sDTM: A Supervised Bayesian Deep Topic Model for Text Analytics

2023 | Information Systems Research | Citations: 0

Authors: Yang, Yi; Zhang, Kunpeng; Fan, Yangyang

Abstract: Topic modeling methods such as latent Dirichlet allocation (LDA) are powerful to ... Expand

Abstract: Topic modeling methods such as latent Dirichlet allocation (LDA) are powerful tools for analyzing massive amounts of textual data. They have been used extensively in information systems (IS) and business discipline research to identify latent topics for data exploration and as a feature engineering mechanism to derive new variables for analyses. However, existing topic modeling approaches are mostly unsupervised and only leverage textual data, while ignoring additional useful metadata often associated with text, such as star ratings in customer reviews or categories of posts in online forums. As a result, the identified topics and variables derived based on the learned topic model may not be accurate, which could lead to incorrect estimations that affect subsequent empirical analysis and to inferior performance on predictive tasks. In this study, we propose a novel supervised deep topic modeling approach called sDTM, which combines a neural variational autoencoder model and a recurrent neural network. sDTM leverages the auxiliary data associated with text to enhance the topic modeling capability. We conduct empirical case studies and predictive analytics on an online consumer review data set and an online knowledge community data set. Experimental results show that in comparison with benchmark methods, sDTM can enhance both the empirical estimation and predictive performance. sDTM makes methodological contributions to the IS literature and has direct relevance for research using text analytics.History: Alok Gupta, Senior Editor; Huimin Zhao, Associate Editor.Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2022.1124. Collapse

Topics: online review open source user-generated content Wikipedia accounting

Methods: topic model deep learning machine learning BERT data transformation

Digital transformation solutions of entrepreneurial SMEs based on an information error-driven T-spherical fuzzy cloud algorithm

2023 | International Journal of Information Management | Citations: 0

Authors: Yang, Zaoli; Chang, Jinping; Huang, Lucheng; Mardani, Abbas

Abstract: The digital transformation of enterprises has become an inevitable development t ... Expand

Abstract: The digital transformation of enterprises has become an inevitable development trend and one of the key driving forces that promotes the sustainable development of enterprises. However, due to the many obstacles of financial burdens, technical thresholds, and talent shortages, digital transformation has become a challenging task for entrepreneurial Small and Medium-Sized Enterprises (SMEs). Additionally, many competitive digital trans­ formation solutions on the market cause confusion when enterprises must choose one. This study drew a new information error-driven T-spherical fuzzy cloud algorithm to evaluate digital transformation solutions of entrepreneurial SMEs and support its selection. First, an evaluation index system for the digital transformation solution of entrepreneurial SMEs was established from four aspects. Then, a new concept of a T-spherical fuzzy cloud was defined to represent the evaluation information of the indicators. Additionally, a T-spherical Fuzzy Cloud Weighted Heronian Mean (T-SFCWHM) operator was used to aggregate the evaluation information. Af­ terward, an evaluation and selection decision framework for the digital transformation solution of entrepre­ neurial SMEs based on the T-SFCWHM operator was developed. Further, a practical example was given to illustrate the effectiveness of the proposed method. Finally, a discussion of the findings in our study was con­ ducted, and the conclusions were summarized. Collapse

Topics: digital transformation cloud computing IT strategic planning decision making smart manufacturing

Methods: computational algorithm expert evaluation design science theoretical contribution synthesis

Theories: fuzzy set theory

Information Technology Adaption by Senior Citizens: Why Seniors Use IT

2023 | HICSS | Citations: 0

Authors: Yasuoka, M.

Abstract: Along with the progress of digitalization, it becomes essential for everyone to ... Expand

Abstract: Along with the progress of digitalization, it becomes essential for everyone to use digital means at every corner in society. At the same time, the potential disadvantages of not being able to use digital services have increased. This paper, by focusing on the elderly as one of the central concerns in the digital divide discussion, studies the elderly's technology acceptance through a comparative study of two countries. Denmark and Japan are chosen as subjects of the study, which have similarly advanced IT infrastructure but significant difference in IT utilization among the elderly. The comparative analysis shows that reasons why the elderly do not use IT are very different, but three key aspects are identified as essential drivers of IT use. That is: advanced usability, informal supporters, and external mandate. Our work identifies findings within the current digital divide discussion and provides implications for the future inclusion strategies of the elderly. Collapse

Topics: information system use digital divide mobile application technology adoption digital signature

Methods: cross sectional research survey qualitative interview literature study mixed method

Does stress reduce violation intention? Insights from eustress and distress processes on employee reaction to information security policies

