Pub Date : 2021-09-01DOI: 10.25300/misq/2021/14349
Wenbo Guo, D. Straub, Pengzhu Zhang, Zhao Cai
IS research has extensively examined the role of trust in client-vendor relationships, as well as the role of governance in information technology (IT) outsourcing, but little research has been carried out on the latest manifestation of outsourcing—namely, microsourcing, i.e., the sourcing of smaller scale projects. To extend the literature on the traditional IT outsourcing literature—a stream that largely focuses on medium-to-large scale offline projects—we investigate how to develop trust and commitment in a triadic microsourcing relationship which includes the microsourcer, the microsourcee, and the microsourcing platform (MP). We draw on transaction cost economics (TCE) to theorize a model specifically adapted to the microsourcing phenomenon to scrutinize the influences of formal contractual mechanisms, relational mechanisms, and third-party mechanisms. Combining data from a matched sample of microsourcers and microsourcees on the leading Chinese MP, Zbj.com, the paper deploys degree-symmetric modeling (DSM) for construct conceptualization, measurement, and data analysis. DSM is consistent with the holistic view used to develop the research model for triadic relationships. Findings confirm that the MP is critical in delivering governance mechanisms to ensure the development of triadic trust and commitment. The results suggest that researchers and practitioners should pay closer attention to triadic trust and commitment building through proper governance mechanisms in the online microsourcing marketplace. We argue that this work could be extended to other online digital platforms that involve multiple transacting parties.
{"title":"How Trust Leads to Commitment on Microsourcing Platforms: Unraveling the Effects of Governance and Third-Party Mechanisms on Triadic Microsourcing Relationships","authors":"Wenbo Guo, D. Straub, Pengzhu Zhang, Zhao Cai","doi":"10.25300/misq/2021/14349","DOIUrl":"https://doi.org/10.25300/misq/2021/14349","url":null,"abstract":"IS research has extensively examined the role of trust in client-vendor relationships, as well as the role of governance in information technology (IT) outsourcing, but little research has been carried out on the latest manifestation of outsourcing—namely, microsourcing, i.e., the sourcing of smaller scale projects. To extend the literature on the traditional IT outsourcing literature—a stream that largely focuses on medium-to-large scale offline projects—we investigate how to develop trust and commitment in a triadic microsourcing relationship which includes the microsourcer, the microsourcee, and the microsourcing platform (MP). We draw on transaction cost economics (TCE) to theorize a model specifically adapted to the microsourcing phenomenon to scrutinize the influences of formal contractual mechanisms, relational mechanisms, and third-party mechanisms. Combining data from a matched sample of microsourcers and microsourcees on the leading Chinese MP, Zbj.com, the paper deploys degree-symmetric modeling (DSM) for construct conceptualization, measurement, and data analysis. DSM is consistent with the holistic view used to develop the research model for triadic relationships. Findings confirm that the MP is critical in delivering governance mechanisms to ensure the development of triadic trust and commitment. The results suggest that researchers and practitioners should pay closer attention to triadic trust and commitment building through proper governance mechanisms in the online microsourcing marketplace. We argue that this work could be extended to other online digital platforms that involve multiple transacting parties.","PeriodicalId":18743,"journal":{"name":"MIS Q.","volume":"47 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74341875","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 : 2021-09-01DOI: 10.25300/misq/2021/16535
Mike H. M. Teodorescu, Lily Morse, Yazeed Awwad, Gerald C. Kane
Machine learning (ML) tools reduce the costs of performing repetitive, time-consuming tasks yet run the risk of introducing systematic unfairness into organizational processes. Automated approaches to achieving fair- ness often fail in complex situations, leading some researchers to suggest that human augmentation of ML tools is necessary. However, our current understanding of human–ML augmentation remains limited. In this paper, we argue that the Information Systems (IS) discipline needs a more sophisticated view of and research into human–ML augmentation. We introduce a typology of augmentation for fairness consisting of four quadrants: reactive oversight, proactive oversight, informed reliance, and supervised reliance. We identify significant intersections with previous IS research and distinct managerial approaches to fairness for each quadrant. Several potential research questions emerge from fundamental differences between ML tools trained on data and traditional IS built with code. IS researchers may discover that the differences of ML tools undermine some of the fundamental assumptions upon which classic IS theories and concepts rest. ML may require massive rethinking of significant portions of the corpus of IS research in light of these differences, representing an exciting frontier for research into human–ML augmentation in the years ahead that IS researchers should embrace.
