTM)-encoder to process micro-level behavioral patterns for feature extraction and compression, thus the students’ behavior pattern information were saved into encoded series. The encoded time-series data were then used for pattern analysis and performance prediction. Time series clustering were performed to interpret the unique strength of proposed method. Findings Successful students showed consistent participation levels and balanced behavioral frequency distributions. The successful students also adjusted learning behaviors to meet with course requirements accordingly. The three at-risk patten types showed the low-engagement (R1) the low-interaction (R2) and the non-persistent characteristics (R3). Successful students showed more complete SRL strategies than failed students. Political Science had higher at-risk chances in all three at-risk types. Computer Science, Earth Science and Economics showed higher chances of having R3 students. Research limitations/implications The study identified multiple learning patterns which can lead to the at-risk situation. However, more studies are needed to validate whether the same at-risk types can be found in other educational settings. In addition, this case study found the distributions of at-risk types were vary in different subjects. The relationship between subjects and at-risk types is worth further investigation. Originality/value This study found the proposed method can effectively extract micro-level behavioral information to generate better prediction outcomes and depict student’s SRL learning strategies in online learning. The authors confirm that the research in their work is original, and that all the data given in the paper are real and authentic. The study has not been submitted to peer review and not has been accepted for publishing in another journal.
{"title":"Revealing at-risk learning patterns and corresponding self-regulated strategies via LSTM encoder and time-series clustering","authors":"Mingyan Zhang, Xu Du, K. Rice, Jui-Long Hung, Hao Li","doi":"10.1108/idd-12-2020-0160","DOIUrl":"https://doi.org/10.1108/idd-12-2020-0160","url":null,"abstract":"\u0000Purpose\u0000This study aims to propose a learning pattern analysis method which can improve a predictive model’s performance, as well as discover hidden insights into micro-level learning pattern. Analyzing student’s learning patterns can help instructors understand how their course design or activities shape learning behaviors; depict students’ beliefs about learning and their motivation; and predict learning performance by analyzing individual students’ learning patterns. Although time-series analysis is one of the most feasible predictive methods for learning pattern analysis, literature-indicated current approaches cannot provide holistic insights about learning patterns for personalized intervention. This study identified at-risk students by micro-level learning pattern analysis and detected pattern types, especially at-risk patterns that existed in the case study. The connections among students’ learning patterns, corresponding self-regulated learning (SRL) strategies and learning performance were finally revealed.\u0000\u0000\u0000Design/methodology/approach\u0000The method used long short-term memory (LSTM)-encoder to process micro-level behavioral patterns for feature extraction and compression, thus the students’ behavior pattern information were saved into encoded series. The encoded time-series data were then used for pattern analysis and performance prediction. Time series clustering were performed to interpret the unique strength of proposed method.\u0000\u0000\u0000Findings\u0000Successful students showed consistent participation levels and balanced behavioral frequency distributions. The successful students also adjusted learning behaviors to meet with course requirements accordingly. The three at-risk patten types showed the low-engagement (R1) the low-interaction (R2) and the non-persistent characteristics (R3). Successful students showed more complete SRL strategies than failed students. Political Science had higher at-risk chances in all three at-risk types. Computer Science, Earth Science and Economics showed higher chances of having R3 students.\u0000\u0000\u0000Research limitations/implications\u0000The study identified multiple learning patterns which can lead to the at-risk situation. However, more studies are needed to validate whether the same at-risk types can be found in other educational settings. In addition, this case study found the distributions of at-risk types were vary in different subjects. The relationship between subjects and at-risk types is worth further investigation.\u0000\u0000\u0000Originality/value\u0000This study found the proposed method can effectively extract micro-level behavioral information to generate better prediction outcomes and depict student’s SRL learning strategies in online learning. The authors confirm that the research in their work is original, and that all the data given in the paper are real and authentic. The study has not been submitted to peer review and not has been accepted for publishing in another journal.\u0000","PeriodicalId":43488,"journal":{"name":"Information Discovery and Delivery","volume":" ","pages":""},"PeriodicalIF":2.1,"publicationDate":"2021-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45297818","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 : 2021-06-17DOI: 10.1108/idd-10-2020-0128
Amos Shibambu, N. Marutha
Purpose The purpose of this paper is to investigate a framework for management of digital records on the cloud in South Africa. Design/methodology/approach This qualitative case study used semi-structured interviews and document analysis to collect data from regulatory documents, records practitioners and chief information officers in the national government departments in South Africa. Findings This study reveals that despite the advent of cloud computing, government is still struggling with manual paper-based records challenges, as they have not developed a government-owned cloud in which to manage and dispose records. Practical implications Technological advancements have brought about dramatic changes to the management and disposition of records since cloud computing emerged. The traction gained by cloud computing influences how records are managed and disposed in the cloud storage. Currently, the South African Government manages and disposes records in the government premises as stipulated by the National Archives and Records Service of South Africa Act (1996). This is enforced by the National Archives and Records Service of South Africa, which is the government records regulator because records are on paper-based, microfilms and audio-visual formats. It is hoped that the recommendations and framework proposed in this study may assist the government and related sectors in the adoption and implementation of the cloud computing system for records management and disposal. This may assist in resolving challenges such as missing files, damaged records and archives and long turnaround time for retrieval of records. Social implications In South Africa, the digital records are securely stored in storage mediums such as hard drives and USBs, to mention but a few. In addition to digital obsolescence faced by the storage mediums, global access to information is hindered because information is limited to those who can visit the archival holdings. The alternative option is to manage and dispose of records in the cloud. The framework and recommendations in this study may also assist in improving information, archives and records management policies and service delivery to the community at large. The framework proposed may be applied as a theory for framing future studies in the same area of cloud computing and used as a resource to guide other future studies and policymakers. Originality/value This study provides a framework for management of digital records on the cloud in South Africa. It also proposes the promulgation of the Cloud Act to promote unlimited access to state heritage, regardless of time and location. This study is framed on the Digital Curation Centre Life Cycle Model.
