TRADING GREEN BONDS USING DISTRIBUTED LEDGER TECHNOLOGY

2023 | European Conference On Information Systems | Citations: 0

Authors: Axelsen, Henrik; Rasmussen, Ulrik; Jensen, Johannes; Ross, Omri; Henglein, Fritz

Abstract: The promising markets for voluntary carbon credits are faced with crippling cha ... Expand

Abstract: The promising markets for voluntary carbon credits are faced with crippling challenges to the certification of carbon sequestration and the lack of scalable market infrastructure in which companies and institutions can invest in carbon offsetting. This amounts to a funding problem for green transition projects, such as in the agricultural sector, since farmers need access to the liquidity needed to fund the transition to sustainable practices. We explore the feasibility of mitigating infrastructural challenges based on a DLT Trading and Settlement System for green bonds. The artefact employs a multi-sharded architecture in which the nodes retain carefully orchestrated responsibilities in the functioning of the network. We evaluate the artefact in a supranational context with an EU-based regulator as part of a regulatory sandbox program targeting the new EU DLT Pilot regime. By conducting design-driven research with stakeholders from industrial and governmental bodies, we contribute to the IS literature on the practical implications of DLT. Collapse

Topics: distributed ledger technology network effect blockchain domain-specific language

Methods: design science qualitative interview design artifact testing design artifact

Incorporating Multiple Knowledge Sources for Targeted Aspect-based Financial Sentiment Analysis

2023 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Du, Kelvin; Xing, Frank; Cambria, Erik

Abstract: Combining symbolic and subsymbolic methods has become a promising strategy as re ... Expand

Abstract: Combining symbolic and subsymbolic methods has become a promising strategy as research tasks in AI grow increasingly complicated and require higher levels of understanding. Targeted Aspect-based Financial Sentiment Analysis (TABFSA) is an example of such complicated tasks, as it involves processes like information extraction, information specification, and domain adaptation. However, little is known about the design principles of such hybrid models leveraging external lexical knowledge. To fill this gap, we define anterior, parallel, and posterior knowledge integration and propose incorporating multiple lexical knowledge sources strategically into the fine-tuning process of pre-trained transformer models for TABFSA. Experiments on the Financial Opinion mining and Question Answering challenge (FiQA) Task 1 and SemEval 2017 Task 5 datasets show that the knowledge-enabled models systematically improve upon their plain deep learning counterparts, and some outperform state-of-the-art results reported in terms of aspect sentiment analysis error. We discover that parallel knowledge integration is the most effective and domain-specific lexical knowledge is more important according to our ablation analysis. Collapse

Topics: microblog domain-specific language Twitter social media knowledge graph

Methods: sentiment analysis RoBERTa transformer model BERT XLNet

Analyzing the Needs of Ukrainian Refugees on Telegram in Real-Time: A Machine Learning Approach

2023 | International Conference on Business Informatics | Citations: 0

Authors: Reimann, Raphael; Caron, Matthew

Abstract: The humanitarian crisis resulting from the Russian invasion of Ukraine has led ... Expand

Abstract: The humanitarian crisis resulting from the Russian invasion of Ukraine has led to millions of displaced individuals across Europe. Addressing the evolving needs of these refugees is crucial for hosting countries and humanitarian organizations. This study leverages social media analytics to supplement traditional surveys, providing real-time insights into refugee needs by analyzing over two million messages from Telegram, a vital platform for Ukrainian refugees in Germany. We employ Natural Language Processing techniques, including language identification, sentiment analysis, and topic modeling, to identify well-defined topic clusters such as housing, financial and legal assistance, language courses, job market access, and medical needs. Our findings also reveal changes in topic occurrence and nature over time. To support practitioners, we introduce an interactive web-based dashboard for continuous analysis of refugee needs. Collapse

Topics: Telegram social media digital dashboard Twitter decision making

Methods: topic model natural language processing sentiment analysis transformer model data transformation

A text summary-based method to detect new events from streams of online news articles

2022 | Information & Management | Citations: 0

Authors: Lee, Yen-Hsien; Wei, Chih-Ping; Hu, Paul Jen-Hwa; Wu, Pao-Feng; Jiang, How

