Appreciating the Performance of Neuroscience Mining in NeuroIS Research: A Case Study on Consumer's Product Perceptions in the Two UI Modes-Dark UI vs. Light UI

2023 | HICSS | Citations: 0

Authors: Costello, F.; Kim, M.; Lee, K.

Abstract: The goal of the current study was to explore the potential of neuroscience mini ... Expand

Abstract: The goal of the current study was to explore the potential of neuroscience mining (NSM) for comprehending NeuroIS paradigms. NSM is an interdisciplinary field that combines neuroscience and business mining, which is the application of big data analytics, computational social science, and other areas to business problems. NSM makes it possible to apply predictive models to NeuroIS datasets, such as machine learning and deep learning, to find intricate patterns hidden by conventional regression-based analysis. First, we predicted 28 individual EEG power spectra separated brainwave data using a Random Forest (RF) model. Next, we used NSM to precisely predict how consumers would perceive a product online, depending on whether a light or dark user interface (UI) mode was used. The model was then used to extract more precise results that could not be obtained using more conventional linear-based analytical models using sensitivity analysis. The benefits of using NSM in NeuroIS research are as follows: (1) it can relieve the burden of the threehorned dilemma described by Runkel and McGrath; (2) it can enable more temporal data to be directly analyzed on the target variables; and (3) sensitivity analysis can be performed on a condition/individual basis, strengthening the rigor of findings by reducing sample bias that can be lost in grand averaging of data when analyzed with methods like GLM. Collapse

Topics: user interface big data usability tablet artificial intelligence

Methods: electroencephalography NeuroIS computational algorithm sensitivity analysis machine learning

Interactive Visual Analytics for Knowledge Integration and Decision Intelligence (CC BY-NC-ND 4.0)

2023 | HICSS | Citations: 0

Authors: Fisher, B.; Gaither, K.; Ebert, D.

Abstract: Interactive Visual Analytics for Knowledge Integration and Decision Intelligenc ... Expand

Abstract: Interactive Visual Analytics for Knowledge Integration and Decision Intelligence seeks to find ways to develop visualization environments and methods for their use that will support human analysis and decision making with interaction with data and statistical and machine learning processes. Visual analytics provides a way to address problems and opportunities that are characterized by complex data that may be uncertain in fact, relevance, location in space and position in time. Knowledge integration comes into play when multiple datasets from different sources must be evaluated and integrated into the decision-making process. Decision intelligence focuses on the decision-making process itself, examining how individuals and groups chose among alternatives in making plans for action. As defined by Gartner, DI "brings together the best of applied data science, social science, and managerial science into a unified field that helps people use data to improve their lives, their businesses, and the world around them."Applications of this approach include many areas where decision-making must consider complex situations, conflicting data, and priorities. Examples include environmental science and technologies, natural resources and energy, health, and related life sciences. safety and security and many business processes. This year we are examining new approaches to integrating data from neural activity into human factors and discussing ways in which organizations from different sectors can partner to provide value for both industry and academia. Key research challenges of interest in this area include studies of visual analytics and decision support for industrial organizations including the integration of domain knowledge and better understanding of opportunities to improve safety and efficiency in aircraft design.The rapid pace and demand of an increasingly more digital world necessarily mandates that analytics play a key role as we increasingly need to make rapid sense of complex and fast changes driven by big, realtime data. We have moved into an era in which being able to "see" the information in the data is no longer optional and sophisticated visualization methods facilitating rapid understanding is a necessary and critical piece of the "competitive edge". The focus in this minitrack goes beyond analytics to include rich, powerful visualization techniques for turning data into actionable information and ways to better support the decision-making process.This minitrack builds upon earlier HICSS minitracks on visual analytics, mobile computing, and digital media at scale, focusing more decision analytics on various applications from business to science, and public safety. Our first paper seeks to find ways to use machine learning analysis of EEG data to better assess the cognitive load of a task on analysts and decisionmakers. They compare this measure to the humanfactors standard for cognitive load estimation, the NASA-TLX. The second paper gives a retrospective account of an exemplary research collaboration between two universities in Canada and Boeing, a large and technologically sophisticated industry partner, on a focused research effort to integrate visual analytics into Boeing's manufacturing and safety analysis processes. Multiple departments and fields of study relating to analysis, visualization, and decision-making participated in this process, and funding from multiple government agencies supported this effort. Our third paper aims to contribute novel transparency enhancing grounded theory model illustrations annotated with discussion and suggestions that others can adapt for their purposes.These papers show a wide range of applications of visualization and analytics in complex decision-making environments and provide valuable insights into the design, production, and deployment of visual analytics applicable to most decision and discovery tasks across a broad spectrum of applications. Moreover, they clearly demonstrate effective ways to harness and tame big data for discovery, insight, management, and action in realworld, actionable environments. We hope you will join us for interesting presentations and lively discussions on new visual analytics techniques and solutions for our evolving landscape of societal problems requiring rapid and reliable decision making. Collapse

