How do consumers perceive and process online overall vs. individual text-based reviews? Behavioral and eye-tracking evidence

2023 | Information & Management | Citations: 0

Authors: Jin, Jia; Wang, Ailian; Wang, Cuicui; Ma, Qingguo

Abstract: Building on the Heuristic-Systematic model, we use a survey and two eye-tracking ... Expand

Abstract: Building on the Heuristic-Systematic model, we use a survey and two eye-tracking experiments to investigate consumers’ perceived usefulness of overall and individual text-based reviews (OTRs vs. ITRs) for search vs. experience products, and the information processing features. Results indicate that OTRs show higher usefulness than ITRs, regardless of product type. ITRs are perceived to be more useful for experience products than for search products. Furthermore, two eye-tracking studies confirm these results from a physiological standpoint and reveal the attentional allocation during information processing. OTRs affect subjects’ processing of ITRs infor­ mation differently in purchase search and experience products. Collapse

Topics: perceived usefulness online review electronic commerce user-generated content web page

Methods: oculometry experiment survey parametric test ANOVA

Theories: information processing theory

Fake review detection system for online E-commerce platforms: A supervised general mixed probability approach

2023 | Decision Support Systems | Citations: 0

Authors: Luo, Jiwei; Luo, Jian; Nan, Guofang; Li, Dahui

Abstract: Online consumer reviews play an important role in helping consumers judge the qu ... Expand

Abstract: Online consumer reviews play an important role in helping consumers judge the quality and authenticity of products on e-commerce platforms. However, the constant presence of fake reviews on these platforms has significantly impacted the operation and development of e-commerce platforms. In this study, we develop a novel supervised probabilistic method to detect fake reviews by utilizing the difference in the distribution of nonfraudulent reviews and that of fake reviews. Specifically, we first derive the univariate distributions of several unique features (linguistic, behavioral, and interrelationship features). We then integrate these distributions into two mixed distributions according to their labels to represent the overall difference between non-fraudulent reviews and fake reviews. Next, we randomly generate synthetic review data points with different labels from the above mixed distributions. Finally, we train a Multilayer Perceptron model by using these synthetic review data to obtain a classifier. We conducted several experiments to test the model using several original real-world review datasets. Numerical results indicated that the proposed supervised method outperformed some wellknown sampling models and fake review detection methods, in terms of classification accuracy. Moreover, we extend the proposed method to handle the scenarios with small samples of raw review data. This study con­ tributes to the literature by exploiting the difference in the distribution of non-fraudulent reviews and that of fraudulent reviews, which can improve the accuracy of fake review detection for online platforms. Collapse

Topics: fake review electronic commerce big data decision support system user behavior

Methods: computational algorithm experiment machine learning semi-supervised learning artificial neural network

Generative Artificial Intelligence in Information Systems Education: Challenges, Consequences, and Responses

2023 | Communications of the Association for Information Systems | Citations: 0

Authors: Van Slyke, Craig; Johnson, Richard; Sarabadani, Jalal

Abstract: ChatGPT, an interactive, generative artificial intelligence (AI) system, was in ... Expand

Abstract: ChatGPT, an interactive, generative artificial intelligence (AI) system, was introduced in late 2022, quickly becoming one of the most rapidly adopted technologies in history. The rapid emergence of ChatGPT and similar AI tools, such as Google's Bard, and GPT-enabled Bing from Microsoft have led to intense discussions about how they will affect various aspects of society, including higher education. Information systems (IS) education will not escape the impact of AI tools. Our goal for this paper is to develop a better understanding of the range of possible impacts of ChatGPT on IS education and to describe how IS educators might respond to these potential impacts. To that end, we discuss challenges for IS education brought on by generative AI tools, and discuss potential future scenarios based on the emergence of such tools, ranging from AI having little impact on IS education to AI serving as competition for IS educators. We examine the challenges and consequences of each scenario. We also discuss potential responses, ranging from doing nothing to embracing AI tools as legitimate learning aids. We then provide several specific recommendations that will allow IS educators to effectively respond to the rise of AI tools. Collapse

Topics: artificial intelligence IS education IT career generative AI disruptive innovation

Methods: chatGPT experiment case study

Showcase: A Data-Driven Dashboard for Federal Criminal Sentencing

2023 | Journal of the Association for Information Systems | Citations: 0

Authors: Vo, Ace; Plachkinova, Miloslava

Abstract: The main purpose of the Sentencing Reform Act of 1984 was to provide more unifo ... Expand

Abstract: The main purpose of the Sentencing Reform Act of 1984 was to provide more uniformity in sentencing and reduce interjudge disparity. Subsequently, the act created the federal sentencing guidelines to offer judges a possible sentencing range for offenses. However, since these recommendations were based on historical data, the guidelines amplified existing biases and increased inequality and the disproportionate sentencing of minorities. To address this problem, we developed an artifact called "ShowCase"-a data-driven dashboard-that is grounded in penal theory, organizational context theory, social bonds theory, and triangulation notion in design theory. The artifact helps judges make fairer and more objective decisions by integrating a variety of data points. We used a design science research methodology and mixed methods to guide the development and evaluation of the proposed dashboard. Our research inquiry revealed the legal and extralegal factors that contribute to more equitable judicial decisions. We also found support for integrating data science and more diverse viewpoints in the sentencing process. Our study shows that a validated data-driven dashboard can be used to promote fairness, objectivity, and transparency in the criminal justice system. Collapse