{"title":"A framework for management of digital records on the cloud in the public sector of South Africa","authors":"Amos Shibambu, N. Marutha","doi":"10.1108/idd-10-2020-0128","DOIUrl":"https://doi.org/10.1108/idd-10-2020-0128","url":null,"abstract":"\u0000Purpose\u0000The purpose of this paper is to investigate a framework for management of digital records on the cloud in South Africa.\u0000\u0000\u0000Design/methodology/approach\u0000This qualitative case study used semi-structured interviews and document analysis to collect data from regulatory documents, records practitioners and chief information officers in the national government departments in South Africa.\u0000\u0000\u0000Findings\u0000This study reveals that despite the advent of cloud computing, government is still struggling with manual paper-based records challenges, as they have not developed a government-owned cloud in which to manage and dispose records.\u0000\u0000\u0000Practical implications\u0000Technological advancements have brought about dramatic changes to the management and disposition of records since cloud computing emerged. The traction gained by cloud computing influences how records are managed and disposed in the cloud storage. Currently, the South African Government manages and disposes records in the government premises as stipulated by the National Archives and Records Service of South Africa Act (1996). This is enforced by the National Archives and Records Service of South Africa, which is the government records regulator because records are on paper-based, microfilms and audio-visual formats. It is hoped that the recommendations and framework proposed in this study may assist the government and related sectors in the adoption and implementation of the cloud computing system for records management and disposal. This may assist in resolving challenges such as missing files, damaged records and archives and long turnaround time for retrieval of records.\u0000\u0000\u0000Social implications\u0000In South Africa, the digital records are securely stored in storage mediums such as hard drives and USBs, to mention but a few. In addition to digital obsolescence faced by the storage mediums, global access to information is hindered because information is limited to those who can visit the archival holdings. The alternative option is to manage and dispose of records in the cloud. The framework and recommendations in this study may also assist in improving information, archives and records management policies and service delivery to the community at large. The framework proposed may be applied as a theory for framing future studies in the same area of cloud computing and used as a resource to guide other future studies and policymakers.\u0000\u0000\u0000Originality/value\u0000This study provides a framework for management of digital records on the cloud in South Africa. It also proposes the promulgation of the Cloud Act to promote unlimited access to state heritage, regardless of time and location. This study is framed on the Digital Curation Centre Life Cycle Model.\u0000","PeriodicalId":43488,"journal":{"name":"Information Discovery and Delivery","volume":"1 1","pages":""},"PeriodicalIF":2.1,"publicationDate":"2021-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41371830","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 : 2021-04-05DOI: 10.1108/IDD-04-2020-0044
Nasser Assery, Y. Xiaohong, Qu Xiuli, Roy Kaushik, S. Almalki
PurposeThis study aims to propose an unsupervised learning model to evaluate the credibility of disaster-related Twitter data and present a performance comparison with commonly used supervised machine learning models.Design/methodology/approachFirst historical tweets on two recent hurricane events are collected via Twitter API. Then a credibility scoring system is implemented in which the tweet features are analyzed to give a credibility score and credibility label to the tweet. After that, supervised machine learning classification is implemented using various classification algorithms and their performances are compared.FindingsThe proposed unsupervised learning model could enhance the emergency response by providing a fast way to determine the credibility of disaster-related tweets. Additionally, the comparison of the supervised classification models reveals that the Random Forest classifier performs significantly better than the SVM and Logistic Regression classifiers in classifying the credibility of disaster-related tweets.Originality/valueIn this paper, an unsupervised 10-point scoring model is proposed to evaluate the tweets’ credibility based on the user-based and content-based features. This technique could be used to evaluate the credibility of disaster-related tweets on future hurricanes and would have the potential to enhance emergency response during critical events. The comparative study of different supervised learning methods has revealed effective supervised learning methods for evaluating the credibility of Tweeter data.
