On Predicting ESG Ratings Using Dynamic Company Networks

2023 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Ang, Gary; Guo, Zhiling; Lim, Ee-Peng

Abstract: Environmental, social and governance (ESG) considerations play an increasingly i ... Expand

Abstract: Environmental, social and governance (ESG) considerations play an increasingly important role due to the growing focus on sustainability globally. Entities, such as banks and investors, utilize ESG ratings of companies issued by specialized rating agencies to evaluate ESG risks of companies. The process of assigning ESG ratings by human analysts is however laborious and time intensive. Developing methods to predict ESG ratings could alleviate such challenges, allow ESG ratings to be generated in a more timely manner, cover more companies, and be more accessible. Most works study the effects of ESG ratings on target variables such as stock prices or financial fundamentals of companies, but few works study how different types of company information can be utilized to predict ESG ratings. Previous works also largely focus on using only the financial information of individual companies to predict ESG ratings, leaving out the different types of inter-company relationship networks. Such inter-company relationship networks are typically dynamic, i.e., they evolve across time. In this paper, we focus on utilizing dynamic inter-company relationships for ESG ratings prediction, and examine the relative importance of different financial and dynamic network information in this prediction task. Our analysis shows that utilizing dynamic inter-company network information, based on common director, common investor and news event-based knowledge graph relationships, can significantly improve ESG rating prediction performance. Robustness checks over different time-periods and different number of time-steps in the future further validate these insights. Collapse

Topics: shapley additive explanation knowledge graph database system missing data network effect

Methods: machine learning econometric modeling longitudinal research Granger causality robustness check

The Influence of Professional Embeddedness and Public Reputation on Critic Review Behavior

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Deng, Tianjie; Dong, Tianxi; Lee, Young Jin

Abstract: ... Expand

Abstract: Collapse

Topics: social network online review

Methods: robustness check moderation analysis regression analysis method

Formation and Action of a Learning Community with Collaborative Learning Software

2023 | Journal of Management Information Systems | Citations: 0

Authors: Eryilmaz, Evren; Thoms, Brian; Ahmed, Zafor; Lee, Howard

Abstract: This paper explores the formation of a learning community facilitated by custom ... Expand

Abstract: This paper explores the formation of a learning community facilitated by custom collaborative learning software. Drawing on research in group cognition, knowledge building discourse, and learning analytics, we conducted a mixed-methods field study involving an asynchronous online discussion consisting of 259 messages posted by 50 participants. The cluster analysis results provide evidence that the recommender system within the software can support the formation of a learning community with a small peripheral cluster. Regarding knowledge building discourse, we identified the distinct roles of central, intermediate (i.e., middle of three clusters), and peripheral clusters within a learning community. Furthermore, we found that message lexical complexity does not correlate to the stages of knowledge building. Overall, this study contributes to the group cognition theory to deepen our understanding about collaboration to construct new knowledge in online discussions. Moreover, we add a much-needed text mining perspective to the qualitative interaction analysis model. Collapse

Topics: recommender system collaborative filtering pandemic online learning system open source

Methods: qualitative content analysis descriptive statistic sociometry synthesis mixed method

Theories: cognitive theory

Do Early Words from New Ventures Predict Fundraising? A Comparative View of Social Media Narratives

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Havakhor, Taha; Golmohammadi, Alireza; Sabherwal, Rajiv; Gauri, Dinesh

Abstract: Online equity markets have significantly changed the dynamics of connecting ang ... Expand

Abstract: Online equity markets have significantly changed the dynamics of connecting angels and individual equity investors to new ventures that seek early-stage capital. However, for those early-stage investors, information pointing to the success of business-to-business (B2B) new ventures (B2BNVs) is scattered and disconnected. This paper focuses on social media narratives (SMNs) as a source of insight for such investors and proposes that predicting a B2BNV's likelihood of success requires a comparative view, i.e., a comparison of its SMNs with those of its competitors and customers. We expect that higher (lower) lingual similarity between the SMNs of an early-stage B2BNV and those of its prospective customers (competitors) predict its success. Using a longitudinal panel of 574 B2BNVs resulting in more than 2,700 venture-round observations, we find that a comparative view of a venture's SMNs can give early-stage investors reliable predictions about the B2BNV's ability to manage its market presence and its success in later stages. Our models show that a comparative view of SMNs increases the accuracy of predicting a B2BNV's later-stage fundraising success by an average of 15%. Furthermore, predictive models can reliably point to a successful market presence in later stages, including the landing of customers, the winning of awards and competitions, the receiving of endorsements, the generating of revenue, and the successful patenting of products. Our study contributes to existing literature that focuses on the business impacts of social media by demonstrating the usefulness of comparative linguistics in social media analytics, i.e., comparing the firm's social media communications to those of its competitors and business customers in the prediction of the entrepreneurial firm's success. Collapse

Topics: Twitter social media social media analytics social capital website

Methods: machine learning chi squared test latent dirichlet allocation robustness check theoretical contribution