{"title":"Failures of Fairness in Automation Require a Deeper Understanding of Human-ML Augmentation","authors":"Mike H. M. Teodorescu, Lily Morse, Yazeed Awwad, Gerald C. Kane","doi":"10.25300/misq/2021/16535","DOIUrl":"https://doi.org/10.25300/misq/2021/16535","url":null,"abstract":"Machine learning (ML) tools reduce the costs of performing repetitive, time-consuming tasks yet run the risk of introducing systematic unfairness into organizational processes. Automated approaches to achieving fair- ness often fail in complex situations, leading some researchers to suggest that human augmentation of ML tools is necessary. However, our current understanding of human–ML augmentation remains limited. In this paper, we argue that the Information Systems (IS) discipline needs a more sophisticated view of and research into human–ML augmentation. We introduce a typology of augmentation for fairness consisting of four quadrants: reactive oversight, proactive oversight, informed reliance, and supervised reliance. We identify significant intersections with previous IS research and distinct managerial approaches to fairness for each quadrant. Several potential research questions emerge from fundamental differences between ML tools trained on data and traditional IS built with code. IS researchers may discover that the differences of ML tools undermine some of the fundamental assumptions upon which classic IS theories and concepts rest. ML may require massive rethinking of significant portions of the corpus of IS research in light of these differences, representing an exciting frontier for research into human–ML augmentation in the years ahead that IS researchers should embrace.","PeriodicalId":18743,"journal":{"name":"MIS Q.","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75155074","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 : 2021-09-01DOI: 10.25300/misq/2021/14368
Prasanna P. Karhade, John Qi Dong
Firms’ investment in information technology (IT) has been widely considered to be a key enabler of innovation. In this study, we integrate prior findings on the augmenting pathways (where IT investment supports innovation) with a new theory explaining the suppressing pathways (where dynamic adjustment costs associated with large IT investment can be detrimental to innovation) to propose an overall inverted U-shaped relationship between IT investment and commercialized innovation performance (CIP). To test our theory, we analyze a unique panel dataset from the largest economy in Europe and discovered a curvilinear relationship between IT investment and CIP for firms across a broad spectrum of industries. Our research presents empirical evidence corroborating the augmenting and suppressing pathways linking IT investment and CIP. Our findings serve as a cautionary signal to executives, discouraging overinvestment in IT.