{"title":"Evaluating disaster-related tweet credibility using content-based and user-based features","authors":"Nasser Assery, Y. Xiaohong, Qu Xiuli, Roy Kaushik, S. Almalki","doi":"10.1108/IDD-04-2020-0044","DOIUrl":"https://doi.org/10.1108/IDD-04-2020-0044","url":null,"abstract":"PurposeThis study aims to propose an unsupervised learning model to evaluate the credibility of disaster-related Twitter data and present a performance comparison with commonly used supervised machine learning models.Design/methodology/approachFirst historical tweets on two recent hurricane events are collected via Twitter API. Then a credibility scoring system is implemented in which the tweet features are analyzed to give a credibility score and credibility label to the tweet. After that, supervised machine learning classification is implemented using various classification algorithms and their performances are compared.FindingsThe proposed unsupervised learning model could enhance the emergency response by providing a fast way to determine the credibility of disaster-related tweets. Additionally, the comparison of the supervised classification models reveals that the Random Forest classifier performs significantly better than the SVM and Logistic Regression classifiers in classifying the credibility of disaster-related tweets.Originality/valueIn this paper, an unsupervised 10-point scoring model is proposed to evaluate the tweets’ credibility based on the user-based and content-based features. This technique could be used to evaluate the credibility of disaster-related tweets on future hurricanes and would have the potential to enhance emergency response during critical events. The comparative study of different supervised learning methods has revealed effective supervised learning methods for evaluating the credibility of Tweeter data.","PeriodicalId":43488,"journal":{"name":"Information Discovery and Delivery","volume":" ","pages":""},"PeriodicalIF":2.1,"publicationDate":"2021-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46914863","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 : 2021-02-08DOI: 10.1108/IDD-06-2020-0064
S. Olaleye, I. T. Sanusi, R. Agjei, F. Adusei-Mensah
Purpose Drivers, travellers/tourists, pedestrians, paramedical officers, road safety officers, police officers and other security agencies in emergency times in developing countries are often challenged. The purpose of this paper is to explore the intervention of a quick mobile contact called “My Contact Person” (MCP) during such emergencies. Design/methodology/approach This study used a quantitative research method to collect data. The research tool is a researcher-made questionnaire with items developed using the five innovation dimensions and domestication. The data was analyzed with SmartPLS 3.0 software. The reliability values were above the postulated demarcation of 0.7, while the average variance extracted conforms to the norm of 0.5. The study participants were mobile phone users who own and use a mobile phone. Owing to the study’s nature, a simple random sampling technique was used to appraise 196 respondents across Nigeria’s demography. Findings The results show that the mobile users in a developing context are willing to observe “MCP’s” efficacy before they try to appropriate it to their daily lifestyle. Further, “MCP’s” compatibility with the telephone user is an antecedent of its relative advantages over the existing telephone lists. The results reveal that the respondents perceived integrating and adapting “MCP” to their daily lives as a complicated process. In this study, most participants did not regard observability and trialability as a means of appropriating MCP to their daily lifestyle. Research limitations/implications This paper’s findings’ generalizability is limited because the present study was conducted using two higher education institutions (HEI) with a relatively small sample in Nigeria. Probing MCP domestication in more institutions and other communities, as significant communities’ aside HEI use mobile phones will increase our research findings’ generalizability. A parallel investigation of a range of developed and developing countries should be explored to ascertain mobile phone users’ perceptions across context. Practical implications This study has several implications for citizens, especially in the developing world. MCP will provide quick contact opportunities to loved ones of the traumatized, saving lives by significantly avoiding worry, fear, anxiety and depression. MCP also has the potential of increasing input needs to be undertaken to accelerate the appropriate use of digital technology by health-care consumers, including enhancing education and technological literacy and providing access to low-cost digital technology. Originality/value “MCP” will be a quick intervention for drivers, travellers/tourists, pedestrians, paramedical officers, road safety officers, police officers and other security agencies in the time of emergency. For the managers, the relative advantage is the preferable factor to create awareness for “MCP”, while observability needs more effort to persuade the mobile phone user
{"title":"Please call my contact person: mobile devices for a rescue mission during an emergency","authors":"S. Olaleye, I. T. Sanusi, R. Agjei, F. Adusei-Mensah","doi":"10.1108/IDD-06-2020-0064","DOIUrl":"https://doi.org/10.1108/IDD-06-2020-0064","url":null,"abstract":"\u0000Purpose\u0000Drivers, travellers/tourists, pedestrians, paramedical officers, road safety officers, police officers and other security agencies in emergency times in developing countries are often challenged. The purpose of this paper is to explore the intervention of a quick mobile contact called “My Contact Person” (MCP) during such emergencies.\u0000\u0000\u0000Design/methodology/approach\u0000This study used a quantitative research method to collect data. The research tool is a researcher-made questionnaire with items developed using the five innovation dimensions and domestication. The data was analyzed with SmartPLS 3.0 software. The reliability values were above the postulated demarcation of 0.7, while the average variance extracted conforms to the norm of 0.5. The study participants were mobile phone users who own and use a mobile phone. Owing to the study’s nature, a simple random sampling technique was used to appraise 196 respondents across Nigeria’s demography.