A Theory-based Deep-Learning Approach to Detecting Disinformation in Financial Social Media

2023 | Information Systems Frontiers | Citations: 0

Authors: Chung, Wingyan; Zhang, Yinqiang; Pan, Jia

Abstract: The spreading of disinformation in social media threatens cybersecurity and unde ... Expand

Abstract: The spreading of disinformation in social media threatens cybersecurity and undermines market efficiency. Detecting disinformation is challenging due to large volumes of social media content and a rapidly changing environment. This research developed and validated a theory-based, novel deep-learning approach (called TRNN) to disinformation detection. Grounded in social and psychological theories, TRNN uses deep-learning and data-centric augmentation to enhance disinformation detection in financial social media. Temporal and contextual information is encoded as specific knowledge about human-validated disinformation, which was identified from our unique collection of 745,139 financial social media messages about four U.S. high-tech company stocks and their fine-grained trading data. TRNN uses multiple series of long short-term memory (LSTM) recurrent neurons to learn dynamic and hidden patterns to support disinformation detection. Our experimental findings show that TRNN significantly outperformed widely-used machine learning techniques in terms of precision, recall, F-score and accuracy, achieving consistently better classification performance in disinformation detection. A case study of Apple Inc.’s stock price movement demonstrates the potential usability of TRNN for secure knowledge management. The research contributes to developing novel approach and model, producing new information systems artifacts and dataset, and providing empirical findings of detecting online disinformation. Collapse

Topics: disinformation social media Twitter fake news usability

Methods: machine learning experiment design artifact deep learning recurrent neural network

Theories: psychological theory

Cross-cultural and Institutional Perspectives on Information Technology Governance

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Fernandes, Pedro; Pereira, Ruben; Wiedenhoft, Guilherme

Abstract: Nowadays, over 20% of organizations' worldwide capital expenditure goes toward ... Expand

Abstract: Nowadays, over 20% of organizations' worldwide capital expenditure goes toward Information Technology (IT). Hence IT Governance (ITG) is essential to establish a mutually beneficial connection between IT and the business. To deploy ITG, some factors, such as Organizational Culture (OC), should be considered. This study focuses on how the different cultures in the OCAI model affect employees' perception of ITG institutionalization. A survey was conducted on 513 workers from over 150 companies worldwide. Our model was validated using the Kruskal-Wallis H test. Although the results were not as anticipated, the general hypothesis was validated, demonstrating that individuals' perceptions of ITG institutionalization are influenced by their predominant OC type. Market and Hierarchy cultures show higher levels of individual perception of ITG. Organizations will learn how various cultures affect employees' perceptions of ITG, which will help them create a more ITG-oriented culture, greater alignment between business and IT, and more IT-enabled value. Collapse

Topics: organizational culture missing data national culture anonymity

Methods: survey Kruskal Wallis test nonparametric test factor analysis data transformation

Theories: institutional theory

Explanation matters: An experimental study on explainable AI

2023 | Electronic Markets | Citations: 0

Authors: Hamm, Pascal; Klesel, Michael; Coberger, Patricia; Wittmann, H. Felix

Abstract: Explainable artificial intelligence (XAI) is an important advance in the field o ... Expand

Abstract: Explainable artificial intelligence (XAI) is an important advance in the field of machine learning to shed light on black box algorithms and thus a promising approach to improving artificial intelligence (AI) adoption. While previous literature has already addressed the technological benefits of XAI, there has been little research on XAI from the user’s perspective. Building upon the theory of trust, we propose a model that hypothesizes that post hoc explainability (using Shapley Additive Explanations) has a significant impact on use-related variables in this context. To test our model, we designed an experiment using a randomized controlled trial design where participants compare signatures and detect forged signatures. Surprisingly, our study shows that XAI only has a small but significant impact on perceived explainability. Nevertheless, we demonstrate that a high level of perceived explainability has a strong impact on important constructs including trust and perceived usefulness. A post hoc analysis shows that hedonic factors are significantly related to perceived explainability and require more attention in future research. We conclude with important directions for academia and for organizations. Collapse

Topics: explainable artificial intelligence artificial intelligence perceived ease of use perceived usefulness digital dashboard

Methods: experimental group experiment parametric test experimental task ANOVA

Theories: information systems theory trust theory

Mixed Method Literature Review on Computational Thinking – Developing an Integrated Research Framework and Research Propositions

2023 | European Conference On Information Systems | Citations: 0

Authors: Hubert, Mirja; Petersen, Camilla Kølsen; Akther, Farzana; Carugati, Andrea

Abstract: Being part of a digital societies requires a "digital mindset". But what exactl ... Expand