Topics: visual analytics decision making

Methods: exploratory data analysis grounded theory electroencephalography machine learning

IMPACT OF EXPLAINABLE AI ON COGNITIVE LOAD: INSIGHTS FROM AN EMPIRICAL STUDY

2023 | European Conference On Information Systems | Citations: 0

Authors: Herm, Lukas-Valentin

Abstract: While the emerging research field of explainable artificial intelligence (XAI) ... Expand

Abstract: While the emerging research field of explainable artificial intelligence (XAI) claims to address the lack of explainability in high-performance machine learning models, in practice, XAI targets developers rather than actual end-users. Unsurprisingly, end-users are often unwilling to use XAI-based decision support systems. Similarly, there is limited interdisciplinary research on end-users' behavior during XAI explanations usage, rendering it unknown how explanations may impact cognitive load and further affect end-user performance. Therefore, we conducted an empirical study with 271 prospective physicians, measuring their cognitive load, task performance, and task time for distinct implementationindependent XAI explanation types using a COVID-19 use case. We found that these explanation types strongly influence end-users' cognitive load, task performance, and task time. Further, we contextualized a mental efficiency metric, ranking local XAI explanation types best, to provide recommendations for future applications and implications for sociotechnical XAI research. Collapse

Topics: explainable artificial intelligence task productivity artificial intelligence decision support system shapley additive explanation

Methods: descriptive statistic statistical hypothesis test literature study machine learning survey

Theories: theory of abduction

Cognitive load during planned and unplanned virtual shopping: Evidence from a neurophysiological perspective

2023 | International Journal of Information Management | Citations: 0

Authors: Kakaria, Shobhit; Saffari, Farzad; Z. Ramsøy, Thomas; Bigné, Enrique

Abstract: Rapid adoption of virtual-reality-assisted retail applications is inadvertently ... Expand

Abstract: Rapid adoption of virtual-reality-assisted retail applications is inadvertently reshaping consumer buying pat­ terns, making it crucial for businesses to enhance their shopping experience. This new scenario challenges marketers with unique hurdles in both the commercialization of products and in managing information cues derived via VR retailing. Therefore, this study examined consumers’ impulsive behavior and unplanned pur­ chases in a virtual retail store, using self-reports and electroencephalography. Borrowing assorted perspectives from retailing, virtual reality, and neuromarketing literature, we extended the stimulus-organism-response framework to evaluate how unplanned behavior evolves through conscious and unconscious measures. We found that consumers’ impulsiveness was significantly associated with their unplanned expenditure and the number of unplanned purchases. Using mediation analysis, we observed that flow experience during shopping partially mediated the relationship between the sense of presence and the desire to stay longer in a virtual shopping store. Desire to stay in the virtual store positively influenced store satisfaction, basket-size deviation, and budget deviation. Additionally, cognitive workload obtained via electroencephalogram revealed significant differences during both planned and unplanned purchases. These findings provide fresh opportunities for re­ tailers to leverage the disruptive potential of immersive and interactive virtual technology to transform consumer shopping experiences. Collapse

