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

EMBRACING CONCEPTUAL MODELLING TO ENABLE THE MEDIATION ROLE OF ENTERPRISE INFORMATION SYSTEMS

2023 | European Conference On Information Systems | Citations: 0

Authors: Chis, Andrei; Ghiran, Ana-Maria

Abstract: Nowadays, digital environments are critical regarding the way enterprise operat ... Expand

Abstract: Nowadays, digital environments are critical regarding the way enterprise operations are conducted and how enterprises are being developed. Traditional information systems used by enterprises need to evolve to accommodate the shift of their role from representation to mediation, role that has been recently conceptualized but not sufficiently researched to identify means that enable its operationalization across domains and purposes. This work identifies what are the key enablers and how should these be applied regardless of the domain of interest. For this, our paper showcases as a proof-of-concept artifact that operationalizes the before mentioned new role of the IS. Our proposal relies on Conceptual Modelling together with all the other related enablers like Digital Twins, metamodelling platforms or model-driven operation. Our example concerns the modern organization that continuously aims to become more innovative and gain competitive advantage therefore, it employs smart devices like drones in different business operations. Collapse

Topics: Python systems development digital twin usability production management

Methods: design science design artifact business process model and notation modeling language metamodel

Mastering Agile Practice Adoption through a Model-Driven Approach for the Combination of Development Methods

2023 | Business & Information Systems Engineering | Citations: 0

Authors: Giachetti, Giovanni; de la Vara, José Luis; Marín, Beatriz

Abstract: Many software companies are adapting their traditional development processes to ... Expand

Abstract: Many software companies are adapting their traditional development processes to incorporate agile practices. In this context, it is necessary to count on expert knowledge to evaluate different agile practices and configure them according to project needs. However, this expert knowledge is scarce, difficult to validate, and time-consuming, since it is applied manually. As a solution, the paper presents a model-driven approach, called SIAM, which automatically generates guidelines for the adoption of agile practices through the combination of different development methods. SIAM is supported by a meta-model architecture to implement a knowledge repository that characterizes method configuration decisions, which can be reused in different development projects. SIAM has been implemented in a tool suite that facilitates the specification of models and the identification of issues during the definition of the development processes. The approach has been successfully applied to reconfigure an industrial development process with agile methods, showing that the effort required for tailoring agile practices according to organizational standards is considerably reduced. Collapse

Topics: agile software development Scrum knowledge repository system development method waterfall model

Methods: design methodology business process modeling case study metamodel design science

How Best to Hunt a Mammoth - Toward Automated Knowledge Extraction From Graphical Research Models

2023 | International Conference on Business Informatics | Citations: 0

Authors: Huettemann, Sebastian; Mueller, Roland M.; Larsen, Kai R.; Dinter, Barbara; Chiny, Joshua Campos

Abstract: ... Expand

Abstract: Collapse

Topics: knowledge repository database system knowledge base application programming interface Python

Methods: design science metamodel computational algorithm machine learning literature study

Model-Based Cybersecurity Analysis

2023 | Business & Information Systems Engineering | Citations: 0

Authors: Jiang, Yuning; Jeusfeld, Manfred A.; Ding, Jianguo; Sandahl, Elin

Abstract: Critical infrastructure (CIs) such as power grids link a plethora of physical co ... Expand

Abstract: Critical infrastructure (CIs) such as power grids link a plethora of physical components from many different vendors to the software systems that control them. These systems are constantly threatened by sophisticated cyber attacks. The need to improve the cybersecurity of such CIs, through holistic system modeling and vulnerability analysis, cannot be overstated. This is challenging since a CI incorporates complex data from multiple interconnected physical and computation systems. Meanwhile, exploiting vulnerabilities in different information technology (IT) and operational technology (OT) systems leads to various cascading effects due to interconnections between systems. The paper investigates the use of a comprehensive taxonomy to model such interconnections and the implied dependencies within complex CIs, bridging the knowledge gap between IT security and OT security. The complexity of CI dependence analysis is harnessed by partitioning complicated dependencies into cyber and cyber-physical functional dependencies. These defined functional dependencies further support cascade modeling for vulnerability severity assessment and identification of critical components in a complex system. On top of the proposed taxonomy, the paper further suggests power-grid reference models that enhance the reproducibility and applicability of the proposed method. The methodology followed was design science research (DSR) to support the designing and validation of the proposed artifacts. More specifically, the structural, functional adequacy, compatibility, and coverage characteristics of the proposed artifacts are evaluated through a three-fold validation (two case studies and expert interviews). The first study uses two instantiated power-grid models extracted from existing architectures and frameworks like the IEC 62351 series. The second study involves a real-world municipal power grid. Collapse

Topics: IT security virtualization technology database system knowledge representation data center

Methods: reference modelling case study qualitative interview design artifact simulation

SITUATIONAL ROADMAP DEVELOPMENT FOR BUSINESS PROCESS IMPROVEMENT VIA A MODELING TOOL

2023 | European Conference On Information Systems | Citations: 0

Authors: Johannsen, Florian

Abstract: The integration of new technologies as well as the need to increase customer sa ... Expand

Abstract: The integration of new technologies as well as the need to increase customer satisfaction and reduce costs require companies to continuously analyze and improve their business processes. Hence, Business Process Improvement (BPI) ranks high on the agenda of many companies. However, existing methods like Six Sigma are often perceived as overly complex for projects with a limited scope. Therefore, more and more companies focus on the application of a few selected BPI techniques only, which are logically arranged in the form of "roadmaps" to tackle process weaknesses. Against this backdrop, the concept of "tool-supported situational roadmap development for BPI" along with a corresponding prototype are introduced. The approach builds on conceptual modeling and is technically realized by means of a metamodeling platform. Accordingly, the research offers practitioners a solution to systematically create project-specific roadmaps for BPI to improve process performance. Collapse