2023 | European Journal of Information Systems | Citations: 0

Authors: Yazdanmehr, Adel; Li, Yuan; Wang, Jingguo

Abstract: Past research suggests that the demands of information security policies (ISPs) ... Expand

Abstract: Past research suggests that the demands of information security policies (ISPs) cause stress upon employees, leading them to violate the policies. It emphasises the distress process but overlooks a possible positive process that may arise from the ISP demands (i.e., the eustress process) and motivate employees to reduce ISP violations. This study explores both the distress and eustress processes. It proposes that the challenge and hindrance aspects of ISP demands induce these processes and subsequently affect ISP violations. Besides, employees’ ISP-related self-efficacy may facilitate or impede these processes. To test the research model, a survey was conducted on 375 employees in the U.S. The results show that the challenge aspect of ISP demands elicits a positive psychological response of employees, which in turn triggers their planful problem-solving to deal with these demands. In contrast, the hindrance aspect of ISP demands provokes a negative psychological response that triggers employees’ wishful thinking about ISP demands. Meanwhile, employees’ self-efficacy strengthens the effect of positive psychological response on planful problem-solving. Subsequently, planful problem-solving reduces employees’ intention to violate the ISP, while wishful thinking increases their intention. This dual-process view sheds new light on the connection between ISP demands and ISP violation intention. Collapse

Topics: problem solving self efficacy data security security policy technostress

Methods: survey chi squared test SEM tool data transformation structural equation modeling

Theories: organizational behavior theory

Employee responses to information security related stress: Coping and violation intention

2023 | Information Systems Journal | Citations: 1

Authors: Yazdanmehr, Adel; Li, Yuan; Wang, Jingguo

Abstract: Studies on employee responses to the information security policy (ISP) demands t ... Expand

Abstract: Studies on employee responses to the information security policy (ISP) demands to show that employees who experience stress over the demands would resort to emotion-focused coping to alleviate the stress and subsequently violate the ISP. However, their intent to engage in problem-focused coping to meet the ISP demands and possibly reduce ISP violations has yet to be analysed. We argue that both types of coping responses coexist in employee responses to ISP demands and they together influence ISP violation intention. Drawing upon the Transactional Model of Stress and Coping, we examine how security-related stress (SRS) triggers inward and outward emotion-focused coping, and problem-focused coping to the ISP demands, which together influence employee ISP violations. We also examine how ISP-related self-efficacy and organisational support moderate the effects of SRS on coping responses. We surveyed 200 employees in the United States to test our model. The results indicate that SRS triggers all three coping responses, and ISP-related self-efficacy and organisational support reduce the effects of SRS on inward and outward emotion-focused coping. Problem-focused coping then decreases ISP violation intention, whereas inward and outward emotion-focused coping increases it. The model was further verified with ISP compliance as the outcome construct, which yielded consistent results. Understanding various coping responses to SRS and the factors that facilitate or inhibit the responses can assist managers in effectively designing and implementing the ISP to reduce employee ISP violations. Collapse

Topics: self efficacy security policy data security problem solving internet technology

Methods: survey descriptive statistic partial least squares regression survey design factor analysis

Theories: technology threat avoidance theory

Can peers help reduce violations of information security policies? The role of peer monitoring

2023 | European Journal of Information Systems | Citations: 0

Authors: Yazdanmehr, Adel; Wang, Jingguo

Abstract: Peers may help others avoid violating organisational information security polici ... Expand

Abstract: Peers may help others avoid violating organisational information security policies (ISPs). This study explores how peer monitoring reduces employee ISP violation intention. We propose that peer monitoring discourages employees from violating ISP. Moreover, trust plays an important role. Trust not only facilitates peer monitoring, but also moderates the effect of peer monitoring on employee ISP violation intention. In addition, collective responsibility leads to peer monitoring. We test our research model with data from two waves of surveys of 254 employees in the United States conducted two weeks apart. We utilise four scenarios in the second wave of surveys capturing the dependent variable and measure all other constructs in the first wave of surveys. Our results suggest that peer monitoring decreases one’s intention to violate ISPs. Furthermore, both collective responsibility and trust contribute to peer monitoring. Finally, trust amplifies the effect of peer monitoring on employees’ intention to violate ISPs. We discuss the theoretical contributions and practical implications. Collapse

Topics: data security password social capital workstation team productivity

Methods: survey SEM tool expert panel theoretical contribution factor analysis

Theories: motivation theory

Problem Specification in Crowdsourcing Contests: A Natural Experiment

2023 | International Conference on Information Systems | Citations: 0

Authors: Ye, Kai; Koh, Tat Koon

Abstract: Problem specification is a key aspect in crowdsourcing contests through which s ... Expand