{"title":"Information Technology Investment and Commercialized Innovation Performance: Dynamic Adjustment Costs and Curvilinear Impacts","authors":"Prasanna P. Karhade, John Qi Dong","doi":"10.25300/misq/2021/14368","DOIUrl":"https://doi.org/10.25300/misq/2021/14368","url":null,"abstract":"Firms’ investment in information technology (IT) has been widely considered to be a key enabler of innovation. In this study, we integrate prior findings on the augmenting pathways (where IT investment supports innovation) with a new theory explaining the suppressing pathways (where dynamic adjustment costs associated with large IT investment can be detrimental to innovation) to propose an overall inverted U-shaped relationship between IT investment and commercialized innovation performance (CIP). To test our theory, we analyze a unique panel dataset from the largest economy in Europe and discovered a curvilinear relationship between IT investment and CIP for firms across a broad spectrum of industries. Our research presents empirical evidence corroborating the augmenting and suppressing pathways linking IT investment and CIP. Our findings serve as a cautionary signal to executives, discouraging overinvestment in IT.","PeriodicalId":18743,"journal":{"name":"MIS Q.","volume":"9 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76186512","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 : 2021-09-01DOI: 10.25300/misq/2021/16523
Jingyu Li, Mengxiang Li, Xincheng Wang, J. Thatcher
This paper applies upper echelons theory to investigate whether chief information officers (CIOs) and boards of directors affect the development of AI orientation, which represents firms’ overall strategic direction and goals regarding the introduction and application of artificial intelligence (AI)technology. We tested our model using a dataset drawn from 1,454 publicly listed firms in China. Our findings show that the presence of a CIO positively influences AI orientation and that board educational diversity, R&D experience, and AI experience positively moderate the CIO’s effect on AI orientation. Our post hoc analysis further demonstrates that these board characteristics represent contingencies that impact AI orientation but not conventional IT orientation. This paper contributes to the upper echelons literature and IT management research by offering contextualized arguments that explain new business and IT strategies such as AI orientation. Further, our findings suggest important implications about how to build top management teams and boards capable of effectively developing AI orientations
{"title":"Strategic Directions for AI: The Role of CIOs and Boards of Directors","authors":"Jingyu Li, Mengxiang Li, Xincheng Wang, J. Thatcher","doi":"10.25300/misq/2021/16523","DOIUrl":"https://doi.org/10.25300/misq/2021/16523","url":null,"abstract":"This paper applies upper echelons theory to investigate whether chief information officers (CIOs) and boards of directors affect the development of AI orientation, which represents firms’ overall strategic direction and goals regarding the introduction and application of artificial intelligence (AI)technology. We tested our model using a dataset drawn from 1,454 publicly listed firms in China. Our findings show that the presence of a CIO positively influences AI orientation and that board educational diversity, R&D experience, and AI experience positively moderate the CIO’s effect on AI orientation. Our post hoc analysis further demonstrates that these board characteristics represent contingencies that impact AI orientation but not conventional IT orientation. This paper contributes to the upper echelons literature and IT management research by offering contextualized arguments that explain new business and IT strategies such as AI orientation. Further, our findings suggest important implications about how to build top management teams and boards capable of effectively developing AI orientations","PeriodicalId":18743,"journal":{"name":"MIS Q.","volume":"31 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86025470","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 : 2021-09-01DOI: 10.25300/misq/2021/14375
A. Liu, Yilin Li, S. Xu
This work examines the question of who is more likely to provide future helpful reviews in the context of online product reviews by synergistically using personality theories and data analytics. It trains a deep learning model to infer a reviewer’s personality traits. This enables analyses to reveal the role of personality traits in review helpfulness among a large population of reviewers. We develop hypotheses on how personality traits are associated with review helpfulness, followed by hypotheses testing that confirms that higher review helpfulness is related to higher openness, conscientiousness, extraversion, and agreeableness and to lower emotional stability. These results suggest the appropriateness of using these five personality traits as inputs for developing a model for predicting future review helpfulness. Based on an ensemble model using supervised classification algorithms, we develop a predictive model and demonstrate its superior performance. Theoretical and practical implications are discussed.