\u0000\u0000\u0000Findings\u0000The results show that the mobile users in a developing context are willing to observe “MCP’s” efficacy before they try to appropriate it to their daily lifestyle. Further, “MCP’s” compatibility with the telephone user is an antecedent of its relative advantages over the existing telephone lists. The results reveal that the respondents perceived integrating and adapting “MCP” to their daily lives as a complicated process. In this study, most participants did not regard observability and trialability as a means of appropriating MCP to their daily lifestyle.\u0000\u0000\u0000Research limitations/implications\u0000This paper’s findings’ generalizability is limited because the present study was conducted using two higher education institutions (HEI) with a relatively small sample in Nigeria. Probing MCP domestication in more institutions and other communities, as significant communities’ aside HEI use mobile phones will increase our research findings’ generalizability. A parallel investigation of a range of developed and developing countries should be explored to ascertain mobile phone users’ perceptions across context.\u0000\u0000\u0000Practical implications\u0000This study has several implications for citizens, especially in the developing world. MCP will provide quick contact opportunities to loved ones of the traumatized, saving lives by significantly avoiding worry, fear, anxiety and depression. MCP also has the potential of increasing input needs to be undertaken to accelerate the appropriate use of digital technology by health-care consumers, including enhancing education and technological literacy and providing access to low-cost digital technology.\u0000\u0000\u0000Originality/value\u0000“MCP” will be a quick intervention for drivers, travellers/tourists, pedestrians, paramedical officers, road safety officers, police officers and other security agencies in the time of emergency. For the managers, the relative advantage is the preferable factor to create awareness for “MCP”, while observability needs more effort to persuade the mobile phone user","PeriodicalId":43488,"journal":{"name":"Information Discovery and Delivery","volume":" ","pages":""},"PeriodicalIF":2.1,"publicationDate":"2021-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49178710","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 : 2021-01-21DOI: 10.1108/IDD-08-2020-0106
Erick Mendez Guzman, Ziqi Zhang, W. Ahmed
Purpose The purpose of this work is to study how different stakeholders of a football club engage with interactions online through Twitter. It analyses the football club’s Twitter network to discover influential actors and the topic of interest in their online communication. Design/methodology/approach The authors analysed the social networks derived from over two million tweets collected during football matches played by Manchester United. The authors applied social network analysis to discover influencers and sub-communities and performed content analysis on the most popular tweets of the prominent influencers. Findings Sub-communities can be formed around current affairs that are irrelevant to football, perhaps due to opportunistic attempts of using the large networks and massive attention during football matches to disseminate information. Furthermore, the popularity of tweets featuring different topics depends on the types of influencers involved. Practical implications The methods can help football clubs develop a deeper understanding of their online social communities. The findings can also inform football clubs on how to optimise their communication strategies by using various influencers. Originality/value Compared to previous research, the authors discovered a wide range of influencers and denser networks characterised by a smaller number of large clusters. Interestingly, this study also found that bots appeared to become influential within the network.
{"title":"Towards understanding a football club’s social media network: an exploratory case study of Manchester United","authors":"Erick Mendez Guzman, Ziqi Zhang, W. Ahmed","doi":"10.1108/IDD-08-2020-0106","DOIUrl":"https://doi.org/10.1108/IDD-08-2020-0106","url":null,"abstract":"\u0000Purpose\u0000The purpose of this work is to study how different stakeholders of a football club engage with interactions online through Twitter. It analyses the football club’s Twitter network to discover influential actors and the topic of interest in their online communication.\u0000\u0000\u0000Design/methodology/approach\u0000The authors analysed the social networks derived from over two million tweets collected during football matches played by Manchester United. The authors applied social network analysis to discover influencers and sub-communities and performed content analysis on the most popular tweets of the prominent influencers.\u0000\u0000\u0000Findings\u0000Sub-communities can be formed around current affairs that are irrelevant to football, perhaps due to opportunistic attempts of using the large networks and massive attention during football matches to disseminate information. Furthermore, the popularity of tweets featuring different topics depends on the types of influencers involved.\u0000\u0000\u0000Practical implications\u0000The methods can help football clubs develop a deeper understanding of their online social communities. The findings can also inform football clubs on how to optimise their communication strategies by using various influencers.\u0000\u0000\u0000Originality/value\u0000Compared to previous research, the authors discovered a wide range of influencers and denser networks characterised by a smaller number of large clusters. Interestingly, this study also found that bots appeared to become influential within the network.\u0000","PeriodicalId":43488,"journal":{"name":"Information Discovery and Delivery","volume":" ","pages":""},"PeriodicalIF":2.1,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49062499","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}
