Pub Date : 2023-04-03DOI: 10.1080/07421222.2023.2196779
Hamed Qahri-Saremi, O. Turel
ABSTRACT User susceptibility to phishing messages on social media is a growing information security concern. Contingency factors that can influence this susceptibility and the theoretical mechanisms through which they operate need more scholarly attention. To bridge this gap, we present a temptation and restraint (TR) model (a specific manifestation of the dual–system theory) of social media phishing susceptibility, which explains it as an outcome of a struggle between users’ temptation toward engaging with a social media phishing message and their cognitive and behavioral restraint against it. The balance in this struggle is a function of various situational contingencies. First, via a Delphi study, we identify four key situational contingency factors in the context of social media that can influence this balance: (1) poor sleep quality, (2) social media ostracism, (3) source likability, and (4) fear appeals. Next, via five randomized controlled experiments using an ostensible social media paradigm with social media users, we show that the TR model explains (a) why and how users engage with social media phishing messages, and (b) when users are more or less susceptible to it based on key situational contingency factors. Our findings offer a nuanced perspective on social media phishing susceptibility, elucidate the fundamental roles of situational contingencies in the genesis of social media phishing victimization, and delineate important directions for future research in this area
{"title":"Situational Contingencies in Susceptibility of Social Media to Phishing: A Temptation and Restraint Model","authors":"Hamed Qahri-Saremi, O. Turel","doi":"10.1080/07421222.2023.2196779","DOIUrl":"https://doi.org/10.1080/07421222.2023.2196779","url":null,"abstract":"ABSTRACT User susceptibility to phishing messages on social media is a growing information security concern. Contingency factors that can influence this susceptibility and the theoretical mechanisms through which they operate need more scholarly attention. To bridge this gap, we present a temptation and restraint (TR) model (a specific manifestation of the dual–system theory) of social media phishing susceptibility, which explains it as an outcome of a struggle between users’ temptation toward engaging with a social media phishing message and their cognitive and behavioral restraint against it. The balance in this struggle is a function of various situational contingencies. First, via a Delphi study, we identify four key situational contingency factors in the context of social media that can influence this balance: (1) poor sleep quality, (2) social media ostracism, (3) source likability, and (4) fear appeals. Next, via five randomized controlled experiments using an ostensible social media paradigm with social media users, we show that the TR model explains (a) why and how users engage with social media phishing messages, and (b) when users are more or less susceptible to it based on key situational contingency factors. Our findings offer a nuanced perspective on social media phishing susceptibility, elucidate the fundamental roles of situational contingencies in the genesis of social media phishing victimization, and delineate important directions for future research in this area","PeriodicalId":50154,"journal":{"name":"Journal of Management Information Systems","volume":"40 1","pages":"503 - 540"},"PeriodicalIF":7.7,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43192351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1080/07421222.2023.2196775
Shilei Li, Yang Liu, Juan Feng
ABSTRACT With the wide use of information technologies including Big Data and artificial intelligence (AI), consumers’ personal actions (their search history, transaction records, click-through behaviors, etc.) can be tracked, recorded and analyzed by the service provider (e.g., Google) to provide personalized services. Under the current regime, consumers usually hand over their personal data for free in exchange for high-quality services. As it becomes more and more commonly accepted that “data is property,” should consumers be entitled to claim their property rights over their personal data? New technologies emerge to empower consumers to control their own data, and the service provider may need to compensate for the usage of such data. How consumers and the service provider should react to such technologies, however, is not clear. We build a theoretical model in which consumers have different sensitivities towards their data ownership. We show that the impact of the data ownership shift depends not only on the service provider’s revenue structure and the discount in the service quality offered to non-data-providing consumers, but also on whether and how consumers are compensated. More importantly, if the service provider can endogenously adjust the qualities of services provided to consumers, the shift of data ownership may not necessarily benefit consumers, or harm the service provider. We also offer guidelines for data regulation policy designs.