Abstract: New event detection (NED), which is crucial to firms’ environmental surveillance ... Expand

Abstract: New event detection (NED), which is crucial to firms’ environmental surveillance, requires timely access to and effective analysis of live streams of news articles from various online sources. These news articles, available in unprecedent frequency and quantity, are difficult to sift through manually. Most of existing techniques for NED are full-text-based; typically, they perform full-text analysis to measure the similarity between a new article and previous articles. This full-text-based approach is potentially ineffective, because a news article often contains sentences that are less relevant to define the focal event being reported and the inclusion of these less relevant sentences into the similarity estimation can impair the effectiveness of NED. To address the limitation of the fulltext-based approach and support NED more effectively and efficiently, this study proposes and develops a summary-based event detection method that first selects relevant sentences of each article as a summary, then uses the resulting summaries to detect new events. We empirically evaluate our proposed method in comparison with some prevalent full-text-based techniques, including a vector space model and two deep-learning-based models. Our evaluation results confirm that the proposed method provides greater utilities for detecting new events from online news articles. This study demonstrates the value and feasibility of the text summarization approach for generating news article summaries for detecting new events from live streams of online news ar­ ticles, proposes a new method more effective and efficient than the benchmark techniques, and contributes to NED research in several important ways. Collapse

Topics: digital news domain-specific language website computer virus evaluation criteria

Methods: BERT deep learning cluster analysis decision tree classification supervised learning

What Makes Data Possible? A Sociotechnical View on Structured Data Innovations

2021 | HICSS | Citations: 12

Authors: Aaltonen, Aleksi; Penttinen, Esko

Abstract: Drawing from the theory of digital objects, this paper examines the distinction ... Expand

Abstract: Drawing from the theory of digital objects, this paper examines the distinction between structured and unstructured data as carriers of facts. We argue that data do not ‘have’ a structure but are made by a structure that confers data their capacity to represent contextual facts. We employ a case vignette involving XBRL (eXtensible Business Reporting Language) and its use in statutory financial reporting to illustrate and explore the sociotechnical nature of data and to describe what we call data innovations: new valuable ways to render phenomena as data. We find that data structure is best viewed as a matter that is relative to a purpose in a context. Theorizing data from a sociotechnical perspective could evolve to provide, in effect, the material science of digital economy. Collapse

Topics: electronic data interchange accounting domain-specific language innovation management information reporting system

Methods: natural language processing data modeling design science database modeling

Theories: theory of digital objects

Introduction to the Digital Government and Business Process Management (BPM) minitrack HICSS’54

2021 | HICSS | Citations: 0

Authors: Delgado, Andrea; Montarnal, Aurelie; Astudillo, Hernán; María, Federico Santa; Cabanillas, Cristina; de Sevilla, Universidad

Abstract: Digital Government (traditionally known as eGovernment) focuses on value deliver ... Expand

Abstract: Digital Government (traditionally known as eGovernment) focuses on value delivery to citizens through information and communication technology (ICT) support for processes, activities and resources. Digital government’s collaborative processes involve organizations (employees, technologies), partners (providers, consumers), and users (citizens, foreigners), leading to complex interactions within different eGovernment models and available technologies. Business Process Management (BPM) constitutes a real asset for enhancing the services of an organization and their coordination, as well as the products that each actor of a virtual network delivers to meet clients’ expectations (citizens, patients, etc.). Successful interorganizational process management within eGovernment collaborative organizations will lead to better conceptual and technological integration, not only with each other but also with citizens and users in general. To this end, it is necessary to devise new ways to deal with the complexity of e-Government collaborative process definition, modeling, analysis, enactment and monitoring from various dimensions and points of view including theory, engineering, interoperability, agility, social aspects, etc. Collapse

Topics: government system smart contract online auction business process management system support

Methods: business process model and notation modeling language business process modeling case study

MuTent: Dynamic Android Intent Protection with Ownership-Based Key Distribution and Security Contracts

2021 | HICSS | Citations: 0

Authors: Duraisamy Soundrapandian, Pradeep Kumar; Bao, Tiffany; Baek, Jaejong; Shoshitaishvili, Yan; Doupé, Adam; Wang, Ruoyu; Ahn, Gail-Joon