{"title":"Assessing the Unacquainted: Inferred Reviewer Personality and Review Helpfulness","authors":"A. Liu, Yilin Li, S. Xu","doi":"10.25300/misq/2021/14375","DOIUrl":"https://doi.org/10.25300/misq/2021/14375","url":null,"abstract":"This work examines the question of who is more likely to provide future helpful reviews in the context of online product reviews by synergistically using personality theories and data analytics. It trains a deep learning model to infer a reviewer’s personality traits. This enables analyses to reveal the role of personality traits in review helpfulness among a large population of reviewers. We develop hypotheses on how personality traits are associated with review helpfulness, followed by hypotheses testing that confirms that higher review helpfulness is related to higher openness, conscientiousness, extraversion, and agreeableness and to lower emotional stability. These results suggest the appropriateness of using these five personality traits as inputs for developing a model for predicting future review helpfulness. Based on an ensemble model using supervised classification algorithms, we develop a predictive model and demonstrate its superior performance. Theoretical and practical implications are discussed.","PeriodicalId":18743,"journal":{"name":"MIS Q.","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73462934","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 : 2021-06-01DOI: 10.25300/misq/2021/15324
M. Chau, Wenwen Li, Bo Yang, Alice J. Lee, Z. Bao
Online auction markets host a large number of transactions every day. The transaction data in auction markets are useful for understanding the buyers and sellers in the market. Previous research has shown that sellers with different levels of reputation, as shown by the ratings and comments left in feedback systems, enjoy different levels of price premiums for their transactions. Feedback scores and feedback texts have been shown to correlate with buyers’ level of trust in a seller and the price premium that buyers are willing to pay (Ba and Pavlou 2002; Pavlou and Dimoka 2006). However, existing models do not consider the time-order effect, which means that feedback posted more recently may be considered more important than feedback posted less recently. This paper addresses this shortcoming by (1) testing the existence of the time-order effect, and (2) proposing a Bayesian updating model to represent buyers’ perceived reputation considering the time-order effect and assessing how well it can explain the variation in buyers’ trust and price premiums. In order to validate the time-order effect and evaluate the proposed model, we conducted a user experiment and collected real-life transaction data from the eBay online auction market. Our results confirm the existence of the time-order effect and the proposed model explains the variation in price premiums better than the benchmark models. The contribution of this research is threefold. First, we verify the time-order effect in the feedback mechanism on price premiums in online markets. Second, we propose a model that provides better explanatory power for price premiums in online auction markets than existing models by incorporating the time-order effect. Third, we provide further evidence for trust building via textual feedback in online auction markets. The study advances the understanding of the feedback mechanism in online auction markets.
网上拍卖市场每天都有大量的交易。拍卖市场的交易数据对了解市场上的买卖双方很有帮助。先前的研究表明，不同声誉水平的卖家(如在反馈系统中留下的评级和评论)在交易中享有不同水平的价格溢价。反馈分数和反馈文本已被证明与买家对卖家的信任水平和买家愿意支付的价格溢价相关(Ba和Pavlou 2002;Pavlou and Dimoka 2006)。然而，现有模型没有考虑时间顺序效应，这意味着最近发布的反馈可能被认为比最近发布的反馈更重要。本文通过(1)检验时间顺序效应的存在性，以及(2)提出一个考虑时间顺序效应的贝叶斯更新模型来表示买家感知声誉，并评估它如何很好地解释买家信任和价格溢价的变化。为了验证时间顺序效应并评估所提出的模型，我们进行了用户实验并收集了eBay在线拍卖市场的真实交易数据。我们的研究结果证实了时间顺序效应的存在，并且所提出的模型比基准模型更能解释价格溢价的变化。这项研究的贡献有三个方面。首先，我们验证了在线市场价格溢价反馈机制中的时间顺序效应。其次，我们提出了一个模型，该模型通过纳入时间顺序效应，为在线拍卖市场的价格溢价提供了比现有模型更好的解释力。第三，我们为在线拍卖市场通过文本反馈建立信任提供了进一步的证据。该研究促进了对在线拍卖市场反馈机制的理解。
{"title":"Incorporating the Time-Order Effect of Feedback in Online Auction Markets through a Bayesian Updating Model","authors":"M. Chau, Wenwen Li, Bo Yang, Alice J. Lee, Z. Bao","doi":"10.25300/misq/2021/15324","DOIUrl":"https://doi.org/10.25300/misq/2021/15324","url":null,"abstract":"Online auction markets host a large number of transactions every day. The transaction data in auction markets are useful for understanding the buyers and sellers in the market. Previous research has shown that sellers with different levels of reputation, as shown by the ratings and comments left in feedback systems, enjoy different levels of price premiums for their transactions. Feedback scores and feedback texts have been shown to correlate with buyers’ level of trust in a seller and the price premium that buyers are willing to pay (Ba and Pavlou 2002; Pavlou and Dimoka 2006). However, existing models do not consider the time-order effect, which means that feedback posted more recently may be considered more important than feedback posted less recently. This paper addresses this shortcoming