Topics: evaluation criteria ease of learning systems development

Methods: design science design artifact metamodel conceptual modelling

Leveraging Interactions for Stationary and Dynamic Financial Distress Prediction: A Spatio-Temporal Financial Graph Attention Network

2023 | International Conference on Information Systems | Citations: 0

Authors: Qi, Qi; Xing, Frank

Abstract: Financial distress prediction is a prominent research topic in information syst ... Expand

Abstract: Financial distress prediction is a prominent research topic in information systems, with two primary modelling categories: stationary and dynamic modelling. Recent stationary modelling works have leveraged company interactions to improve prediction performance, considering the heterogeneity of interactions while ignoring the dynamicity. However, few dynamic modelling works utilized interactions. To address the inconsistency and limitation of stationary and dynamic modelling works in leveraging interactions, we propose the Spatio-Temporal Financial Graph Attention Network with Metalearning (STFGAN-Meta). STFGAN-Meta leverages interactions' spatial heterogeneity via the Spatial Aggregation module and temporal dynamicity via the Temporal Aggregation module. STFGAN-Meta introduces the Meta-learning Optimization module to unify stationary and dynamic modelling. Our experimental evaluation demonstrates that leveraging dynamicity and heterogeneity of interactions outperforms leveraging dynamicity or heterogeneity alone. Meta-learning succeeds in providing a generalized approach between stationary and dynamic modelling. STFGAN-Meta can be a promising risk assessment and decision-making tool in the financial industry. Collapse

Topics: decision making database system accounting Python

Methods: meta learning experiment machine learning metamodel design science

Beyond Paper and Plastic: A Meta-Model for Credential Use and Governance

2023 | European Conference On Information Systems | Citations: 0

Authors: Richter, Daniel; Praas, Christopher; Anke, Jürgen

Abstract: ID cards, public transport tickets, and diplomas are examples of credentials th ... Expand

Abstract: ID cards, public transport tickets, and diplomas are examples of credentials that society has established as a means to provide trustworthy information to others. In the digital world, the emergence of self-sovereign identity as a new paradigm for the management of digital credentials aims to narrow the conceptual gap between digital and physical credentials. The ongoing digital transformation in the public sector requires dealing with a large variety of credentials in different forms systematically. However, there is still currently no generic conceptual model of credentials in the Information Systems (IS) discipline. We employ design science research to develop a unified meta-model on credentials, their use, and their governance. Our results contribute to research through an empirically grounded conceptualization of credentials and provide practitioners with a common basis to capture, analyze, and design the handling of credentials in real-world scenarios. Collapse

Topics: knowledge base Near Field Communication IT governance security policy government system

Methods: design science metamodel design requirement literature study qualitative interview

Architecture Design Options for Federated Data Spaces

2023 | HICSS | Citations: 3

Authors: Schleimer, Anna Maria; Jahnke, Nils; Otto, Boris

Abstract: The massive growth of data and the increasing potential of data analytics in ind ... Expand

Abstract: The massive growth of data and the increasing potential of data analytics in industrial production fuel the emergence of data spaces and corresponding platforms that realize data ecosystems and enable data-driven sustainability applications. To leverage their benefits of demand-driven and scalable data integration, the stakeholders of emerging data space initiatives must make informed decisions about their data space support platforms (DSSPs). This study proposes a conceptual framework based on federated architectures and by considering existing endeavors of data infrastructures. Based on existing literature about data ecosystem resources and an explorative single case study of an industrial data space with sustainability-focused applications, we elaborate on the key design options of data, services, and computing infrastructures. The resulting conceptual framework guides design decisions for DSSPs. The framework captures not only the resources involved but also the operational concepts of federated services and shared services to introduce governance mechanisms and sustainability policies. Collapse

Topics: digital ecosystem enterprise resource planning

Methods: single case study design science metamodel case study

Depicting Risk Profile over Time: A Novel Multiperiod Loan Default Prediction Approach

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Wang, Zhao; Jiang, Cuiqing; Zhao, Huimin

Abstract: With the rapid development of fintech, the need for dynamic credit risk evaluat ... Expand

Abstract: With the rapid development of fintech, the need for dynamic credit risk evaluation is becoming increasingly important. While previous studies on credit scoring have mostly focused on single-period loan default prediction, we call for a new avenue-multiperiod default prediction (MPDP)-to depict risk profiles over time. To address the challenges raised by MPDP, such as monotonic default probability prediction and complex relationship accommodation, we propose a novel approach, hybrid and collective scoring (HACS). We design a hybrid modeling strategy to predict whether and when a borrower will default separately through a default discrimination model and a default time estimation model, respectively, and synthesize them through a probabilistic framework. To accommodate various possible patterns of default time and measure the distribution of default probability over successive time intervals, we propose a joint default modeling method to train the default time estimation model. Empirical evaluations at the model (time-to-default prediction performance and discrimination performance) and mechanism (identifiability and discriminability) levels, as well as impact analyses at the application (granting performance and profitability performance) level, show that HACS outperforms the benchmarked survival analysis and multilabel learning methods on all fronts. It can more accurately predict time-to-default and provide financial institutions and investors better decisionsupport in granting loans and selecting loan portfolios. Collapse

Topics: online lending risk management decision making analytical information system

Methods: survival analysis case study machine learning design science design artifact

Theories: portfolio theory