Theories: lemon market theory

From Seeker to Provider: User Ability and Role Switching in Online Support Communities

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Lee, Michael; Liao, Ruochen; Wang, Xunyi; Kishore, Rajiv

Abstract: Online health communities offer a platform for patients to seek support from ot ... Expand

Abstract: Online health communities offer a platform for patients to seek support from other users with similar conditions. As those support seekers' situation improves, they may ultimately want to give back to the community and provide support to others. This study explores how seekers' ability to provide support, operationalized using their cognitive state and social network structure, can influence the seekers' propensity to switch roles and become support providers. We leverage the Dual Perspective Model of Agency and Communion and Social Networks literature to theorize a seeker's ability to provide support. We apply survival analysis to study seekers' first role switch to a provider and the duration from seekers' initial post to role switch. We find that while seekers who have higher positive agency and closeness centrality are more likely to switch roles to a provider, those having higher positive communality, degree centrality, and eigenvector centrality are less likely to switch. Collapse

Topics: social network Python

Methods: survival analysis proportional hazards model theory development robustness check word2vec

A Linguistic Cloud-Based Consensus Framework with Three Behavior Classifications Under Trust-Interest Relations

2023 | Group Decision and Negotiation | Citations: 0

Authors: Liu, Weiqiao; Zhu, Jianjun; Liu, Peide; Wang, Peng; Song, Wen

Abstract: In the consensus reaching process (CRP), experts are not infinitely compromising ... Expand

Abstract: In the consensus reaching process (CRP), experts are not infinitely compromising when adjusting opinions, and the “compromise limit” is used to reflect the limited compromise behaviors in the process of expert opinion adjustment. In complex and multiple social relations, experts tend to exhibit different behaviors according to their compromise limits. This paper aims to develop a novel CRP framework to promote a consensus that categorizes and manages experts based on their compromise limits. Firstly, the trust-interest network is defined to represent the multiple relations among experts, and the expert weights are calculated by considering the impact of interest manipulation on trust relations. Secondly, a novel cloud model-based minimum cost consensus model is established, which considers the mutual acceptance between the experts and the group, as well as the changes in the ranges of experts’ hesitation and the collective acceptance. Thirdly, three behavior classifications are defined based on individual compromise limits and group acceptance ranges: cooperative behavior, hesitating non-cooperative behavior, and strong non-cooperative behavior, and a CRP optimization model is constructed to manage the three behaviors. Finally, a numerical example is given to illustrate the validity and superiority of the proposed model. Collapse

Topics: cloud computing social network decision making

Methods: optimization model cross sectional research group interview computational algorithm social network analysis

Theories: optimization theory

Differential Impacts of Technology-Network Structures on Cost Efficiency: Knowledge Spillovers in Healthcare

2023 | Journal of Management Information Systems | Citations: 0

Authors: Nwafor, Onyi; Ma, Xiao; Johnson, Norman A.; Singh, Rahul; Aron, Ravi

Abstract: We examine how hospital cost efficiency can improve because of knowledge spillov ... Expand

Abstract: We examine how hospital cost efficiency can improve because of knowledge spillover effects, arising from the experiences of members of a healthcare system. We identify two types of functional technology networks—that we term repository-type and workflow-type networks—which are defined by the adoption patterns of different types of electronic health record (EHR) systems application functions by hospitals in a health system. Additionally, we examine how structural features of these two network types—namely, network centrality and interconnectedness—impact such knowledge spillover effects. By analyzing seven years of panel data for 1,420 U.S. hospitals across 216 health systems, and data obtained from surveys of healthcare experts, we found that greater centrality of nodes in repository-type networks enhances the influence of partners' experiences on cost efficiency but has the opposite effect in workflow-type networks, while greater interconnectedness of workflow-type networks enhances the influence of partners' experiences on cost efficiency. Interestingly, we found the opposite effect in repository-type networks, where greater interconnectedness diminishes the influence of partners' experiences on cost efficiency. We discuss reasons for this surprising and counterintuitive finding. Overall, our results demonstrate that at least in healthcare settings where information technologies enable knowledge-sharing networks to be formed, benefits can accrue through knowledge spillover effects; moreover, variations across functional categories of technologies adopted in a network context can result in different technology-network structures with differential impacts on hospital cost efficiency because of their influence on knowledge spillover at both the hospital and system levels. Not only can these results explain mixed findings in the literature that has been dominated by a focus on cost efficiency outcomes dependent solely on the EHR adoption choices of individual hospitals, but they also provide the basis for guidelines for a network-based perspective of technology adoption. We discuss other possible settings to which our empirical findings can be reasonably generalized, including supply chain technologies and the Internet of Things. Collapse

Topics: health information system knowledge sharing knowledge spillover technology adoption IT manager

Methods: longitudinal research robustness check descriptive statistic parametric test ANOVA

Theories: social network theory

A Responsible AI Framework for Mitigating the Ramifications of the Organ Donation Crisis