{"title":"Who Should Own the Data? The Impact of Data Ownership Shift from the Service Provider to Consumers","authors":"Shilei Li, Yang Liu, Juan Feng","doi":"10.1080/07421222.2023.2196775","DOIUrl":"https://doi.org/10.1080/07421222.2023.2196775","url":null,"abstract":"ABSTRACT With the wide use of information technologies including Big Data and artificial intelligence (AI), consumers’ personal actions (their search history, transaction records, click-through behaviors, etc.) can be tracked, recorded and analyzed by the service provider (e.g., Google) to provide personalized services. Under the current regime, consumers usually hand over their personal data for free in exchange for high-quality services. As it becomes more and more commonly accepted that “data is property,” should consumers be entitled to claim their property rights over their personal data? New technologies emerge to empower consumers to control their own data, and the service provider may need to compensate for the usage of such data. How consumers and the service provider should react to such technologies, however, is not clear. We build a theoretical model in which consumers have different sensitivities towards their data ownership. We show that the impact of the data ownership shift depends not only on the service provider’s revenue structure and the discount in the service quality offered to non-data-providing consumers, but also on whether and how consumers are compensated. More importantly, if the service provider can endogenously adjust the qualities of services provided to consumers, the shift of data ownership may not necessarily benefit consumers, or harm the service provider. We also offer guidelines for data regulation policy designs.","PeriodicalId":50154,"journal":{"name":"Journal of Management Information Systems","volume":"40 1","pages":"366 - 400"},"PeriodicalIF":7.7,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43408477","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1080/07421222.2023.2196773
A. Dennis, Akshat Lakhiwal, Agrim Sachdeva
ABSTRACT Organizations are beginning to deploy artificial intelligence (AI) agents as members of virtual teams to help manage information, coordinate team processes, and perform simple tasks. How will team members perceive these AI team members and will they be willing to work with them? We conducted a 2 x 2 x 2 lab experiment that manipulated the type of team member (human or AI), their performance (high or low), and the performance of other team members (high or low). AI team members were perceived to have higher ability and integrity but lower benevolence, which led to no differences in trustworthiness or willingness to work with them. However, the presence of an AI team member resulted in lower process satisfaction. When the AI team member performed well, participants perceived less conflict compared to a human team member with the same performance, but there were no differences in perceived conflict when it performed poorly. There were no other interactions with performance, indicating that the AI team member was judged similarly to humans, irrespective of variations in performance; there was no evidence of algorithm aversion. Our research suggests that AI team members are likely to be accepted into teams, meaning that many old collaboration research questions may need to be reexamined to consider AI team members.
组织开始部署人工智能(AI)代理作为虚拟团队的成员，以帮助管理信息、协调团队流程和执行简单任务。团队成员如何看待这些人工智能团队成员，他们是否愿意与他们合作?我们进行了一个2 x 2 x 2的实验室实验，操纵团队成员的类型(人类或AI)，他们的表现(高或低)，以及其他团队成员的表现(高或低)。人工智能团队成员被认为有更高的能力和诚信，但更低的仁慈，这导致在可信度或愿意与他们合作方面没有差异。然而，人工智能团队成员的存在导致了较低的过程满意度。当人工智能团队成员表现良好时，与表现相同的人类团队成员相比，参与者感受到的冲突较少，但当人工智能团队成员表现不佳时，他们感受到的冲突没有差异。没有其他与表现的互动，这表明人工智能团队成员的判断与人类相似，无论其表现如何变化;没有证据表明存在算法厌恶。我们的研究表明，人工智能团队成员很可能被团队接受，这意味着许多旧的协作研究问题可能需要重新审视，以考虑人工智能团队成员。
{"title":"AI Agents as Team Members: Effects on Satisfaction, Conflict, Trustworthiness, and Willingness to Work With","authors":"A. Dennis, Akshat Lakhiwal, Agrim Sachdeva","doi":"10.1080/07421222.2023.2196773","DOIUrl":"https://doi.org/10.1080/07421222.2023.2196773","url":null,"abstract":"ABSTRACT Organizations are beginning to deploy artificial intelligence (AI) agents as members of virtual teams to help manage information, coordinate team processes, and perform simple tasks. How will team members perceive these AI team members and will they be willing to work with them? We conducted a 2 x 2 x 2 lab experiment that manipulated the type of team member (human or AI), their performance (high or low), and the performance of other team members (high or low). AI team members were perceived to have higher ability and integrity but lower benevolence, which led to no differences in trustworthiness or willingness to work with them. However, the presence of an AI team member resulted in lower process