Self-Building Artificial Intelligence and Machine Learning to Empower Big Data Analytics in Smart Cities

2023 | Information Systems Frontiers | Citations: 0

Authors: Alahakoon, Damminda; Nawaratne, Rashmika; Xu, Yan; De Silva, Daswin; Sivarajah, Uthayasankar; Gupta, Bhumika

Abstract: The emerging information revolution makes it necessary to manage vast amounts of ... Expand

Abstract: The emerging information revolution makes it necessary to manage vast amounts of unstructured data rapidly. As the world is increasingly populated by IoT devices and sensors that can sense their surroundings and communicate with each other, a digital environment has been created with vast volumes of volatile and diverse data. Traditional AI and machine learning techniques designed for deterministic situations are not suitable for such environments. With a large number of parameters required by each device in this digital environment, it is desirable that the AI is able to be adaptive and self-build (i.e. self-structure, self-configure, self-learn), rather than be structurally and parameter-wise pre-defined. This study explores the benefits of self-building AI and machine learning with unsupervised learning for empowering big data analytics for smart city environments. By using the growing self-organizing map, a new suite of self-building AI is proposed. The self-building AI overcomes the limitations of traditional AI and enables data processing in dynamic smart city environments. With cloud computing platforms, the self-building AI can integrate the data analytics applications that currently work in silos. The new paradigm of the self-building AI and its value are demonstrated using the IoT, video surveillance, and action recognition applications. Collapse

Topics: artificial intelligence smart city big data cloud computing distributed system

Methods: computational algorithm experiment unsupervised learning machine learning longitudinal research

Incorporating evolutionary adaptions into the cognitive fit model for data visualization

2023 | Decision Support Systems | Citations: 0

Authors: Bina, Saman; Kaskela, Timothy; Jones, Donald R.; Walden, Eric; Graue, William B.

Abstract: With the proliferation of data has arisen an array of information visualization ... Expand

Abstract: With the proliferation of data has arisen an array of information visualization tools to help humans convert data to information for better decision-making. This ever-expanding visualization toolset has outrun the development of theories of data visualization usage for decision support. In the current research, we contribute to the development of visualization theories in two ways. First, we incorporate our understanding of evolutionary adaptations into the cognitive fit theory to explain why 3-D surface graphs often outperform traditional 2-D graphs in various sensemaking tasks. Drawing on geon theory to interpret the 3-D advantage, we develop the concept of geonic/non-geonic information representations and tasks. We tested and found support for our hy­ potheses that geonic representations have a speed advantage for the tasks we studied, derived from the human evolved capacity for geographic orienteering, but accuracy depends on the match of representation and task, as geonic or non-geonic. Our experiment compared the geonic representation (3-D surface graph) to non-geonic planar representations (cluster bar, heat map, and line) in geonic (integration, proportion) and non-geonic atomic (acquisition, comparison) tasks. For our second contribution, we build on this result to expand the cognitive fit model to incorporate classic human information processes and evolutionary adaptations. We suggest that the cognitive fit model can expand to include new advances in neuroscience. We discuss the theoretical and practical implications of our experiment and our expanded model. Collapse

Topics: data visualization sensemaking decision making spreadsheet Python

Methods: experiment parametric test ANOVA exploratory data analysis descriptive statistic

Theories: cognitive fit theory

Informational and emotional appeals of cover image in crowdfunding platforms and the moderating role of campaign outputs

2023 | Decision Support Systems | Citations: 0

Authors: Chen, Shiqin; Wang, Hongwei; Fang, Yulin; Wang, Wei

Abstract: The first-stage decision is critical in the decision process in crowdfunding, wh ... Expand

Abstract: The first-stage decision is critical in the decision process in crowdfunding, where the cover image plays an important role in forming first impressions and persuading click funders. This study explores how emotional visual cues (human face) and informational visual cues (visual text) in the cover image affect funders’ decisions and how the effects differ across campaigns. The results demonstrate the great persuasive power of human faces and visual text. We further illustrate the effects of joyful expressions and image-text congruency as well as the non-significant influence of the length and polarity of visual text. Moreover, emotional visual cues are more effective in intangible product campaigns, while informational visual cues are more effective in tangible product campaigns, and both are important in social service campaigns. Valuable insight is provided to creators about the design of the cover image. Collapse

Topics: crowdsourcing crowdfunding decision making application programming interface missing data

Methods: robustness check sentiment analysis descriptive statistic deep learning theoretical contribution