by (1) testing the existence of the time-order effect, and (2) proposing a Bayesian updating model to represent buyers’ perceived reputation considering the time-order effect and assessing how well it can explain the variation in buyers’ trust and price premiums. In order to validate the time-order effect and evaluate the proposed model, we conducted a user experiment and collected real-life transaction data from the eBay online auction market. Our results confirm the existence of the time-order effect and the proposed model explains the variation in price premiums better than the benchmark models. The contribution of this research is threefold. First, we verify the time-order effect in the feedback mechanism on price premiums in online markets. Second, we propose a model that provides better explanatory power for price premiums in online auction markets than existing models by incorporating the time-order effect. Third, we provide further evidence for trust building via textual feedback in online auction markets. The study advances the understanding of the feedback mechanism in online auction markets.","PeriodicalId":18743,"journal":{"name":"MIS Q.","volume":"1 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79875192","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 : 2021-06-01DOI: 10.25300/misq/2021/15360
B. Pentland, Emmanuelle Vaast, J. R. Wolf
The growing availability of digital trace data has generated unprecedented opportunities for analyzing, explaining, and predicting the dynamics of process change. While research on process organization studies theorizes about process and change, and research on process mining rigorously measures and models business processes, there has so far been limited research that measures and theorizes about process dynamics. This gap represents an opportunity for new information systems research. This research note lays the foundation for such an endeavor by demonstrating the use of process mining for diachronic analysis of process dynamics. We detail the definitions, assumptions, and mechanics of an approach that is based on representing processes as weighted, directed graphs. Using this representation, we offer a precise definition of process dynamics that focuses attention on describing and measuring changes in process structure over time. We analyze process structure over two years at four dermatology clinics. Our analysis reveals process changes that were invisible to the medical staff in the clinics. This approach offers empirical insights that are relevant to many theoretical perspectives on process dynamics.
{"title":"Theorizing Process Dynamics with Directed Graphs: A Diachronic Analysis of Digital Trace Data","authors":"B. Pentland, Emmanuelle Vaast, J. R. Wolf","doi":"10.25300/misq/2021/15360","DOIUrl":"https://doi.org/10.25300/misq/2021/15360","url":null,"abstract":"The growing availability of digital trace data has generated unprecedented opportunities for analyzing, explaining, and predicting the dynamics of process change. While research on process organization studies theorizes about process and change, and research on process mining rigorously measures and models business processes, there has so far been limited research that measures and theorizes about process dynamics. This gap represents an opportunity for new information systems research. This research note lays the foundation for such an endeavor by demonstrating the use of process mining for diachronic analysis of process dynamics. We detail the definitions, assumptions, and mechanics of an approach that is based on representing processes as weighted, directed graphs. Using this representation, we offer a precise definition of process dynamics that focuses attention on describing and measuring changes in process structure over time. We analyze process structure over two years at four dermatology clinics. Our analysis reveals process changes that were invisible to the medical staff in the clinics. This approach offers empirical insights that are relevant to many theoretical perspectives on process dynamics.","PeriodicalId":18743,"journal":{"name":"MIS Q.","volume":"26 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83365956","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 : 2021-06-01DOI: 10.25300/misq/2021/15574
Hongyi Zhu, S. Samtani, Randall A. Brown, Hsinchun Chen