satisfaction. When the AI team member performed well, participants perceived less conflict compared to a human team member with the same performance, but there were no differences in perceived conflict when it performed poorly. There were no other interactions with performance, indicating that the AI team member was judged similarly to humans, irrespective of variations in performance; there was no evidence of algorithm aversion. Our research suggests that AI team members are likely to be accepted into teams, meaning that many old collaboration research questions may need to be reexamined to consider AI team members.","PeriodicalId":50154,"journal":{"name":"Journal of Management Information Systems","volume":"40 1","pages":"307 - 337"},"PeriodicalIF":7.7,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47073950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1080/07421222.2023.2196776
Jun Zhang, Qiqi Jiang, Wenping Zhang, Lele Kang, P. Lowry, Zhang Xiong
ABSTRACT Social gamification, which allows technology users to interact with each other in gamified tasks, has drawn increasing interest due to its effectiveness in facilitating users’ game engagement and task efforts. In social gamification, users can compete or cooperate with other users or teams to complete game tasks and achieve game goals. However, it remains unclear how various social interaction mechanisms (SIMs), such as cooperation, interpersonal competition, and intergroup competition, influence gamification outcomes when they are separately or jointly implemented. In addition, the effects of SIMs on experiential and instrumental gamification outcomes have not been well differentiated. In this study, we systematically investigate the influences of these fundamental SIMs, as well as the possible interaction effects among them, on fitness app users’ game engagement and fitness behavior. Using a fitness app custom-developed for the Chinese market, Fitness Castle, we conducted a longitudinal field experiment to test our proposed model and hypotheses. The results indicate that when separately implemented, cooperation and interpersonal competition can lead to differential instrumental gamification outcomes in the fitness context. We also systematically compare the differential gamification outcomes when cooperation, interpersonal competition, and intergroup competition are combined in various coopetition settings. Our study offers a theory-based framework and design principles for social gamification. Our findings help practitioners better design SIMs in their gamified technologies with the purpose of achieving optimal experiential and instrumental gamification outcomes simultaneously.
{"title":"Explaining the Outcomes of Social Gamification: A Longitudinal Field Experiment","authors":"Jun Zhang, Qiqi Jiang, Wenping Zhang, Lele Kang, P. Lowry, Zhang Xiong","doi":"10.1080/07421222.2023.2196776","DOIUrl":"https://doi.org/10.1080/07421222.2023.2196776","url":null,"abstract":"ABSTRACT Social gamification, which allows technology users to interact with each other in gamified tasks, has drawn increasing interest due to its effectiveness in facilitating users’ game engagement and task efforts. In social gamification, users can compete or cooperate with other users or teams to complete game tasks and achieve game goals. However, it remains unclear how various social interaction mechanisms (SIMs), such as cooperation, interpersonal competition, and intergroup competition, influence gamification outcomes when they are separately or jointly implemented. In addition, the effects of SIMs on experiential and instrumental gamification outcomes have not been well differentiated. In this study, we systematically investigate the influences of these fundamental SIMs, as well as the possible interaction effects among them, on fitness app users’ game engagement and fitness behavior. Using a fitness app custom-developed for the Chinese market, Fitness Castle, we conducted a longitudinal field experiment to test our proposed model and hypotheses. The results indicate that when separately implemented, cooperation and interpersonal competition can lead to differential instrumental gamification outcomes in the fitness context. We also systematically compare the differential gamification outcomes when cooperation, interpersonal competition, and intergroup competition are combined in various coopetition settings. Our study offers a theory-based framework and design principles for social gamification. Our findings help practitioners better design SIMs in their gamified technologies with the purpose of achieving optimal experiential and instrumental gamification outcomes simultaneously.","PeriodicalId":50154,"journal":{"name":"Journal of Management Information Systems","volume":"40 1","pages":"401 - 439"},"PeriodicalIF":7.7,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41408959","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1080/07421222.2023.2196774