Theories: processing fluency theory

Collateral Damage: The Relationship Between High-Salience Events and Variation in Racial Discrimination

2023 | Organization Science | Citations: 0

Authors: Gorbatai, Andreea; Younkin, Peter; Burtch, Gordon

Abstract: To what extent are individual or organizational biases affected by racially sali ... Expand

Abstract: To what extent are individual or organizational biases affected by racially salient events? We propose that acts of discrimination and the individual biases that undergird them are sensitive to high-salience events and will oscillate with the salience of the focal attribute. In short, that the propensity to discriminate reflects both individual and environmental differences, and therefore a given person may become more prone to discriminate in the aftermath of a high-salience event. We test our hypothesis in three online experiments that examine how varying the salience of race affects the evaluation of in-group or out-group founders. We find that respondents evaluate their in-group members more favorably, and out-group members less favorably, when exposed to a high-salience event, which translates into a significant disadvantage for the minority (African American) group. We complement these studies with an assessment of how police shootings affect fundraising outcomes on Kickstarter to confirm the external validity of our findings. Together, these studies indicate that racially salient events depress the quality evaluations and success odds of African American entrepreneurs relative to others. Hence, discrimination levels can be affected by salient yet unrelated events, and such events are consequential for the economic fortunes of individuals belonging to minority and disadvantaged groups.History: This paper has been accepted for the Organization Science Special Issue on Experiments in Organizational Theory.Supplemental Material: The online appendices are available at https://doi.org/10.1287/orsc.2021.1527. Collapse

Topics: crowdfunding crowdsourcing website criminality application programming interface

Methods: experiment parametric test statistical hypothesis test survey facial recognition system

Does additional audio really work? A study on users' cognitive behavior with audio-visual dual-channel in panoramic digital museum

2023 | Information & Management | Citations: 0

Authors: He, Xiaoyang; Wu, Dan

Abstract: Multi-channel human-computer interaction offers a new perspective for optimizati ... Expand

Abstract: Multi-channel human-computer interaction offers a new perspective for optimization research in the digital museum, though there is no empirical evidence on how these factors affect cognition. This paper conducted a controlled experiment using the audio guide as a breakthrough point, aiming to determine the cognitive changes before and after the audio-visual dual-channel interaction. The results demonstrate that adding the auditory channel brought more cognitive load but not better cognitive outcomes. This paper evaluated the reasons behind it and noted that designing channels based solely on technical feasibility is undesirable, with suggestions pro­ posed for museum practitioners and platform developers. Collapse

Topics: mobile system usability human computer interaction virtual reality computer hardware

Methods: oculometry experiment parametric test descriptive statistic survey

The future is yesterday: Use of AI-driven facial recognition to enhance value in the travel and tourism industry

2023 | Information Systems Frontiers | Citations: 0

Authors: Gupta, Shivam; Modgil, Sachin; Lee, Choong-Ki; Sivarajah, Uthayasankar

Abstract: This study aims to investigate the role of artificial intelligence (AI) driven f ... Expand

Abstract: This study aims to investigate the role of artificial intelligence (AI) driven facial recognition to enhance a value proposition by influencing different areas of services in the travel and tourism industry. We adopted semi-structured interviews to derive insights from 26 respondents. Thematic analysis reveals the development of four main themes (personalization, data-driven service offering, security and safety, and seamless payments). Further, we mapped the impact of AI- driven facial recognition to enhance value and experience for corporate guests. Findings indicate that AI-based facial recognition can facilitate the travel and tourism industry in understanding travelers’ needs, optimization of service offers, and value-based services, whereas data-driven services can be realized in the form of customized trip planning, email, and calendar integration, and quick bill summarization. This contributes to strengthening the tourism literature through the lens of organizational information processing theory. Collapse

Topics: artificial intelligence usability personalization human resource management pandemic

Methods: facial recognition system biometric measurement personal interview qualitative interview qualitative content analysis

Theories: organizational information processing theory

Understanding the Role of Expert Intuition in Medical Image Annotation: A Cognitive Task Analysis Approach

2023 | HICSS | Citations: 0

Authors: Leiser, F.; Warsinsky, S.; Daum, M.; Schmidt-Kraepelin, M.; Thiebes, S.; Wagner, M.; Sunyaev, A.