Data science in pandemic The coronavirus disease, a novel severe acute respiratory syndrome (SARS COVID-19), has become a severe global health crisis due to its unpredictable nature and lack of adequate treatment. The COVID-19 pandemic has generated a strong demand for using technologies such as data science to understand or mitigate the adverse effects of the COVID-19 on public health, society and the economy (He et al., 2021). In the current era of big data, data science and data analytics have become increasingly crucial in academia, healthcare, public relationships and business operations. Machine learning (ML) models could be effective in identifying the most critical factors responsible for the overall fatalities caused by the COVID-19. However, the functional capabilities of ML models in conducting epidemiological research, especially for the COVID-19, have not been substantially explored. There are several related research methodologies regarding the COVID-19 data analytics. For instance, adopted ML models and Random Forest (RF) have been used to perform the regression modeling and provide useful information to identify the relevant critical explanatory variables and evaluate interconnections between and among the key explanatory variables and the COVID-19 case and death counts (Gupta et al., 2021). Time-series analyses have been used to examine the rate of incidences of the COVID-19 cases and deaths (Khayyat et al., 2021). Social network analysis (SNA) has been used to track cases and simulations for modeling the COVID-19 outbreaks (Bahja and Safdar, 2020). Researchers have built models to interpret patterns of public sentiment on disseminating health-related information and assess the political and economic influence of the pandemic.
冠状病毒病是一种新型严重急性呼吸系统综合征(SARS - COVID-19)，由于其不可预测的性质和缺乏适当的治疗，已成为严重的全球健康危机。COVID-19大流行产生了使用数据科学等技术来了解或减轻COVID-19对公共卫生、社会和经济的不利影响的强烈需求(He et al.， 2021)。在当今大数据时代，数据科学和数据分析在学术界、医疗保健、公共关系和商业运营中变得越来越重要。机器学习(ML)模型可以有效地识别导致COVID-19造成的总体死亡人数的最关键因素。然而，机器学习模型在流行病学研究中的功能，特别是在COVID-19研究中的功能，尚未得到实质性的探索。关于COVID-19数据分析，有几种相关的研究方法。例如，采用ML模型和随机森林(RF)来执行回归建模，并提供有用的信息，以识别相关的关键解释变量，并评估关键解释变量与COVID-19病例和死亡计数之间的相互联系(Gupta等人，2021)。已使用时间序列分析来检查COVID-19病例发病率和死亡率(Khayyat等人，2021年)。社会网络分析(SNA)已用于跟踪病例和模拟COVID-19暴发(Bahja和Safdar, 2020年)。研究人员已经建立了模型来解释公众对传播健康相关信息的情绪模式，并评估疫情的政治和经济影响。
{"title":"Using data science to understand the COVID-19 pandemic","authors":"X. Tian, W. He, Y. Xing","doi":"10.1108/idd-08-2021-161","DOIUrl":"https://doi.org/10.1108/idd-08-2021-161","url":null,"abstract":"Data science in pandemic The coronavirus disease, a novel severe acute respiratory syndrome (SARS COVID-19), has become a severe global health crisis due to its unpredictable nature and lack of adequate treatment. The COVID-19 pandemic has generated a strong demand for using technologies such as data science to understand or mitigate the adverse effects of the COVID-19 on public health, society and the economy (He et al., 2021). In the current era of big data, data science and data analytics have become increasingly crucial in academia, healthcare, public relationships and business operations. Machine learning (ML) models could be effective in identifying the most critical factors responsible for the overall fatalities caused by the COVID-19. However, the functional capabilities of ML models in conducting epidemiological research, especially for the COVID-19, have not been substantially explored. There are several related research methodologies regarding the COVID-19 data analytics. For instance, adopted ML models and Random Forest (RF) have been used to perform the regression modeling and provide useful information to identify the relevant critical explanatory variables and evaluate interconnections between and among the key explanatory variables and the COVID-19 case and death counts (Gupta et al., 2021). Time-series analyses have been used to examine the rate of incidences of the COVID-19 cases and deaths (Khayyat et al., 2021). Social network analysis (SNA) has been used to track cases and simulations for modeling the COVID-19 outbreaks (Bahja and Safdar, 2020). Researchers have built models to interpret patterns of public sentiment on disseminating health-related information and assess the political and economic influence of the pandemic.","PeriodicalId":43488,"journal":{"name":"Information Discovery and Delivery","volume":"44 1","pages":""},"PeriodicalIF":2.1,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"62544948","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 : 2020-12-16DOI: 10.1108/idd-10-2019-0076
Jitendra Nath Shaw, Tanmay De Sarkar
Purpose The study aims to focus on the present automation status of the college libraries with an objective to offer enhanced Web-based library service on an affordable virtualization on cloud computing model. Design/methodology/approach With Infrastructure as a Service (Infrastructure as a Service) delivery model, this study demonstrates how libraries of colleges/smaller institutes could be connected to cloud Library Management System infrastructure through internet or dedicated point-to-point WAN connectivity. The Software as a Service (SaaS) delivery model depicts how college libraries could form library consortium at its own private cloud environment with installation of the required LMS application, database, middleware and other prerequisites. Findings A cloud-based consortium approach for the college libraries will reduce the cost of purchasing hardware equipment and setting up of infrastructural facilities; relieve libraries of involving additional IT skilled manpower; foster collaborative approach with shared environment and minimise duplication in resource subscription. Originality/value To the best of the authors’ knowledge, the present study is the first of its kind in the light of shifting of infrastructure, software and hardware requirements of smaller libraries for cooperative sharing in both IaaS and SaaS cloud platform. The study delineates step by step how college libraries could effectively leverage the cooperative cloud architecture for enhanced library services to reach wider user community.