Jing Gong, Yi Liang, Narayan Ramasubbu
ABSTRACT Firms often assemble digital infrastructures using continuously evolving software applications sourced from a multitude of vendors. Using the theoretical lens of the threat-rigidity thesis, we raise the possibility that during adverse environmental conditions, software-vendor diversification can be a source of organizational rigidity that may dampen firm performance. Empirical analysis using data on 918 large public U.S. firms operating during two severe environmental shocks, the global financial crisis and the burst of the dot-com bubble, lends strong support to our thesis. Results indicate that a variety of firm performance indicators (e.g., stock return and operating income measures) are negatively associated with software-vendor diversification during crisis periods. Mediation analysis highlights the role of IT-related material weakness in firms’ internal controls in transmitting threat-rigidity effects that decrease performance. These results underscore the importance of software portfolio optimization for countering the dysfunctional effects of software-vendor diversification during adverse environmental shocks.
{"title":"Software-Vendor Diversification: A Source of Organizational Rigidity in Adversity?","authors":"Jing Gong, Yi Liang, Narayan Ramasubbu","doi":"10.1080/07421222.2023.2196774","DOIUrl":"https://doi.org/10.1080/07421222.2023.2196774","url":null,"abstract":"ABSTRACT Firms often assemble digital infrastructures using continuously evolving software applications sourced from a multitude of vendors. Using the theoretical lens of the threat-rigidity thesis, we raise the possibility that during adverse environmental conditions, software-vendor diversification can be a source of organizational rigidity that may dampen firm performance. Empirical analysis using data on 918 large public U.S. firms operating during two severe environmental shocks, the global financial crisis and the burst of the dot-com bubble, lends strong support to our thesis. Results indicate that a variety of firm performance indicators (e.g., stock return and operating income measures) are negatively associated with software-vendor diversification during crisis periods. Mediation analysis highlights the role of IT-related material weakness in firms’ internal controls in transmitting threat-rigidity effects that decrease performance. These results underscore the importance of software portfolio optimization for countering the dysfunctional effects of software-vendor diversification during adverse environmental shocks.","PeriodicalId":50154,"journal":{"name":"Journal of Management Information Systems","volume":"40 1","pages":"338 - 365"},"PeriodicalIF":7.7,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42454842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1080/07421222.2023.2196777
Yang Pan, Sunil Mithas, J. P. Hsieh, Che-Wei Liu
ABSTRACT How do investors’ risk preferences influence the relationships between investors’ online channel use intensity and both their trading behaviors and performance? This study answers this important question even as investors are increasingly relying on the Internet for their trading activities. We leverage rare and unique micro-level historical dataset from more than 7,000 investor accounts over a 44-month period between 2010 and 2013 at a large brokerage firm in China. The dataset and analyses enable us to provide new insights into how investors’ online channel use intensity and risk preferences jointly influence their trading behaviors and performance, even though some other aspects of financial markets have changed considerably over the years. The findings reveal that although online channel use intensity is associated with increased trading volume, trading frequency, and investment returns, these effects differ across investors with different risk preferences. We find that while online channel use intensity has strong positive effects on transaction frequency for both risk-seeking and risk-averse investors, it has a much lower effect on trading volume for risk-averse investors than for risk-seeking investors. We further find that risk-averse investors with higher online channel use intensity outperform investors with other risk preferences in terms of investment performance. This paper contributes to the emerging literature at the intersection of information systems and behavioral finance by revealing the moderating role of risk preferences in the relationships between investors’ online trading channel use intensity and both their trading behaviors and outcomes. We discuss the implications for research and practice.