Abstract: To improve contemporary machine learning (ML) models, research is increasingly ... Expand

Abstract: To improve contemporary machine learning (ML) models, research is increasingly looking at tapping in and incorporating the knowledge of domain experts. However, expert knowledge often relies on intuition, which is difficult to formalize for incorporation into ML models. Against this backdrop, we investigate the role of intuition in the context of expert medical image annotation. We apply a cognitive task analysis approach, where we observe and interview six expert medical image annotators to gain insights into pertinent decision cues and the role of intuition during annotation. Our results show that intuition plays an important role in various steps of the medical image annotation process, particularly in the appraisals of very easy or very difficult images, and in case purely cognitive appraisals remain inconclusive. Overall, we contribute to a better understanding of expert intuition in medical image annotation and provide possible interfaces to incorporate said intuition into ML models. Collapse

Topics: decision making knowledge representation

Methods: qualitative interview survey self reported survey triangulation cognitive task analysis

Debunking Sustainability Excuses with Instrumentality and Expectancy Visualizations: A Physiological Perspective

2023 | International Conference on Information Systems | Citations: 0

Authors: Li, Zhiyin; Choi, Ben

Abstract: This study advances the IS literature by investigating the effects of visualiza ... Expand

Abstract: This study advances the IS literature by investigating the effects of visualization on promoting sustainability knowledge and pro-environmental behaviors. Specifically, drawing on the visualization literature, we explain how the key visualization features, expectancy illustration, and interactivity affect individuals' understanding of the impact of their behaviors on the environment, encouraging pro-environmental behaviors. Additionally, we draw on the pedagogy literature to explicate that the effects of visualization on learning outcomes and pro-environmental practices can be explained through individuals' psychological responses in their course of interpreting the visualization. Collectively, this study presents our endeavor in understanding the roles of visualization in ecological discourse by integrating the visualization literature and sustainability research. Moreover, by unboxing individuals' psychological processes in interpreting visualization, we offer a fresh perspective to understanding the promises and challenges of using visualization for knowledge acquisition. Collapse

Topics: task productivity knowledge acquisition data literacy

Methods: oculometry parametric test ANOVA simulation experiment

Theories: expectancy theory of motivation

Online promotion effects under time limitation - A study of survey and physiological signals

2023 | Decision Support Systems | Citations: 0

Authors: Liang, Chih-Chin; Lin, Yu-Wen

Abstract: Online shopping platforms attract consumers to purchase by offering discounts or ... Expand

Abstract: Online shopping platforms attract consumers to purchase by offering discounts or informing them about the availability of limited quantities of cheaper items during a set time period. Offering goods on sale for a brief window creates a sense of time pressure and encourages impulse purchases. However, few studies have discussed the relationship between physiological signals and the promotional impact of limited time offers. In this study, we discuss the promotional impact of different promotion methods under time pressure and perform experiments using brainwaves and galvanic skin responses of 53 participants to reveal the relationships. This study surveys 501 participants to determine the promotional impact of limited time offers on customers using qualified experimented pictures to recall their feeling toward limited time offers. The analytical results indicate that timelimited promotions, monetary discounts, and online reviews significantly affect impulse purchase behavior. The experiential results show that promotion methods can arouse physiological signals and emotional reactions in participants. Finally, the research and managerial implications are discussed. Collapse

Topics: online review marketing management decision making consumer behavior missing data

Methods: experiment survey Student's t-test parametric test electrodermal activity

Detection of interaction-based knowledge for reclassification of service robots: big data analytics perspective

2023 | HICSS | Citations: 0

Authors: Lyu, F.; Wang, M.; Choi, J.

Abstract: With the advancement of artificial intelligence technology, the robot industry ... Expand

Abstract: With the advancement of artificial intelligence technology, the robot industry in human-robot interactive service has rapidly developed. The purpose of this paper is to uncover user acceptance of humanrobot interactive service robots based on online reviews. Extract reviews the public service robots and the domestic service robots from YouTube uses word2vec, sentiment classification, and LDA (Latent Dirichlet Allocation) analysis methods for research. The results show that in the interactive technology, the public service robots, the domestic service robots, and the service robots can well receive the user's speech, gestures, and understanding of emotional states and navigating with and around. However, collaborating with humans, users may be more fearful and worried. At the same time, the positive topic of the public service robots is experience value, and the negative topic is system quality. The positive topic of the domestic service robots is anthropomorphism, and the negative topic is perceived intelligence. Collapse

Topics: robotic YouTube user acceptance online review service quality

Methods: word2vec natural language processing computational algorithm topic model classification method