Abstract: Being part of a digital societies requires a "digital mindset". But what exactly is a digital mindset? There are many answers that have not really been systematized. A related area where systematization already started is Computational Thinking (CT): a branch of pedagogy that catalogued the capabilities necessary to live in a digitized and technology-driven world. CT is defined as a general problem-solving competence based on abstraction, algorithmic-thinking, problem-decomposition, pattern-recognition, and evaluation. Researchers promote CT as a 21 st century skills important for everyone. Aim of our article is to reveal the relevance of CT as complement to IS-research in the creation of a digital mindset. We conducted a computational and qualitative literature review using quantitative bibliometric-citation analysis. From the analysis, we derive an integrative framework to identify how IS-research could profit from teaching, and applying CT, as a competence in the digital transformation of their discipline. Collapse

Topics: digital transformation IS education organizational culture robotic IS maturity

Methods: co-citation analysis qualitative coding literature study bibliometric analysis theoretical contribution

Theories: general systems theory

Do Employees Work Less for Female Leaders? A Multi-Method Study of Entrepreneurial Firms

2023 | Organization Science | Citations: 0

Authors: Kacperczyk, Olenka; Younkin, Peter; Rocha, Vera

Abstract: We propose that female-founded ventures receive a lower amount of employee labor ... Expand

Abstract: We propose that female-founded ventures receive a lower amount of employee labor for equal pay because employees are more likely to decline requests for additional labor by female founders. First, using longitudinal matched employer-employee data covering all founders of new ventures with personnel in Portugal between 2002 and 2012, we confirm that full-time employees contribute fewer regular hours and less overtime work to female-founded firms. Second, using a series of online experiments, we show that this variation in employee labor across female and male-founded firms is partly motivated by a difference in the employee’s expectations of work demands. Specifically, employees perceive female founders’ requests for additional labor to be unfair and more difficult than expected, and both these perceptions explain the lower amount of employee labor supplied in female-founded ventures. Overall, our findings uncover a novel mechanism that helps explain the existence of a gender gap in entrepreneurship beyond the entry stage. Supplemental Material: The online appendices are available at https://doi.org/10.1287/orsc.2022.1611. Collapse

Topics: entrepreneurship IT career database system productivity missing data

Methods: experiment quantitative observational study theory development survey descriptive statistic

Theories: sociological theory

Diffusion of real versus misinformation during a crisis event: A big data-driven approach

2023 | International Journal of Information Management | Citations: 0

Authors: King, Kelvin K.; Wang, Bin

Abstract: Misinformation has captured the interest of academia in recent years with severa ... Expand

Abstract: Misinformation has captured the interest of academia in recent years with several studies looking at the topic broadly with inconsistent results. In this research, we attempt to bridge the gap in the literature by examining the impacts of user-, time-, and content-based characteristics that affect the virality of real versus misinformation during a crisis event. Using a big data-driven approach, we collected over 42 million tweets during Hurricane Harvey and obtained 3589 original verified real or false tweets by cross-checking with fact-checking websites and a relevant federal agency. Our results show that virality is higher for misinformation, novel tweets, and tweets with negative sentiment or lower lexical density. In addition, we reveal the opposite impacts of sentiment on the virality of real news versus misinformation. We also find that tweets on the environment are less likely to go viral than the baseline religious news, while real social news tweets are more likely to go viral than misin­ formation on social news. Collapse

Topics: Twitter misinformation social media hurricane big data

Methods: machine learning computational algorithm natural language processing decision tree classification gradient boosting

Cultural Roots of Entrepreneurship: Evidence from Second-Generation Immigrants

2023 | Organization Science | Citations: 0

Authors: Kleinhempel, Johannes; Klasing, Mariko J.; Beugelsdijk, Sjoerd

Abstract: Does national culture influence entrepreneurship? Given that entrepreneurship an ... Expand

Abstract: Does national culture influence entrepreneurship? Given that entrepreneurship and the economic, formal institutional, and cultural characteristics of nations are deeply intertwined and co-vary, it is difficult to isolate the effect of culture on entrepreneurship. In this study, we examine the self-employment choices of second-generation immigrants who were born, educated, and currently live in one country, but were raised by parents stemming from another country. We argue that entrepreneurship is influenced by durable, portable, and intergenerationally transmitted cultural imprints such that second-generation immigrants are more likely to become entrepreneurs if their parents originate from countries characterized by a strong entrepreneurial culture. Our multilevel analysis of two independent samples—65,323 second-generation immigrants of 52 different ancestries who were born, were raised, and live in the United States and 4,165 second-generation immigrants of 31 ancestries in Europe—shows that entrepreneurial culture is positively associated with the likelihood that individuals are entrepreneurs. Our results are robust to alternative non-cultural explanations, such as differences in resource holdings, labor market discrimination, and direct parent-child linkages. Overall, our study highlights the durability, portability, and intergenerational transmission of entrepreneurial culture as well as the profound impact of national culture on entrepreneurship. Supplemental Material: The online appendix is available at https://doi.org/10.1287/orsc.2022.1645. Collapse