{"title":"Do Risk Preferences Shape the Effect of Online Trading on Trading Frequency, Volume, and Portfolio Performance?","authors":"Yang Pan, Sunil Mithas, J. P. Hsieh, Che-Wei Liu","doi":"10.1080/07421222.2023.2196777","DOIUrl":"https://doi.org/10.1080/07421222.2023.2196777","url":null,"abstract":"ABSTRACT How do investors’ risk preferences influence the relationships between investors’ online channel use intensity and both their trading behaviors and performance? This study answers this important question even as investors are increasingly relying on the Internet for their trading activities. We leverage rare and unique micro-level historical dataset from more than 7,000 investor accounts over a 44-month period between 2010 and 2013 at a large brokerage firm in China. The dataset and analyses enable us to provide new insights into how investors’ online channel use intensity and risk preferences jointly influence their trading behaviors and performance, even though some other aspects of financial markets have changed considerably over the years. The findings reveal that although online channel use intensity is associated with increased trading volume, trading frequency, and investment returns, these effects differ across investors with different risk preferences. We find that while online channel use intensity has strong positive effects on transaction frequency for both risk-seeking and risk-averse investors, it has a much lower effect on trading volume for risk-averse investors than for risk-seeking investors. We further find that risk-averse investors with higher online channel use intensity outperform investors with other risk preferences in terms of investment performance. This paper contributes to the emerging literature at the intersection of information systems and behavioral finance by revealing the moderating role of risk preferences in the relationships between investors’ online trading channel use intensity and both their trading behaviors and outcomes. We discuss the implications for research and practice.","PeriodicalId":50154,"journal":{"name":"Journal of Management Information Systems","volume":"40 1","pages":"440 - 469"},"PeriodicalIF":7.7,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46827655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1080/07421222.2023.2196772
K. Chen, Yifan Fan, S. Liao
ABSTRACT Crypto tokens, issued and managed via smart contracts, function as rewards in blockchain systems to encourage user participation. Distinct from monetary incentives, token incentives are uncertain in reward magnitude due to the large swings in token prices on crypto markets. By focusing on token price volatility, this study investigates how the reward uncertainty affects user contribution in a tokenized digital platform. Our empirical setting is Steemit, a platform where bloggers write posts and share token rewards based on their posts’ popularity. We find that while high token price volatility induces a large volume of blog posts, it diminishes post quality. The dichotomous effects are explained via two mechanisms: users’ direct reactions to reward uncertainties and their indirect reactions, mediated by altered token preference amid volatility shocks. Deeply exploring this dynamic process, our results reveal that token price volatility facilitates a platform’s network short-term effect but impairs long-term user creativity. Our empirical findings thus extend the literature on blockchain economics and cryptocurrencies and have practical implications for the design of incentive mechanisms on tokenized digital platforms.