Topics: virtual reality decision making psychological ownership social media marketing management

Methods: electroencephalography self reported survey longitudinal research neurophysiology experiment

Embracing brain and behaviour: Designing programs of complementary neurophysiological and behavioural studies

2023 | Information Systems Journal | Citations: 3

Authors: Kirwan, C. Brock; Vance, Anthony; Jenkins, Jeffrey L.; Anderson, Bonnie Brinton

Abstract: NeuroIS—the methods and knowledge of neuroscience applied to the information sys ... Expand

Abstract: NeuroIS—the methods and knowledge of neuroscience applied to the information systems (IS) domain—has become an established research field within the IS discipline. A key advantage of NeuroIS is its ability to provide insights into human cognition beyond those obtained using behavioural techniques alone. Nevertheless, in neuroscience, there is renewed interest in examining behaviour together with neurophysiological methods to better inform our understanding of neural processes. In this research opinion article, we argue that in the field of NeuroIS, there is an opportunity for hybrid programs of study that combine neurophysiological and behavioural methods in a complementary manner. We outline four strategies for designing complementary neurophysiological and behavioural experiments in a research program: (1) observe the relationship between neural processes and behavioural change; (2) combine neurophysiological and behavioural methods to enhance internal, external, and ecological validity; (3) extend, rather than replicate, experiments based on theory; and (4) use neurophysiological and behavioural experiments together to evaluate IT artefact design. By applying these strategies, researchers can more effectively design programs using complementary neurophysiological and behavioural methods, which, in turn, can help to provide richer insights into the phenomena under study as well as accelerate the advancement of IS knowledge. Collapse

Topics: marketing management Google+ IT security threat personal computer enterprise resource planning

Methods: experiment NeuroIS neurophysiology oculometry functional magnetic resonance imaging

Ambivalence is Better than Indifference: Behavioral and Neurophysiological Assessment of Ambivalence in Online Environments

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Lakhiwal, Akshat; Bala, Hillol; Léger, Pierre-Majorique

Abstract: Information representations such as ratings and reviews play an important role ... Expand

Abstract: Information representations such as ratings and reviews play an important role in assisting users in making decisions in online environments. Prior information systems (IS) research has mostly focused on the role of extreme valence, i.e., the positivity/negativity of information, portrayed by such representations. Yet this bipolar approach discounts how the coexistence of positivity and negativity (i.e., ambivalence) or their absence (i.e., indifference) is formed and leads to distinct attentional processes and outcomes such as purchase decisions. We theorize how and why the valence of information projected through such representations may elicit mixed feelings and influence decision-making in online environments. We conducted four randomized controlled experiments, including an electroencephalography (EEG) study, to disentangle the influence of ambivalence and indifference on decision-making in an online shopping context. We found that ambivalence and indifference to online information distinctly influenced attention and purchase decisions relative to positivity and negativity. Our findings further suggest the inability of incumbent bipolar representations, such as the widely implemented star rating system, to capture the mixed feelings expressed in online content. We propose a bivariate intervention that overcomes the limitations of bipolar representations by not only discerning ambivalence from indifference but also amplifying purchase decisions for products with ambivalent information by at least 50%, compared to incumbent bipolar representations. Our findings advance ongoing research on the role of information valence in online environments and offer implications for practice. Collapse

Topics: decision making enterprise resource planning digital platform user experience user attitude

Methods: experiment theory development electroencephalography NeuroIS statistical power analysis

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

What Disrupts Flow in Office Work? The Impact of Frequency and Relevance of IT-Mediated Interruptions

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Nadj, Mario; Rissler, Raphael; Adam, Marc; Knierim, Michael; Li, Maximilian; Maedche, Alexander; Riedl, René