2023 | Information Systems Frontiers | Citations: 0

Authors: Tutun, Salih; Harfouche, Antoine; Albizri, Abdullah; Johnson, Marina E.; He, Haiyue

Abstract: Thousands of people die while waiting for organ transplants due to a significant ... Expand

Abstract: Thousands of people die while waiting for organ transplants due to a significant gap between demand and supply. This gap often leads to illegal activities and ethical issues such as illicit organ trade and auctions. Therefore, to increase the organ supply and procure more organs, organizations must understand the causes of families who refuse to consent to donate their loved one's organs. Furthermore, such organizations must better identify those families most likely to consent to organ donation. We propose a responsible AI framework that integrates network science and artificial intelligence to identify consent outcomes for organ donation. The proposed framework includes three phases: (1) collecting and pre-processing data, (2) creating new features and identifying root causes of family refusal, and (3) training and testing models to predict the probability of families granting consent for organ donation. The designed artifact included collaborative decisions and network measures, increasing explainability through network science. It integrated human reviews and assessment of risks which increases correct and interpretable predictions. Results can help encourage organ donations and reduce the illegal organ trade. The experimental results show that the designed artifact outperformed previous studies identifying factors affecting consent outcomes. This framework integrates network science and artificial intelligence to reduce maleficence, solve the lack of transparency (i.e., increase trustworthiness) and improve accountability of the model that aims to predict consent outcomes. Collapse

Topics: responsible artificial intelligence artificial intelligence explainable artificial intelligence procurement management authorization

Methods: machine learning computational algorithm support vector machine experiment classification method

Theories: justice theory

An AI-based Decision Support System for Predicting Mental Health Disorders

2023 | Information Systems Frontiers | Citations: 0

Authors: Tutun, Salih; Johnson, Marina E.; Ahmed, Abdulaziz; Albizri, Abdullah; Irgil, Sedat; Yesilkaya, Ilker; Ucar, Esma Nur; Sengun, Tanalp; Harfouche, Antoine

Abstract: Approximately one billion individuals suffer from mental health disorders, such ... Expand

Abstract: Approximately one billion individuals suffer from mental health disorders, such as depression, bipolar disorder, schizophrenia, and anxiety. Mental health professionals use various assessment tools to detect and diagnose these disorders. However, these tools are complex, contain an excessive number of questions, and require a significant amount of time to administer, leading to low participation and completion rates. Additionally, the results obtained from these tools must be analyzed and interpreted manually by mental health professionals, which may yield inaccurate diagnoses. To this extent, this research utilizes advanced analytics and artificial intelligence to develop a decision support system (DSS) that can efficiently detect and diagnose various mental disorders. As part of the DSS development process, the Network Pattern Recognition (NEPAR) algorithm is first utilized to build the assessment tool and identify the questions that participants need to answer. Then, various machine learning models are trained using participants’ answers to these questions and other historical data as inputs to predict the existence and the type of their mental disorder. The results show that the proposed DSS can automatically diagnose mental disorders using only 28 questions without any human input, to an accuracy level of 89%. Furthermore, the proposed mental disorder diagnostic tool has significantly fewer questions than its counterparts; hence, it provides higher participation and completion rates. Therefore, mental health professionals can use this proposed DSS and its accompanying assessment tool for improved clinical decision-making and diagnostic accuracy. Collapse

Topics: artificial intelligence decision support system explainable artificial intelligence information portal decision making

Methods: computational algorithm support vector machine design process lasso regression ridge regression

The influence of project initiators’ person-to-person followership on project popularity in open source communities: The role of reach and importance

2023 | Journal of Strategic Information Systems | Citations: 0

Authors: Weng, Qin; Soh, Franck

Abstract: Person-to-person (P2P) followership is an important aspect of major open source ... Expand

Abstract: Person-to-person (P2P) followership is an important aspect of major open source software (OSS) development platforms. In this age of social media platforms, P2P followership has significantly shaped the way users engage in OSS development by facilitating the establishment of connections among OSS users. Despite the prevalence of P2P followership, less is known about the impact of OSS project initiators’ P2P followership nodes on their project popularity. This is a particularly important gap considering the low rate of OSS project success. We posit that OSS project initiators derive information and influence benefits from the quantity and connectivity of their P2P followership nodes, explaining the popularity of the projects initiated. We determine the con­ nectivity of OSS project initiators’ P2P followership nodes based on the nodes’ reach and importance. To test the hypotheses, we use a large panel dataset collected over 24 months from GitHub. The findings indicate that the quantity of OSS project initiators’ P2P followership nodes including followers and followees has a positive effect on their project popularity. Moreover, such an effect is mostly dependent on the connectivity of the OSS project initiators’ P2P followership nodes in such a way that highly connected P2P followership nodes do not impact influence benefits but they increase information benefits. We discuss the theoretical and practical impli­ cations of our findings. Collapse

Topics: peer-to-peer model social network application programming interface social media Instagram

Methods: longitudinal research autocorrelation analysis theory development Granger causality descriptive statistic

Theories: social network theory