Rumor Classification through a Multimodal Fusion Framework and Ensemble Learning

2023 | Information Systems Frontiers | Citations: 0

Authors: Azri, Abderrazek; Favre, Cécile; Harbi, Nouria; Darmont, Jérôme; Noûs, Camille

Abstract: The proliferation of rumors on social media has become a major concern due to it ... Expand

Abstract: The proliferation of rumors on social media has become a major concern due to its ability to create a devastating impact. Manually assessing the veracity of social media messages is a very time-consuming task that can be much helped by machine learning. Most message veracity verification methods only exploit textual contents and metadata. Very few take both textual and visual contents, and more particularly images, into account. Moreover, prior works have used many classical machine learning models to detect rumors. However, although recent studies have proven the effectiveness of ensemble machine learning approaches, such models have seldom been applied. Thus, in this paper, we propose a set of advanced image features that are inspired from the field of image quality assessment, and introduce the Multimodal fusiON framework to assess message veracIty in social neTwORks (MONITOR), which exploits all message features by exploring various machine learning models. Moreover, we demonstrate the effectiveness of ensemble learning algorithms for rumor detection by using five metalearning models. Eventually, we conduct extensive experiments on two real-world datasets. Results show that MONITOR outperforms state-of-the-art machine learning baselines and that ensemble models significantly increase MONITOR’s performance. Collapse

Topics: Twitter social network Python microblog logistics management

Methods: computational algorithm machine learning experiment meta learning ensemble learning

What Makes Digital Technology? A Categorization Based on Purpose

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

Authors: Baier, Marie-Sophie; Berger, Stephan; Kreuzer, Thomas; Oberländer, Anna; Röglinger, Maximilian

Abstract: Digital technology (DT) is creating and shaping today's world. Building on its ... Expand

Abstract: Digital technology (DT) is creating and shaping today's world. Building on its identity and history of technology research, the Information Systems discipline is at the forefront of understanding the nature of DT and related phenomena. Understanding the nature of DT requires understanding its purposes. Because of the growing number of DTs, these purposes are diversifying, and further examination is needed. To that end, we followed an organizational systematics paradigm and present a taxonomic theory for DT that enables its classification through its diverse purposes. The taxonomic theory comprises a multi-layer taxonomy of DT and purpose-related archetypes, which we inferred from a sample of 92 real-world DTs. In our empirical evaluation, we assessed the reliability, validity, and usefulness of the taxonomy and archetypes. The taxonomic theory exceeds existing technology classifications by being the first that (1) has been rigorously developed, (2) considers the nature of DT, (3) is sufficiently concrete to reflect the diverse purposes of DT, and (4) is sufficiently abstract to be persistent. Our findings add to the descriptive knowledge on DT, advance our understanding of the diverse purposes of DT, and lay the ground for further theorizing. Our work also supports practitioners in managing and designing DTs. Collapse

Topics: knowledge base perceived usefulness competitive advantage decision making technology adoption

Methods: cluster analysis theory development longitudinal data analysis focus group computational algorithm

Theories: information systems theory sociomaterialism theory

Expl(AI)ned: The Impact of Explainable Artificial Intelligence on Users’ Information Processing

2023 | Information Systems Research | Citations: 0

Authors: Bauer, Kevin; von Zahn, Moritz; Hinz, Oliver

Abstract: Because of a growing number of initiatives and regulations, predictions of moder ... Expand

Abstract: Because of a growing number of initiatives and regulations, predictions of modern artificial intelligence (AI) systems increasingly come with explanations about why they behave the way they do. In this paper, we explore the impact of feature-based explanations on users’ information processing. We designed two complementary empirical studies where participants either made incentivized decisions on their own, with the aid of opaque predictions, or with explained predictions. In Study 1, laypeople engaged in the deliberately abstract investment game task. In Study 2, experts from the real estate industry estimated listing prices for real German apartments. Our results indicate that the provision of feature-based explanations paves the way for AI systems to reshape users’ sense making of information and understanding of the world around them. Specifically, explanations change users’ situational weighting of available information and evoke mental model adjustments. Crucially, mental model adjustments are subject to the confirmation bias so that misconceptions can persist and even accumulate, possibly leading to suboptimal or biased decisions. Additionally, mental model adjustments create spillover effects that alter user behavior in related yet disparate domains. Overall, this paper provides important insights into potential downstream consequences of the broad employment of modern explainable AI methods. In particular, side effects of mental model adjustments present a potential risk of manipulating user behavior, promoting discriminatory inclinations, and increasing noise in decision making. Our findings may inform the refinement of current efforts of companies building AI systems and regulators that aim to mitigate problems associated with the black-box nature of many modern AI systems. History: Alessandro Acquisti, senior editor; Jason Chan, associate editor. Funding: This work was supported by the Deutsche Forschungsgemeinschaft (DFG) (Projek 449023539), Volkswagen Foundation (ML2MT), and LeibnizInstitute for Financial Research SAFE. Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2023.1199. Collapse

Topics: explainable artificial intelligence artificial intelligence shapley additive explanation local interpretable model agnostic explanation decision making