{"title":"Token Incentives in a Volatile Crypto Market: The Effects of Token Price Volatility on User Contribution","authors":"K. Chen, Yifan Fan, S. Liao","doi":"10.1080/07421222.2023.2196772","DOIUrl":"https://doi.org/10.1080/07421222.2023.2196772","url":null,"abstract":"ABSTRACT Crypto tokens, issued and managed via smart contracts, function as rewards in blockchain systems to encourage user participation. Distinct from monetary incentives, token incentives are uncertain in reward magnitude due to the large swings in token prices on crypto markets. By focusing on token price volatility, this study investigates how the reward uncertainty affects user contribution in a tokenized digital platform. Our empirical setting is Steemit, a platform where bloggers write posts and share token rewards based on their posts’ popularity. We find that while high token price volatility induces a large volume of blog posts, it diminishes post quality. The dichotomous effects are explained via two mechanisms: users’ direct reactions to reward uncertainties and their indirect reactions, mediated by altered token preference amid volatility shocks. Deeply exploring this dynamic process, our results reveal that token price volatility facilitates a platform’s network short-term effect but impairs long-term user creativity. Our empirical findings thus extend the literature on blockchain economics and cryptocurrencies and have practical implications for the design of incentive mechanisms on tokenized digital platforms.","PeriodicalId":50154,"journal":{"name":"Journal of Management Information Systems","volume":"40 1","pages":"683 - 711"},"PeriodicalIF":7.7,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44370947","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1080/07421222.2023.2196780
Jiaheng Xie, Yidong Chai, Xinyu Liu
ABSTRACT As video-sharing sites emerge as a critical part of the social media landscape, video viewership prediction becomes essential for content creators and businesses to optimize influence and marketing outreach with minimum budgets. Although deep learning champions viewership prediction, it lacks interpretability, which is required by regulators and is fundamental to the prioritization of the video production process and promoting trust in algorithms. Existing interpretable predictive models face the challenges of imprecise interpretation and negligence of unstructured data. Following the design-science paradigm, we propose a novel Precise Wide-and-Deep Learning (PrecWD) to accurately predict viewership with unstructured video data and well-established features while precisely interpreting feature effects. PrecWD’s prediction outperforms benchmarks in two case studies and achieves superior interpretability in two user studies. We contribute to IS knowledge base by enabling precise interpretability in video-based predictive analytics and contribute nascent design theory with generalizable model design principles. Our system is deployable to improve video-based social media presence.
{"title":"Unbox the Black-Box: Predict and Interpret YouTube Viewership Using Deep Learning","authors":"Jiaheng Xie, Yidong Chai, Xinyu Liu","doi":"10.1080/07421222.2023.2196780","DOIUrl":"https://doi.org/10.1080/07421222.2023.2196780","url":null,"abstract":"ABSTRACT As video-sharing sites emerge as a critical part of the social media landscape, video viewership prediction becomes essential for content creators and businesses to optimize influence and marketing outreach with minimum budgets. Although deep learning champions viewership prediction, it lacks interpretability, which is required by regulators and is fundamental to the prioritization of the video production process and promoting trust in algorithms. Existing interpretable predictive models face the challenges of imprecise interpretation and negligence of unstructured data. Following the design-science paradigm, we propose a novel Precise Wide-and-Deep Learning (PrecWD) to accurately predict viewership with unstructured video data and well-established features while precisely interpreting feature effects. PrecWD’s prediction outperforms benchmarks in two case studies and achieves superior interpretability in two user studies. We contribute to IS knowledge base by enabling precise interpretability in video-based predictive analytics and contribute nascent design theory with generalizable model design principles. Our system is deployable to improve video-based social media presence.","PeriodicalId":50154,"journal":{"name":"Journal of Management Information Systems","volume":"40 1","pages":"541 - 579"},"PeriodicalIF":7.7,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48297299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1080/07421222.2023.2196771
Ruiyun Xu, Hailiang Chen, J. Zhao
ABSTRACT While venture capital firms are increasingly relying on recommendation models in investment decisions, existing startup recommendation models fail to consider the uniqueness of venture capital context, including two-sided matching between investing and investee firms and a lack of information disclosure requirements on startups. Following the design science research paradigm and guided by the proximity principle from social psychology, we develop a novel framework called SocioLink by depicting and analyzing various relations in a knowledge graph via machine learning. Our experimental results show that SocioLink significantly outperforms state-of-the-art startup recommendation methods in both accuracy and quality. This improvement is driven by not only the inclusion of social relations but also the superiority of modelling relations via knowledge graph. We also develop a web-based prototype to demonstrate explainable artificial intelligence. This work contributes to the FinTech literature by adding an innovative design artifact—SocioLink—for decision support in the investment context.