Topics: digital dashboard organizational context decision making criminality societal evaluation criteria

Methods: design artifact survey triangulation literature study design process

Theories: information systems theory

Create the best first glance: The cross-cultural effect of image background on purchase intention

2023 | Decision Support Systems | Citations: 0

Authors: Wang, Ailian; Pan, Jing; Jiang, Caihong; Jin, Jia

Abstract: As globalization drives more firms toward cross-border e-commerce (CBEC), a well ... Expand

Abstract: As globalization drives more firms toward cross-border e-commerce (CBEC), a well-designed decision support system becomes crucial to gain a competitive edge in the international market. Product images, a vital aspect of the system interface, play a significant role in shaping users’ first impressions, facilitating seller-buyer infor­ mation interaction, and ultimately enhancing users’ decisions making in the system. Across a series of studies, this research investigates the effect of cultural differences (thinking style: holistic vs. analytic) on image back­ ground and reveals the underlying mechanism. Results show that online consumers from cultures characterized by holistic thinking style (Chinese sample) are more prone to purchase products presented with contextual backgrounds than those with white backgrounds, while this effect is absent for online consumers from cultures that tend to think in an analytic way (American sample). This effect is also observed when the thinking style is primed within the culture in separate samples from the United States and China. Study 3 employs eye-tracking technology and shows that holistic thinking, compared to analytic thinking, results in an asymmetry in cognitive effort to purchase the same products framed with contextual and white background images. Specifically, contextual (vs. white) background information greatly assists holistic thinking consumers in understanding the product, enabling them to spend less cognitive effort on product information processing. Instead, the cognitive effort that analytic thinking consumers spare in the product information is not affected by the background. Finally, we discuss theoretical contributions and practical insights for CBEC retailers and system designers that the findings indicate. Collapse

Topics: electronic commerce decision support cross cultural research systems design decision making

Methods: oculometry experiment survey parametric test ANOVA

Bridgework: A Model of Brokering Relationships Across Social Boundaries in Organizations

2023 | Organization Science | Citations: 0

Authors: Johnson, Tiffany D.; Joshi, Aparna; Kreiner, Glen E.

Abstract: Relationships are central to organizing, work, and organizations. Yet, in many i ... Expand

Abstract: Relationships are central to organizing, work, and organizations. Yet, in many instances, relationships do not build themselves, and third-party actors are often needed to intervene in situations, persuade individuals, and facilitate connections across disconnected actors in organizations. Little is known about the strategies through which third-party actors can broker relationships across what are considered to be intractable social boundaries—membership in stigmatized or nonstigmatized social identity-based groups. We build a process theory of what we call “bridgework,” the strategy used by third-party agents, intermediaries, and allies to bridge by shifting value-related perceptions about actors on the other side of social identity-based divides. More specifically, we focus on a stigmatizing social identity that can create boundaries that are often reinforced through informal network ties. Based on interviews, participatory observation, and archival data with job coaches for adults with autism spectrum disorders and related developmental disabilities, we showcase a model of bridgework—a combination of internal and external strategies across three stages (adding, stabilizing, and maintaining perceptions of value) to facilitate relationships between stigmatized and nonstigmatized members of organizations. We discuss how our grounded model contributes to the rich traditions of research on stigma, brokerage, disability studies, positive relationships, and compassion in organizations. Funding: This project was supported by a Smeal Small Research Grant in Spring 2015. Collapse

Topics: social identity website innovation management decision making organizational productivity

Methods: qualitative interview theory development grounded theory theoretical contribution participant observation

Activist Protest Spillovers into the Regulatory Domain: Theory and Evidence from the U.S. Nuclear Power Generation Industry

2022 | Organization Science | Citations: 0

Authors: Fremeth, Adam R.; Holburn, Guy L. F.; Piazza, Alessandro

Abstract: We examine how social activism—in the form of public protests against contentiou ... Expand

Abstract: We examine how social activism—in the form of public protests against contentious business practices—can spill over into the regulatory domain, extending beyond activists’ articulated goals to affect firms’ regulatory outcomes in areas that are not directly targeted. We argue that firms are likely to experience broader regulatory repercussions after activist protests because public contention invites greater scrutiny of firm behavior by industry regulators, increasing the likelihood that instances of organizational noncompliance will be discovered. Protests can also cause regulators to evaluate targeted firms more negatively in regulatory assessments, especially firms with less favorable preexisting reputations or stakeholder relations, and to tighten regulations on nontargeted issues that signal their commitment to safeguarding the public interest. We further contend that the political context within which regulatory agencies operate shapes the extent of protest spillovers: When political institutions are aligned with activist goals, and when regulators are ideologically sympathetic too, protests have a more pronounced negative impact on firms’ regulatory outcomes in nontargeted domains. We find robust support for our predictions in a statistical analysis of the impact of antinuclear protests—which sought to block nuclear power plant development by electric utilities—on utilities’ subsequent regulated financial rates of return on their assets. Our analysis contributes new insights to research on the indirect consequences for targeted organizations of social activism. Collapse