Methods: F-test regression analysis method experiment field study robustness check

Will Algorithms Replace Managers? A Systematic Literature Review on Algorithmic Management

2023 | International Conference on Information Systems | Citations: 0

Authors: Becker, Luc; Wurm, Bastian; Hess, Thomas

Abstract: Algorithms increasingly take on tasks traditionally performed by humans. They n ... Expand

Abstract: Algorithms increasingly take on tasks traditionally performed by humans. They not only serve as co-workers to their human counterparts but increasingly take over management tasks by supervising and coordinating human workers -a phenomenon referred to as Algorithmic Management (AM). There is a growing research interest in this topic, but currently, the field lacks an overview and thorough understanding of what types of managerial work algorithms already perform. We address this with a structured literature review. We find that the automation of management work and workers' responses to it (so-called algoactivism) have received the most attention. However, the configuration of AM systems has so far received little systematic attention. We further analyze which management functions algorithms perform. We find that while algorithms primarily supervise and investigate workers, coordinating interdependent workers and tasks has not been addressed. We propose several avenues for future research. Collapse

Topics: algorithmic management database system organizational context Uber knowledge base

Methods: computational algorithm literature study literature sample structured literature research

Natural Language Processing for Medical Texts – A Taxonomy to Inform Integration Decisions into Clinical Practice

2023 | International Conference on Information Systems | Citations: 0

Authors: Braun, Marvin; Kolbe, Lutz; Neumann, Caspar

Abstract: Electronic health records (EHR) have significantly amplified the volume of info ... Expand

Abstract: Electronic health records (EHR) have significantly amplified the volume of information accessible in the healthcare sector. Nevertheless, this information load also translates into elevated workloads for clinicians engaged in extracting and generating patient information. Natural Language Process (NLP) aims to overcome this problem by automatically extracting and structuring relevant information from medical texts. While other methods related to artificial intelligence have been implemented successfully in healthcare (e.g., computer vision in radiology), NLP still lacks commercial success in this domain. The lack of a structured overview of NLP systems is exacerbating the problem, especially with the emergence of new technologies like generative pre-trained transformers. Against this background, this paper presents a taxonomy to inform integration decisions of NLP systems into healthcare IT landscapes. We contribute to a better understanding of how NLP systems can be integrated into daily clinical contexts. In total, we reviewed 29 papers and 36 commercial NLP products. Collapse

Topics: health information system artificial intelligence database system healthcare data information technology infrastructure

Methods: natural language processing computational algorithm information extraction literature sample NLP application

No Ground Truth at Sea – Developing High-Accuracy AI Decision-Support for Complex Environments

2023 | HICSS | Citations: 0

Authors: Bumann, Adrian

Abstract: As AI decision-support systems are increasingly developed for applications outsi ... Expand

Abstract: As AI decision-support systems are increasingly developed for applications outside of traditional organizational confinements, developers are confronted with new sources of complexity they need to address. However, we know little about how AI applications are developed for natural use domains with high environmental complexity, stemming from physical influences outside of the developers’ control. This study investigates what challenges emerge from such complexity and how developers mitigate them. Drawing upon a rich longitudinal single-case study on the development of AI decision-support for maritime navigation, findings show that achieving high output accuracy is complicated by the physical environment hindering training data creation. Further, developers chose to reduce the output accuracy and adapt the HMI design to successfully situate the AI application in an existing sociotechnical context. This study contributes to IS literature following recent calls for phenomenon-based examination of emerging challenges when extending the scope frontier of AI and provides practical recommendations for developing AI decision-support for complex environments. Collapse

Topics: artificial intelligence decision support decision support system geographic information system innovation management

Methods: qualitative interview single case study personal interview longitudinal research field study

Theories: socio technical theory

THE PROCESS AUGMENTABILITY CANVAS - HOW TO FIND THE SWEET SPOT FOR AUGMENTED REALITY

2023 | European Conference On Information Systems | Citations: 0

Authors: Bräker, Julia; Semmann, Martin

Abstract: The adoption of augmented reality (AR) has been one of the defining technologic ... Expand

Abstract: The adoption of augmented reality (AR) has been one of the defining technological trends of the past decade. While AR has experienced significant growth in consumer electronics, its potential for professional use still needs to be explored. Despite the growing interest in AR, determining its feasibility and potential to satisfy business needs remains challenging. To address this gap, we used a mixedmethod research approach to create a guiding framework called the process augmentability canvas. Drawing on a comprehensive case study of a major European maintenance, repair, and overhaul service provider, as well as state-of-the literature, we present a canvas that allows scholars and practitioners to evaluate AR's applicability for a given process thoroughly. By providing a structured approach to analyzing AR solutions, the process augmentability canvas contributes to a better understanding of how AR can be used efficiently in organizational settings. Collapse

Topics: logistics management usability technology adoption human computer interaction innovation management

Methods: literature study qualitative interview case study design artifact cluster analysis

Theories: unified theory of acceptance and use of technology technology acceptance model theory of task technology fit