Abstract: Intents are the plain-text based message object used for ICC by the Android fram ... Expand

Abstract: Intents are the plain-text based message object used for ICC by the Android framework. Hence the framework essentially lacks an inbuilt security mechanism to protect the visibility, accessibility, and integrity of Intent’s data that facilitates adversaries to intercept or manipulate the data. Collapse

Topics: mobile application Android data encryption Java computer hardware

Methods: computational algorithm

Cognitive Diagram Understanding and Task Performance in Systems Analysis and Design

2021 | Management Information Systems Quarterly | Citations: 10

Authors: Malinova, Monika; Mendling, Jan

Abstract: Models play an important role in systems analysis and design (SAD). A diagrammat ... Expand

Abstract: Models play an important role in systems analysis and design (SAD). A diagrammatic model is defined as a mapping from a domain to a visual representation in such a way that relevant information is preserved to meet a specific goal. So far, cognitive research on diagram criteria in relation to task performance has been fragmented. The aim of this paper is to (1) consolidate research on the cognitive processing steps involved during understanding and task performance with diagrams, (2) consolidate corresponding criteria for such diagrams to best support cognitive processing, and (3) demonstrate the support effective diagrams provide for performing SAD tasks. Addressing the first aim, we develop a theoretical cognitive framework of task performance with diagrams called CogniDia. It integrates different cognitive theories from research on diagrams in software engineering and information systems. Regarding the second aim, we review the literature to organize criteria for effective cognitive processing of diagrams. We identify research gaps on verbal and task processing. Regarding the third aim, we use the theoretical cognitive framework to investigate how diagrams support the SAD process effectively. Collapse

Topics: task productivity sensemaking requirements elicitation systems design requirements analysis

Methods: modeling language design science business process modeling literature sample data modeling

Theories: cognitive theory cognitive fit theory cognitive load theory cognitive theory of multimedia learning dual-coding theory

Health in the Era of the Internet of Things: A Domain-Specific Modelling Language

2021 | HICSS | Citations: 0

Authors: Strobel, Gero

Abstract: Based on the cultural, social and technological development of the last hundred ... Expand

Abstract: Based on the cultural, social and technological development of the last hundred years, the pursuit of health driven by primal instincts has been transformed in most areas worldwide into a quasi de facto standard. But this security is deceptive. Not only the global developments of the last few months, but also creeping factors such as demographic change or the steadily growing world population are putting increasing pressure on the healthcare system. Today, more and more health care systems based on continuous demand for medical resources are increasingly reaching their limits. Technologies such as the Internet of Things are not a panacea, but offer great potential for increasing the flexibility and efficiency of healthcare systems. However, the development of such IoT-based healthcare systems requires a holistic understanding of the information technology as well as the domain itself. Against this background, the paper presents a domain-specific modelling language for IoT-based healthcare systems. Collapse

Topics: health information system domain-specific language enterprise architecture technological change electronic health

Methods: design science modeling language design artifact

Detecting Violent Crime with Gang Social Media Postings

2020 | International Conference on Information Systems | Citations: 0

Authors: Fowler, Sherry L; Stylianou, Antonis; Mousavi, Reza; Reid, Shannon; Zhang, Dongsong

Abstract: Many large cities in the U.S. have a problem with violent crime, some of which i ... Expand

Abstract: Many large cities in the U.S. have a problem with violent crime, some of which is committed by gang affiliates who use social media platforms to express and quickly disseminate messages of loss and aggression. This research explored the feasibility of automatically finding gang-affiliated criminal signaling and examining the relationship between this signaling and daily crime. We found that several indicators point to credible aggression and loss in gang-affiliated tweets, including the number of followers and the frequency and speed of the retweets. Credible aggression, along with several other predictors such as weather and past crime instances, were positively associated with violent crime in the subsequent period. Knowledge of these indicators has theoretical importance for understanding credible social media posts and later interactive engagement and practical significance for communities in mitigating violent crime by finding criminal signals in the virtual space before actual crimes are committed in the physical space. Collapse

Topics: Twitter criminality social media information exchange Python

Methods: descriptive statistic word embedding computational algorithm linear regression analysis multiple linear regression