Ensuring the health and safety of senior citizens who live alone is a growing societal concern. The Activity of Daily Living (ADL) approach is a common means to monitor disease progression and the ability of these individuals to care for themselves. However, the prevailing sensor-based ADL monitoring systems primarily rely on wearable motion sensors, capture insufficient information for accurate ADL recognition, and do not provide a comprehensive understanding of ADLs at different granularities. Current healthcare IS and mobile analytics research focuses on studying the system, device, and provided services, and is in need of an end-to-end solution to comprehensively recognize ADLs based on mobile sensor data. This study adopts the design science paradigm and employs advanced deep learning algorithms to develop a novel hierarchical, multiphase ADL recognition framework to model ADLs at different granularities. We propose a novel 2D interaction kernel for convolutional neural networks to leverage interactions between human and object motion sensors. We rigorously evaluate each proposed module and the entire framework against state-of-the-art benchmarks (e.g., support vector machines, DeepConvLSTM, hidden Markov models, and topic-modeling-based ADLR) on two real-life motion sensor datasets that consist of ADLs at varying granularities: Opportunity and INTER. Results and a case study demonstrate that our framework can recognize ADLs at different levels more accurately. We discuss how stakeholders can further benefit from our proposed framework. Beyond demonstrating practical utility, we discuss contributions to the IS knowledge base for future design science-based cybersecurity, healthcare, and mobile analytics applications.
{"title":"A Deep Learning Approach for Recognizing Activity of Daily Living (ADL) for Senior Care: Exploiting Interaction Dependency and Temporal Patterns","authors":"Hongyi Zhu, S. Samtani, Randall A. Brown, Hsinchun Chen","doi":"10.25300/misq/2021/15574","DOIUrl":"https://doi.org/10.25300/misq/2021/15574","url":null,"abstract":"Ensuring the health and safety of senior citizens who live alone is a growing societal concern. The Activity of Daily Living (ADL) approach is a common means to monitor disease progression and the ability of these individuals to care for themselves. However, the prevailing sensor-based ADL monitoring systems primarily rely on wearable motion sensors, capture insufficient information for accurate ADL recognition, and do not provide a comprehensive understanding of ADLs at different granularities. Current healthcare IS and mobile analytics research focuses on studying the system, device, and provided services, and is in need of an end-to-end solution to comprehensively recognize ADLs based on mobile sensor data. This study adopts the design science paradigm and employs advanced deep learning algorithms to develop a novel hierarchical, multiphase ADL recognition framework to model ADLs at different granularities. We propose a novel 2D interaction kernel for convolutional neural networks to leverage interactions between human and object motion sensors. We rigorously evaluate each proposed module and the entire framework against state-of-the-art benchmarks (e.g., support vector machines, DeepConvLSTM, hidden Markov models, and topic-modeling-based ADLR) on two real-life motion sensor datasets that consist of ADLs at varying granularities: Opportunity and INTER. Results and a case study demonstrate that our framework can recognize ADLs at different levels more accurately. We discuss how stakeholders can further benefit from our proposed framework. Beyond demonstrating practical utility, we discuss contributions to the IS knowledge base for future design science-based cybersecurity, healthcare, and mobile analytics applications.","PeriodicalId":18743,"journal":{"name":"MIS Q.","volume":"122 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81973604","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 : 2021-06-01DOI: 10.25300/misq/2021/16266
Xiao Han, Leye Wang, Weiguo Fan
User privacy protection is a vital issue of concern for online social networks (OSNs). Even though users often intentionally hide their private information in OSNs, since adversaries may conduct prediction attacks to predict hidden information using advanced machine learning techniques, private information that users intend to hide may still be at risk of being exposed. Taking the current city listed on Facebook profiles as a case, we propose a solution that estimates and manages the exposure risk of users’ hidden information. First, we simulate an aggressive prediction attack using advanced state-of-the-art machine learning algorithms by proposing a new current city prediction framework that integrates location indications based on various types of information exposed by users, including demographic attributes, behaviors, and relationships. Second, we study prediction attack results to model patterns of prediction correctness (as correct predictions lead to information exposures) and construct an exposure risk estimator. The proposed exposure risk estimator has the ability not only to notify users of exposure risks related to their hidden current city but can also help users mitigate exposure risks by overhauling and selecting countermeasures. Moreover, our exposure risk estimator can improve the privacy management of OSNs by facilitating empirical studies on the exposure risks of OSN users as a group. Taking the current city as a case, this work offers insight on how to protect other types of private information against machine-learning prediction attacks and reveals several important implications for both practice management and future research.