目的研究高校图书馆的自动化现状，以经济实惠的虚拟化云计算模式为基础，提供基于web的增强图书馆服务。设计/方法/途径利用基础设施即服务(Infrastructure as a Service, Infrastructure as a Service)交付模型，本研究展示了高校/小型机构的图书馆如何通过互联网或专用点对点广域网连接到云图书馆管理系统基础设施。软件即服务(SaaS)交付模型描述了高校图书馆如何在自己的私有云环境中，通过安装所需的LMS应用程序、数据库、中间件和其他先决条件，形成图书馆联盟。发现高校图书馆采用基于云计算的联盟方式可以减少购买硬件设备和建立基础设施的成本;减轻图书馆需要额外资讯科技熟练人手的负担;促进共享环境的协作方式，并尽量减少资源订阅的重复。原创性/价值据作者所知，在IaaS和SaaS云平台上，小型图书馆的基础设施、软件和硬件需求发生了变化，因此本研究是同类研究中的第一个。该研究一步一步地描述了高校图书馆如何有效地利用合作云架构来增强图书馆服务，以达到更广泛的用户群体。
{"title":"A cloud-based approach to library management solution for college libraries","authors":"Jitendra Nath Shaw, Tanmay De Sarkar","doi":"10.1108/idd-10-2019-0076","DOIUrl":"https://doi.org/10.1108/idd-10-2019-0076","url":null,"abstract":"\u0000Purpose\u0000The study aims to focus on the present automation status of the college libraries with an objective to offer enhanced Web-based library service on an affordable virtualization on cloud computing model.\u0000\u0000\u0000Design/methodology/approach\u0000With Infrastructure as a Service (Infrastructure as a Service) delivery model, this study demonstrates how libraries of colleges/smaller institutes could be connected to cloud Library Management System infrastructure through internet or dedicated point-to-point WAN connectivity. The Software as a Service (SaaS) delivery model depicts how college libraries could form library consortium at its own private cloud environment with installation of the required LMS application, database, middleware and other prerequisites.\u0000\u0000\u0000Findings\u0000A cloud-based consortium approach for the college libraries will reduce the cost of purchasing hardware equipment and setting up of infrastructural facilities; relieve libraries of involving additional IT skilled manpower; foster collaborative approach with shared environment and minimise duplication in resource subscription.\u0000\u0000\u0000Originality/value\u0000To the best of the authors’ knowledge, the present study is the first of its kind in the light of shifting of infrastructure, software and hardware requirements of smaller libraries for cooperative sharing in both IaaS and SaaS cloud platform. The study delineates step by step how college libraries could effectively leverage the cooperative cloud architecture for enhanced library services to reach wider user community.\u0000","PeriodicalId":43488,"journal":{"name":"Information Discovery and Delivery","volume":" ","pages":""},"PeriodicalIF":2.1,"publicationDate":"2020-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1108/idd-10-2019-0076","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42102125","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 : 2020-07-24DOI: 10.1108/IDD-08-2020-0098
Ramesh Behl, Manit Mishra
Purpose The study aims to carry out predictive modeling based on publicly available COVID-19 data for the duration April 01, 2020 to June 20, 2020 pertaining to India and five of its most infected states: Maharashtra, Tamil Nadu, Delhi, Gujarat and Rajasthan. Design/methodology/approach The study leverages the susceptible, infected, recovered and dead (SIRD) epidemiological framework for predictive modeling. The basic reproduction number R0 is derived by an exponential growth method using RStudio package R0. The differential equations reflecting the SIRD model have been solved using Python 3.7.4 on the Jupyter Notebook platform. For visualization, Python Matplotlib 3.2.1 package is used. Findings The study offers insights on peak-date, peak number of COVID-19 infections and end-date pertaining to India and five of its states. Practical implications The results subtly indicate toward the amount of effort required to completely eliminate the infection. It could be leveraged by the political leadership and industry doyens for economic policy planning and execution. Originality/value The emergence of a clear picture about COVID-19 lifecycle is impossible without integrating data science algorithms and epidemiology theoretical framework. This study amalgamates these two disciplines to undertake predictive modeling based on COVID-19 data from India and five of its states. Population-specific granular and objective assessment of key parameters such as reproduction number (R0), susceptible population (S), effective contact rate (ß) and case-fatality rate (s) have been used to generate a visualization of COVID-19 lifecycle pattern for a critically affected population.