Abstract: Problem specification is a key aspect in crowdsourcing contests through which seekers convey their requirements and taste for the desired submissions. Hence, it is important to understand how problem specification should be framed to achieve better crowdsourcing contest outcomes. In this empirical study, we investigate the effects of a relatively more structured problem specification on contest quantity, solver quantity, and idea quality. We leverage a natural experiment set up on a major crowdsourcing contest platform where the problem specification of logo design contests changed from openended to structured. Our results show that the specification change impacts both seekers and solvers. Specifically, the number of contests increases after the change but solver quantity and idea quality in the respective contests tend to be lower. We discuss the theoretical and practical contributions of this research. Collapse

Topics: crowdsourcing web page self efficacy task characteristic web crawling

Methods: theory development experimental group longitudinal research natural experiment event study

Offline to online: The impacts of offline visit experience on online behaviors and service in an Internet hospital

2023 | Electronic Markets | Citations: 0

Authors: Ye, Qing; Wu, Hong

Abstract: Only the online-to-offline process has been explored, the literature is largely ... Expand

Abstract: Only the online-to-offline process has been explored, the literature is largely silent on the offline-to-online process, which restricts the online service quality and the development of Internet hospitals. We approach this issue by investigating the impact of patients’ offline visit experience on their online engagement, and then how patients’ online engagement affects the quality and efficiency of physicians’ online services. Using archival data with 69,078 online consultation records from a large tertiary hospital and its Internet hospital in China, we developed several regression models to analyze the impact of offline visit experience on patients’ online information provision and the effect of online information provision on service quality and efficiency. We identified that offline visit experience has heterogeneous effects on patients’ online information provision, and patients’ online information provision positively influences physicians’ online service quality, while negatively influencing online service efficiency. Moreover, online information provision mediates the relationship between offline visit experience and online service quality. This study contributes to our understanding of the mechanisms by which the offline visit experience influences online service quality in the online-offline channel integration context. Collapse

Topics: service quality data quality internet technology healthcare data electronic health

Methods: regression analysis method robustness check descriptive statistic cross sectional research statistical hypothesis test

Theories: information integration theory

Local Popularity: A Double-edged Tool in Platform Operation

2023 | International Conference on Information Systems | Citations: 0

Authors: Ye, Xingchen; LI, Andy Tao; Li, Ting

Abstract: Although displaying local popularity is wildly adopted by major platforms, the ... Expand

Abstract: Although displaying local popularity is wildly adopted by major platforms, the actual effect of such information cues on motivating users has not been documented. Findings from a field experiment suggest that local popularity effectively motivates users to invite more friends but surprisingly reduces users' self-participation. Social conformity theory may account for such effects: local information encourages users to invite their local friends, but such effect is limited to users from small cities since users in a relatively small community are more bonded and less likely to reject the invitation due to social pressure. Meanwhile, local information attenuates the power of popularity (e.g., fewer registered users in the local area) and ultimately discourages users' self-participation. This study deepens our understanding of displaying popularity cue in improving platform operation, based on which we suggest that practitioners should be cautious about the persuasive power of such information cues in location-based marketing. Collapse

Topics: participatory design mobile application marketing management data breach privacy

Methods: design methodology field experiment experiment experimental group robustness check

Unveiling the value of big data analytics use: A digital hospital case study

2023 | European Conference On Information Systems | Citations: 0

Authors: Yeh, Yi-Ting; Eden, Rebekah; Fielt, Erwin; Syed, Rehan; Donovan, Raelene; Eley, Robert; Staib, Andrew

Abstract: Big Data Analytics (BDA) has attracted significant attention from healthcare or ... Expand

Abstract: Big Data Analytics (BDA) has attracted significant attention from healthcare organisations seeking to leverage its analytical capabilities to resolve the challenges plaguing healthcare delivery. Yet, the outcomes of BDA have been inconclusive with unintended consequences arising, indicating the path for BDA value creation remains unclear. Responding to calls in literature, we seek to unveil the role of use in BDA value creation. Synthesising literature, we developed the BDA-Use-Value (BDA-UV) framework and subsequently used a case study of an Australian digital hospital to explore the framework. Overall, we found support for the BDA-UV framework and revealed nuanced insights surrounding a cyclical relationship between BDA use and system capabilities, a fuzzy boundary between BDA organisational capabilities and complementary organisational resources, and the complexity of BDA learning loop. Our framework and findings can also assist executives of digital hospitals to tailor their BDA strategies. Collapse

Topics: information technology capability organizational value data quality information system use value creation

Methods: qualitative interview case study qualitative coding single case study conceptual modelling

Theories: theory of affordance