Abstract: Flow, the holistic sensation people experience when they act with total involve ... Expand

Abstract: Flow, the holistic sensation people experience when they act with total involvement, is a known driver for desired work outcomes like task performance. However, the increasing ubiquity of IT at work can disrupt employees' flow. Thus, the impact of IT-mediated interruptions on flow warrants more attention in research and practice. We conducted a NeuroIS laboratory experiment focusing on a typical office work task-an invoice matching task (i.e., matching customer payments to invoices). We manipulated interruption frequency (low, high) and content relevance (irrelevant, relevant) to study the impact of interruptions on self-reported flow, its dimensions, and high-frequency heart rate variability (HF-HRV; calculated from electrocardiography recordings) as a proxy for parasympathetic nervous system (PNS) activation. We found that content relevance moderated the relationship between interruption frequency and self-reported flow and that these results vary along flow dimensions. Content relevance also moderated the relationship between interruption frequency and PNS activation. Furthermore, selfreported flow was positively associated with both perceived and objective task performance, while PNS Collapse

Topics: task productivity cognitive absorption Python technostress information system use

Methods: electrocardiography NeuroIS multivariate analysis of variance experiment descriptive statistic

Theories: flow theory

Subject-Independent Detection of Yes/No Decisions Using EEG Recordings During Motor Imagery Tasks: A Novel Machine-Learning Approach with Fine-Graded EEG Spectrum

2023 | HICSS | Citations: 0

Authors: Penava, Pascal; Brozat, Marie-Louise; Zimmermann, Yara; Breitenbach, Johannes; Ulrich, Patrick; Buettner, Ricardo

Abstract: The classification of sensorimotor rhythms in electroencephalography signals can ... Expand

Abstract: The classification of sensorimotor rhythms in electroencephalography signals can enable paralyzed individuals, for example, to make yes/no decisions. In practice, these approaches are hard to implement due to the variability of electroencephalography signals between and within subjects. Therefore, we report a novel and fast machine learning model, meeting the need for efficiency and reliability as well as low calibration and training time. Our model extracts finely graded frequency bands from motor imagery electroencephalography data by using power spectral density and training a random forest algorithm for classification. The goal was to create a non-invasive generalizable method by training the algorithm with subject-independent EEG data. We evaluate our approach using one of the currently largest publicly available electroencephalography datasets. With a balanced accuracy of 73.94%, our novel algorithm outperforms other state-of-the-art non-subject-dependent algorithms. Collapse

Topics: societal challenge Python

Methods: electroencephalography computational algorithm longitudinal research spectral analysis machine learning

GETTING INTO FLOW!? ENHANCE FLOW-LIKE EXPERIENCES AND LEARNING PERFORMANCE THROUGH PERSONALIZED LEARNING ACTIVITIES

2023 | European Conference On Information Systems | Citations: 0

Authors: Ritz, Eva

Abstract: Although intelligent learning systems provide new opportunities for personalizi ... Expand

Abstract: Although intelligent learning systems provide new opportunities for personalizing learning activities, important design questions remain. To unleash the full impact of such systems, it is vital to examine how the use of Bayesian knowledge tracing can provide learners personalized learning activities and shape their flow experience, performance, and continuity intention. Further, this study explores the moderating role of a growth mindset on the relation between learning task adaptation and flow experience. I rely on electroencephalography to increase the internal validity of flow measurements. The study builds on Flow Theory and aims to empirically unveil the influence of an intelligent personalization of learning processes. The next step will be an experiment with 80 participants following the developed experimental design to evaluate flow experiences in intelligent learning systems. The results of this experiment aim to guide educational designers with prescriptive knowledge on how to design flow-like learning experiences in intelligent learning systems. Collapse

Topics: usability personalization online learning system data quality knowledge representation

Methods: experiment survey electroencephalography experimental design ontological modelling

Theories: flow theory