{"title":"COVID-19 and India: what next?","authors":"Ramesh Behl, Manit Mishra","doi":"10.1108/IDD-08-2020-0098","DOIUrl":"https://doi.org/10.1108/IDD-08-2020-0098","url":null,"abstract":"\u0000Purpose\u0000The study aims to carry out predictive modeling based on publicly available COVID-19 data for the duration April 01, 2020 to June 20, 2020 pertaining to India and five of its most infected states: Maharashtra, Tamil Nadu, Delhi, Gujarat and Rajasthan.\u0000\u0000\u0000Design/methodology/approach\u0000The study leverages the susceptible, infected, recovered and dead (SIRD) epidemiological framework for predictive modeling. The basic reproduction number R0 is derived by an exponential growth method using RStudio package R0. The differential equations reflecting the SIRD model have been solved using Python 3.7.4 on the Jupyter Notebook platform. For visualization, Python Matplotlib 3.2.1 package is used.\u0000\u0000\u0000Findings\u0000The study offers insights on peak-date, peak number of COVID-19 infections and end-date pertaining to India and five of its states.\u0000\u0000\u0000Practical implications\u0000The results subtly indicate toward the amount of effort required to completely eliminate the infection. It could be leveraged by the political leadership and industry doyens for economic policy planning and execution.\u0000\u0000\u0000Originality/value\u0000The emergence of a clear picture about COVID-19 lifecycle is impossible without integrating data science algorithms and epidemiology theoretical framework. This study amalgamates these two disciplines to undertake predictive modeling based on COVID-19 data from India and five of its states. Population-specific granular and objective assessment of key parameters such as reproduction number (R0), susceptible population (S), effective contact rate (ß) and case-fatality rate (s) have been used to generate a visualization of COVID-19 lifecycle pattern for a critically affected population.\u0000","PeriodicalId":43488,"journal":{"name":"Information Discovery and Delivery","volume":"1 1","pages":""},"PeriodicalIF":2.1,"publicationDate":"2020-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1108/IDD-08-2020-0098","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41389130","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}
Purpose Social media, especially microblog, has become one of the most popular platforms for public opinion dissemination. However, so far few studies have been conducted to explore information dissemination under the mobile environment. This paper aims to introduce the approach to analyze the public opinion information dissemination in mobile social networks. Design/methodology/approach This paper chooses “network attack” as the research topic and extracts 23,567 relevant messages from Sina Microblogs to study the structure of nodes for public opinion dissemination and the characteristics of propagation paths on mobile internet. Public opinion dissemination is compared on both mobile and non-mobile terminals. Findings The results reveal the characteristics of public opinion dissemination in mobile environment and identify three patterns of information propagation path. This study concludes that public opinion on mobile internet propagates more widely and efficiently and generates more impact than that on the non-mobile internet. Social implications The methods used in this study can be useful for the government and other organizations to analyze and identify problems in online information dissemination. Originality/value This paper explores the mechanism of public opinion dissemination on mobile internet in China and further investigates how to improve public opinion management through a case study related to “network attack.”