Topics: database system organizational productivity website internet technology missing data

Methods: statistical hypothesis test regression analysis method longitudinal research descriptive statistic archival research

Theories: theory of economic growth

Fraudulent review detection model focusing on emotional expressions and explicit aspects: investigating the potential of feature engineering

2022 | Decision Support Systems | Citations: 5

Authors: Kumar, Ajay; Gopal, Ram D.; Shankar, Ravi; Tan, Kim Hua

Abstract: Reading customer reviews before purchasing items online has become a common prac ... Expand

Abstract: Reading customer reviews before purchasing items online has become a common practice; however, some companies use machine learning (ML) algorithms to generate false reviews in order to create positive brand images of their own products and negative images of competitors' offerings. Existing techniques use review content to identify fraudulent reviewers; however, spammers become more intelligent, started to learn from their mistakes, and changed their tactics in order to avoid detection techniques. Thus, investigating fraudulent ac­ counts' behaviour of generating fake negative or positive reviews for competitors or themselves and the necessity of ML classifiers to identify fraudulent reviews, is more important than ever. In this research, we present a novel feature engineering approach in which we (1) extract several “review-centric” and “reviewer-centric” features from a dataset; (2) combine the cumulative effects of features distributions into a unified model that represents overall behavior of the fraudulent reviewers; (3) investigate the role of effective data pre-processing to improve detection accuracy; and (4) develop a probabilistic approach to detect fraudulent reviewers by learning a novel M-SMOTE model over a derived balanced dataset and feature distributions, which outperforms other ML models. Our study contributes to the literature on digital platforms and fraudulent review detection with significant managerial and theoretical implications through these novel findings. Collapse

Topics: online review electronic commerce website marketing management logistics management

Methods: feature engineering machine learning computational algorithm XGBoost product review

Improving Imbalanced Machine Learning with Neighborhood-Informed Synthetic Sample Placement

2022 | Journal of Management Information Systems | Citations: 0

Authors: Nasir, Murtaza; Dag, Ali; Simsek, Serhat; Ivanov, Anton; Oztekin, Asil

Abstract: Machine learning is widely used in information systems design. Yet, training alg ... Expand

Abstract: Machine learning is widely used in information systems design. Yet, training algorithms on imbalanced datasets may severely affect performance on unseen data. For example, in some cases in healthcare, fintech, or cybersecurity contexts, certain subclasses are difficult to learn because they are underrepresented in training data. Our study offers a flexible and efficient solution based on a new synthetic average neighborhood sampling algorithm (SANSA), which, in contrast to other solutions, introduces a novel "placement" parameter that can be tuned to adapt to each dataset's unique manifestation of the imbalance. This package can be downloaded for R1. We tested SANSA against seven existing sampling methods used in conjunction with the four most frequently used machine learning models trained on 14 benchmark datasets. Our results provide suggestive evidence that SANSA offers a feasible solution to the imbalance problem for most datasets. Our findings provide practical recommendations for how SANSA can be effectively implemented while reducing the complexity level of an imbalanced learning pipeline. Collapse

Topics: marketing management customer service online review logistics management credit card fraud

Methods: computational algorithm machine learning support vector machine artificial neural network descriptive statistic

The Aggregation–Learning Trade-off

2022 | Organization Science | Citations: 0

Authors: Piezunka, Henning; Aggarwal, Vikas A.; Posen, Hart E.

Abstract: Organizational decision making that leverages the collective wisdom and knowledg ... Expand

Abstract: Organizational decision making that leverages the collective wisdom and knowledge of multiple individuals is ubiquitous in management practice, occurring in settings such as top management teams, corporate boards, and the teams and groups that pervade modern organizations. Decision-making structures employed by organizations shape the effectiveness of knowledge aggregation. We argue that decision-making structures play a second crucial role in that they shape the learning of individuals that participate in organizational decision making. In organizational decision making, individuals do not engage in learning by doing but, rather, in what we call learning by participating, which is distinct in that individuals learn by receiving feedback not on their own choices but, rather, on the choice made by the organization. We examine how learning by participating influences the efficacy of aggregation and learning across alternative decision-making structures and group sizes. Our central insight is that learning by participating leads to an aggregation–learning trade-off in which structures that are effective in aggregating information can be ineffective in fostering individual learning. We discuss implications for research on organizations in the areas of learning, microfoundations, teams, and crowds. Collapse

Topics: decision making organizational productivity organizational context organization structure strategic management

Methods: simulation descriptive statistic theory development