Trust and deception with high stakes: Evidence from the friend or foe dataset

2023 | Decision Support Systems | Citations: 0

Authors: Chen, Xunyu; Wang, Xinran; Spitzley, Lee; Nunamaker, Jay

Abstract: Many social interactions rely on the premise of mutual trust, but deception viol ... Expand

Abstract: Many social interactions rely on the premise of mutual trust, but deception violates trust and poses risk. Empirically examining trust and deception, particularly in high-stakes situations, is challenging but essential for improving the research realism and generalizability. To address this difficulty, we study trusting and deceptive behaviors in a high-stakes situation by using a novel dataset created from an American game show, Friend or Foe (FoF). In the show, a contestant's reward was determined through a trust game modified from the prisoner's dilemma. We explore how numerous human behaviors including facial expressions, gaze, head pose, body motion, language, and socio-demographic attributes, were related to a contestant's trusting or deceptive decision. Using a data-driven approach, we find that the deceivers' (contestants who chose Foe) behavior featured a neutralized face, negative facial emotions, enhanced upper body motion, and language with a lower sense of immediacy and agreeableness. The contestants who chose to trust (chose Friend) exhibited opposite behavioral patterns. Socio-demographic factors such as age, height, and facial attractiveness were also associated with a contestant's choice. Combining multimodal information, machine learning classifiers could predict the contes­ tant's choice with an accuracy about 25% greater than earlier reported human accuracy. We contribute to both trust and deception literature by examining the generalizability of trusting and deceptive behaviors to a new high-stakes scenario. We also add to the decision support literature by showing the superior predictive perfor­ mances of combining behavioral and socio-demographic features. Furthermore, we contribute to the academic community by introducing the FoF dataset. Collapse

Topics: decision support website YouTube Python decision making

Methods: meta analysis support vector machine correlation analysis descriptive statistic random forest classification

A temporal graph framework for intelligence extraction in social media networks

2023 | Information & Management | Citations: 0

Authors: Chung, Wingyan; Lai, Vincent S.

Abstract: Social media networks (SMNs) are increasingly used in professional management of ... Expand

Abstract: Social media networks (SMNs) are increasingly used in professional management of knowledge workers and related assets. However, the factors affecting behavioral trends and activity levels in these networks are not well understood. Although social and cognitive theories can help to explain human behavior in traditional social networks, their application to SMNs has not been validated. Traditional social network modeling techniques may not accurately predict real-world SMN activities. This research developed a temporal graph framework for in­ telligence extraction in SMNs. Theory-based, data-driven models (Conformity Model (COM), Recency-Primacy Model (REM), Trend Interaction Model (TIM), Periodic Interaction Model (PIM)) were developed based on the framework to capture various aspects of user behavior: conformity effect, recency, primacy, periodicity, and dynamic trend. The models capture the activity history and dynamically combine pricing information to enhance predictive accuracy. Using data of 83,536 GitHub software repositories on cryptocurrency, this article reports the results of experiments that compare the models’ performance in predicting SMN activities over time. Experi­ mental results show that the model (REM) that captures recency/primacy effects of human cognitive processing outperformed other models in 9 (out of 18) measures pertaining to engagement, contribution, influence, and popularity. Primacy plays a dominant role in predicting engagement, contribution, and popularity, whereas recency plays a key role in predicting influence. Short-term trend (modeled with TIM) was found to yield significantly better performance on predicting user contribution. The models also outperformed an integrated machine learning (IML) model by most measures. Overall, the effects modeled by REM and TIM were found to be more significant than the effects modeled by COM, PIM, and IML. The research contributes to enhancing un­ derstanding of SMN behavior, developing new models to simulate and predict SMN activities, and designing new artifacts for information systems practitioners to manage knowledge assets and to extract SMN intelligence. Collapse

Topics: cryptocurrency social network systems development situation awareness user behavior

Methods: experiment machine learning longitudinal research computational algorithm time series analysis

Theories: psychological theory social contagion theory social interactionist theory social impact theory social sciences theory

Tertiary Study on the Use of Artificial Intelligence for Service Delivery: A Bibliometric Analysis of Systematic Literature Reviews

2023 | HICSS | Citations: 0

Authors: Chouikh, A.; Khechine, H.; Gagnon, M.

Abstract: Despite the large number of systematic literature reviews (SLRs) on the use of ... Expand

Abstract: Despite the large number of systematic literature reviews (SLRs) on the use of artificial intelligence (AI) for service delivery, scholars suggest more scientific evidence. However, the direction that these reviews will take depends on the knowledge accumulated in the existing literature. Therefore, the objective of this research is to explore SLRs that have synthesized the use of AI for service delivery. We conducted a tertiary study, which consists of a bibliometric analysis of SLRs. We searched SLRs published over the last ten years in six bibliographic databases. Sixty-six studies meeting the inclusion criteria were processed through a bibliometric analysis in which we combined article metadata with data extracted from the full-text review. The results describe the publication trends of SLRs, their application domains, and the particularities of the private and public sectors. Recommendations for future SLRs on the use of AI for service delivery are proposed. Collapse

Topics: artificial intelligence database system smart city supply chain management decision support

Methods: bibliometric analysis literature sample computational algorithm structured literature research co-citation analysis