{"title":"Public opinion information dissemination in mobile social networks – taking Sina Weibo as an example","authors":"Xiwei Wang, Yunfei Xing, Yanan Wei, Qingxiao Zheng, Guochun Xing","doi":"10.1108/idd-10-2019-0075","DOIUrl":"https://doi.org/10.1108/idd-10-2019-0075","url":null,"abstract":"\u0000Purpose\u0000Social media, especially microblog, has become one of the most popular platforms for public opinion dissemination. However, so far few studies have been conducted to explore information dissemination under the mobile environment. This paper aims to introduce the approach to analyze the public opinion information dissemination in mobile social networks.\u0000\u0000\u0000Design/methodology/approach\u0000This paper chooses “network attack” as the research topic and extracts 23,567 relevant messages from Sina Microblogs to study the structure of nodes for public opinion dissemination and the characteristics of propagation paths on mobile internet. Public opinion dissemination is compared on both mobile and non-mobile terminals.\u0000\u0000\u0000Findings\u0000The results reveal the characteristics of public opinion dissemination in mobile environment and identify three patterns of information propagation path. This study concludes that public opinion on mobile internet propagates more widely and efficiently and generates more impact than that on the non-mobile internet.\u0000\u0000\u0000Social implications\u0000The methods used in this study can be useful for the government and other organizations to analyze and identify problems in online information dissemination.\u0000\u0000\u0000Originality/value\u0000This paper explores the mechanism of public opinion dissemination on mobile internet in China and further investigates how to improve public opinion management through a case study related to “network attack.”\u0000","PeriodicalId":43488,"journal":{"name":"Information Discovery and Delivery","volume":" ","pages":""},"PeriodicalIF":2.1,"publicationDate":"2020-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1108/idd-10-2019-0075","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41544399","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 : 2020-06-05DOI: 10.1108/idd-12-2019-0087
Muhammad Rafi, Zheng Jian-ming, K. Ahmad
Purpose In the age of knowledge explosion, modern technology facilitates the acquisition, organization and effective dissemination of information to support academic research. To achieve long-term educational goals, integrating digital resources into a knowledge management model (KMM) has become a necessary prerequisite for university management. The proposed KMM aims to combine resources and technology to facilitate resource management, navigation and cross-database search for advanced research. Design/methodology/approach The published literature on digital resource integration was reviewed, and the status of resource organization was discussed with experts to compile research instruments together with the perspectives of serving professionals in universities. The data obtained was systematically processed to develop an integrated resource KMM. Data volume measurement was done with the SPSS software and AMOS was used for path analysis and modeling. After the conceptual model was developed, many assumptions were associated with it, and the software was run on the data set to validate the proposed theoretical model. Findings Library resources with four components (digital resources, information technology, financial planning and service promotion) have been successfully integrated into the knowledge management framework to organize resources and provide academic services for researchers. In addition to the organization of digital resources, the two components of knowledge management, such as the explicit knowledge of its technology-oriented nature and the tacit knowledge of its human-centered positions, remained useful to strengthen the integration process. Practical implications With the development of digital technology and the internet, information authentication, access and dissemination have become a complex task for information centers. As an integral part of modern digital libraries, the expansion of digital collections requires proper accessibility organization. Owing to the increasing number of digital resources, organization and management require thorough research and appropriate integration mechanisms. This integrated KMM helps to organize heterogeneous information resources and databases in libraries for long-term academic tasks. Originality/value Based on literature studies and discussions with academic experts, integration problems were identified, and raw data were obtained from the library management to find a solution. It is unique research owing to a lack of original work and extensive international literature on resource integration in connection with KMMs. This study has innovative findings that can add value to world literature.
{"title":"Digital resources integration under the knowledge management model: an analysis based on the structural equation model","authors":"Muhammad Rafi, Zheng Jian-ming, K. Ahmad","doi":"10.1108/idd-12-2019-0087","DOIUrl":"https://doi.org/10.1108/idd-12-2019-0087","url":null,"abstract":"\u0000Purpose\u0000In the age of knowledge explosion, modern technology facilitates the acquisition, organization and effective dissemination of information to support academic research. To achieve long-term educational goals, integrating digital resources into a knowledge management model (KMM) has become a necessary prerequisite for university management. The proposed KMM aims to combine resources and technology to facilitate resource management, navigation and cross-database search for advanced research.\u0000\u0000\u0000Design/methodology/approach\u0000The published literature on digital resource integration was reviewed, and the status of resource organization was discussed with experts to compile research instruments together with the perspectives of serving professionals in universities. The data obtained was systematically processed to develop an integrated resource KMM. Data volume measurement was done with the SPSS software and AMOS was used for path analysis and modeling. After the conceptual model was developed, many assumptions were associated with it, and the software was run on the data set to validate the proposed theoretical model.\u0000\u0000\u0000Findings\u0000Library resources with four components (digital resources, information technology, financial planning and service promotion) have been successfully integrated into the knowledge management framework to organize resources and provide academic services for researchers. In addition to the organization of digital resources, the two components of knowledge management, such as the explicit knowledge of its technology-oriented nature and the tacit knowledge of its human-centered positions, remained useful to strengthen the integration process.\u0000\u0000\u0000Practical implications\u0000With the development of digital technology and the internet, information authentication, access and dissemination have become a complex task for information centers. As an integral part of modern digital libraries, the expansion of digital collections requires proper accessibility organization. Owing to the increasing number of digital resources, organization and management require thorough research and appropriate integration mechanisms. This integrated KMM helps to organize heterogeneous information resources and databases in libraries for long-term academic tasks.\u0000\u0000\u0000Originality/value\u0000Based on literature studies and discussions with academic experts, integration problems were identified, and raw data were obtained from the library management to find a solution. It is unique research owing to a lack of original work and extensive international literature on resource integration in connection with KMMs. This study has innovative findings that can add value to world literature.\u0000","PeriodicalId":43488,"journal":{"name":"Information Discovery and Delivery","volume":" ","pages":""},"PeriodicalIF":2.1,"publicationDate":"2020-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1108/idd-12-2019-0087","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42160263","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：