{"title":"Is Hidden Safe? Location Protection against Machine-Learning Prediction Attacks in Social Networks","authors":"Xiao Han, Leye Wang, Weiguo Fan","doi":"10.25300/misq/2021/16266","DOIUrl":"https://doi.org/10.25300/misq/2021/16266","url":null,"abstract":"User privacy protection is a vital issue of concern for online social networks (OSNs). Even though users often intentionally hide their private information in OSNs, since adversaries may conduct prediction attacks to predict hidden information using advanced machine learning techniques, private information that users intend to hide may still be at risk of being exposed. Taking the current city listed on Facebook profiles as a case, we propose a solution that estimates and manages the exposure risk of users’ hidden information. First, we simulate an aggressive prediction attack using advanced state-of-the-art machine learning algorithms by proposing a new current city prediction framework that integrates location indications based on various types of information exposed by users, including demographic attributes, behaviors, and relationships. Second, we study prediction attack results to model patterns of prediction correctness (as correct predictions lead to information exposures) and construct an exposure risk estimator. The proposed exposure risk estimator has the ability not only to notify users of exposure risks related to their hidden current city but can also help users mitigate exposure risks by overhauling and selecting countermeasures. Moreover, our exposure risk estimator can improve the privacy management of OSNs by facilitating empirical studies on the exposure risks of OSN users as a group. Taking the current city as a case, this work offers insight on how to protect other types of private information against machine-learning prediction attacks and reveals several important implications for both practice management and future research.","PeriodicalId":18743,"journal":{"name":"MIS Q.","volume":"5 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78913903","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 : 2021-06-01DOI: 10.25300/misq/2021/14617
Yanzhen Chen, Huaxia Rui, A. Whinston
This paper studies whether social media personal branding (PB) improves a job candidate’s labor market performance in the context of executive employment and compensation. We focus on executives employed by Standard & Poor’s 500 constituent companies from 2010 to 2013 and evaluate their PB on social media by analyzing their Twitter accounts. To disentangle the effect of PB from that of personality traits, we exploit a (positive) shock to the effectiveness of PB caused by a series of technology upgrades by Twitter. Estimations from a two-sided matching model suggest that social media PB benefits executive candidates in job markets. This paper contributes to the literature by initiating the study of the emerging phenomenon of social media PB and testing its effect on job market performance.
{"title":"Tweet to the Top? Social Media Personal Branding and Career Outcomes","authors":"Yanzhen Chen, Huaxia Rui, A. Whinston","doi":"10.25300/misq/2021/14617","DOIUrl":"https://doi.org/10.25300/misq/2021/14617","url":null,"abstract":"This paper studies whether social media personal branding (PB) improves a job candidate’s labor market performance in the context of executive employment and compensation. We focus on executives employed by Standard & Poor’s 500 constituent companies from 2010 to 2013 and evaluate their PB on social media by analyzing their Twitter accounts. To disentangle the effect of PB from that of personality traits, we exploit a (positive) shock to the effectiveness of PB caused by a series of technology upgrades by Twitter. Estimations from a two-sided matching model suggest that social media PB benefits executive candidates in job markets. This paper contributes to the literature by initiating the study of the emerging phenomenon of social media PB and testing its effect on job market performance.","PeriodicalId":18743,"journal":{"name":"MIS Q.","volume":"39 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2021-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81977877","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：