{"title":"SocioLink: Leveraging Relational Information in Knowledge Graphs for Startup Recommendations","authors":"Ruiyun Xu, Hailiang Chen, J. Zhao","doi":"10.1080/07421222.2023.2196771","DOIUrl":"https://doi.org/10.1080/07421222.2023.2196771","url":null,"abstract":"ABSTRACT While venture capital firms are increasingly relying on recommendation models in investment decisions, existing startup recommendation models fail to consider the uniqueness of venture capital context, including two-sided matching between investing and investee firms and a lack of information disclosure requirements on startups. Following the design science research paradigm and guided by the proximity principle from social psychology, we develop a novel framework called SocioLink by depicting and analyzing various relations in a knowledge graph via machine learning. Our experimental results show that SocioLink significantly outperforms state-of-the-art startup recommendation methods in both accuracy and quality. This improvement is driven by not only the inclusion of social relations but also the superiority of modelling relations via knowledge graph. We also develop a web-based prototype to demonstrate explainable artificial intelligence. This work contributes to the FinTech literature by adding an innovative design artifact—SocioLink—for decision support in the investment context.","PeriodicalId":50154,"journal":{"name":"Journal of Management Information Systems","volume":"40 1","pages":"655 - 682"},"PeriodicalIF":7.7,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42910401","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-04-03DOI: 10.1080/07421222.2023.2196778
W. Jabr, Abhijeet Ghoshal, Yichen Cheng, P. Pavlou
ABSTRACT Online retailers are increasingly focused on maintaining a long-term relationship with customers, encouraging repeat visits rather than single-time purchases to increase customer lifetime value. To help retailers maximize the probabilities of customers’ revisiting and purchasing, we develop a two-stage model to better characterize and predict these two fundamental customer activities. In the first stage, we characterize the propensity of a customer revisiting the retailer’s website. In the second stage, we develop a stochastic model that predicts revisits while also incorporating individual customer heterogeneity in exerted search effort during repeated visits. This heterogeneity is based on individual customer preferences in the choice of consideration sets, product information, pricing, and the search environment. Using customer level clickstream data, we show that our approach is not only better at predicting repeat customer visits, compared to existing methods, but also explainable and managerially interpretable. Most importantly, using computationally efficient simulation-based prescriptive analytics, we leverage our modeling approach to propose practical intervention strategies that maximize the joint likelihoods of customers revisiting and purchasing at the individual customer level.
{"title":"Maximizing Online Revisiting and Purchasing: A Clickstream-Based Approach to Enhancing Customer Lifetime Value","authors":"W. Jabr, Abhijeet Ghoshal, Yichen Cheng, P. Pavlou","doi":"10.1080/07421222.2023.2196778","DOIUrl":"https://doi.org/10.1080/07421222.2023.2196778","url":null,"abstract":"ABSTRACT Online retailers are increasingly focused on maintaining a long-term relationship with customers, encouraging repeat visits rather than single-time purchases to increase customer lifetime value. To help retailers maximize the probabilities of customers’ revisiting and purchasing, we develop a two-stage model to better characterize and predict these two fundamental customer activities. In the first stage, we characterize the propensity of a customer revisiting the retailer’s website. In the second stage, we develop a stochastic model that predicts revisits while also incorporating individual customer heterogeneity in exerted search effort during repeated visits. This heterogeneity is based on individual customer preferences in the choice of consideration sets, product information, pricing, and the search environment. Using customer level clickstream data, we show that our approach is not only better at predicting repeat customer visits, compared to existing methods, but also explainable and managerially interpretable. Most importantly, using computationally efficient simulation-based prescriptive analytics, we leverage our modeling approach to propose practical intervention strategies that maximize the joint likelihoods of customers revisiting and purchasing at the individual customer level.","PeriodicalId":50154,"journal":{"name":"Journal of Management Information Systems","volume":"40 1","pages":"470 - 502"},"PeriodicalIF":7.7,"publicationDate":"2023-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45495428","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"管理学","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：