Topics: entrepreneurship human resource management accounting national culture database system

Methods: hierarchical linear modeling survey robustness check descriptive statistic instrumental variables estimation

Theories: theory of economic development

Examining the Relationship between National Cybersecurity Commitment, Culture, and Digital Payment Usage: An Institutional Trust Theory Perspective

2023 | Information Systems Frontiers | Citations: 1

Authors: Krishna, Ben; Krishnan, Satish; Sebastian, M. P.

Abstract: Cyberattacks can be considered one of the fundamental challenges that paralyze t ... Expand

Abstract: Cyberattacks can be considered one of the fundamental challenges that paralyze the progress of digital payment usage (DPU) progress among citizens, as consumers shun away from using digital banking services due to increased concern over information security. National Cybersecurity Commitment (NCSC) has emerged as a preventive cybersecurity mechanism for countries to tackle such cybersecurity threats. Previous studies have shown that a country's NCSC positively impacts the business and economy of the country. This study examines the effect of NCSC on digital payment usage (DPU) across nations by grounding our discussion on the institutional trust theory. As trusting belief in security measures is a culturally embedded characteristic, we also examine the moderating role of national culture through Hofstede’s cultural dimensions. We use multilevel models to analyze publicly available archives of repeated cross-sectional data covering 76 countries to test the proposed relationships. Our findings indicate that NCSC has a positive influence on DPU. Further, our results highlight that the relationship between NCSC and DPU in a country is contingent on cultural dimensions. Overall, the evidence suggests that a competent cybersecurity environment compatible with cultural values can influence the speedy diffusion of digital payments in a country. Implications of our findings for research and practice are also discussed. Collapse

Topics: IT security internet technology national culture electronic finance information system use

Methods: longitudinal research hierarchical linear modeling cross sectional research archival research time series analysis

Theories: trust theory cultural dimensions theory contingency theory theory of economic growth

The puzzle of experience vs. memory: Peak-end theory and strategic gamification design in M-commerce

2023 | Information & Management | Citations: 0

Authors: Li, Manning; Jiang, Zhenhui (Jack); Ma, Guanghui

Abstract: As businesses increasingly use gamified mobile marketing campaign (GMMC) systems ... Expand

Abstract: As businesses increasingly use gamified mobile marketing campaign (GMMC) systems to engage mobile shop­ pers, gamification in m-commerce systems warrants more attention in both IS research and design practices. Inspired by peak-end theory, this study focused on the puzzling differences between user experience vs. memory and empirically examined the impact of different experience orders of cognitive load on user perceptions and behavioral intentions. Overall, the outcomes of this research suggest that appropriate applications of the peakend effect, moderated via users’ regulatory focus styles, can alleviate the negative mental utility imagery of users, reducing their perceived uncertainties and opt-out intentions from the GMMC. Important implications for research and practice are then discussed. Collapse

Topics: electronic data interchange marketing management user experience gamification systems design

Methods: experiment electroencephalography survey multivariate analysis of variance survey design

Theories: technology acceptance model flow theory self determination theory theory of planned behavior

Factors Influencing Perceived Legitimacy of Social Scoring Systems: Subjective Privacy Harms and the Moderating Role of Transparency

2023 | International Conference on Information Systems | Citations: 0

Authors: Loefflad, Carmen; Chen, Mo; Grossklags, Jens

Abstract: Technological advancements in recent years have enabled the spread of automated ... Expand

Abstract: Technological advancements in recent years have enabled the spread of automated decision-making (ADM) systems. Social scoring systems are a specific instance of ADM system, using behavioral scores to encourage pro-social behaviors. Building on a survey following an experimental study, we present two structural equation models to determine the impacts of different levels of transparency on the perceived legitimacy of scoring systems, as well as on people's intention to comply with the system. The models are built on well-established theories highlighting procedural justice and outcome favorabilities as key determinating factors. Our results suggest that the determinants of perceived legitimacy are strongly shaped by the level of transparency. However, transparency elevates subjective privacy harms. Our findings add to the ongoing debate on the transparency of ADM systems, by identifying a trade-off between the elimination of outcome favorabilities in determining perceptions of legitimacy, and increased subjective privacy harms, weakening people's intention to comply. Collapse

Topics: privacy decision making information privacy concern anonymity

Methods: experiment structural equation modeling survey SEM tool factor analysis

Theories: procedural justice theory