FINFLUENCERS: OPINION MAKERS OR OPINION FOLLOWERS?

2023 | European Conference On Information Systems | Citations: 0

Authors: Haase, Frederic; Rath, Oliver; Kurka, Marco; Schoder, Detlef

Abstract: This paper explores the concept of Finfluencers: financial social network actor ... Expand

Abstract: This paper explores the concept of Finfluencers: financial social network actors with high potential social influence. Our research aims to clarify whether Finfluencers drive or are influenced by the broader social network sentiment, thereby establishing their role as either opinion makers or opinion followers. Using a dataset of 71 million tweets focusing on stocks and cryptocurrencies, we grouped actors by their social networking potential (SNP). Next, we derived sentiment time series using state-ofthe-art sentiment models and applied the technique of Granger causality. Our findings suggest that the sentiment of Finfluencer actors on Twitter has short-term predictive power for the sentiment of the larger group of actors. We found stronger support for cryptocurrencies in comparison to stocks. From the perspective of financial market regulation, this study emphasizes the relevance of understanding sentiment on social networks and high social influence actors to anticipate scams and fraud. Collapse

Topics: Twitter social network social influence cryptocurrency social media

Methods: longitudinal research time series analysis Granger causality descriptive statistic sentiment analysis

Detection of Stock Manipulation Influencer Content using Supervised Learning

2023 | International Conference on Information Systems | Citations: 0

Authors: Haase, Frederic; Rath, Oliver; Lauten, Julia; Schoder, Detlef

Abstract: In recent years, social media influencers have emerged as key players in stock ... Expand

Abstract: In recent years, social media influencers have emerged as key players in stock manipulation schemes. Despite their growing impact, methods to detect such activities remain scarcely explored. In this study, we examine the social media content of stock manipulation influencers (SMIs) implicated in a $100 million fraud case by the U.S. Securities and Exchange Commission (SEC) in 2022. Leveraging natural language processing (NLP) techniques, we first investigate the linguistic characteristics present in the social media content published by SMIs. Next, we develop and evaluate supervised learning models to detect manipulative content. Our results have significant implications for investors, regulators, and the broader financial community. They reveal the unique linguistic characteristics of SMI content and demonstrate the potential of machinelearning and deep-learning-based techniques in advancing fraud detection systems. Collapse

Topics: Twitter social media fraud detection database system social media analytics

Methods: machine learning RoBERTa DistilBERT computational algorithm natural language processing

A Survey of Technology Selection Approaches in Data Science Projects

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Haertel, Christian; Pohl, Matthias; Nahhas, Abdulrahman; Staegemann, Daniel; Turowski, Klaus

Abstract: In a world where the amount of generated and stored data is steadily increasing ... Expand

Abstract: In a world where the amount of generated and stored data is steadily increasing, Data Science (DS) has emerged as an integral discipline for organizations to extract knowledge and value from these resources. Due to the high failure rate in these undertakings, new approaches to support the project management are urgently needed. The use of appropriate technologies constitutes a success factor in DS and its selection process is regarded as a strategic project management activity. As technology selection is not described sufficiently in current DS process models, a structured literature review is performed in this article that concentrates on the addressed technology layers, the applied decision procedures, and the specific technology instances of the identified approaches. The study shows that holistic technology selection approaches that consider all activities of the DS lifecycle and the entire required tool stack are severely lacking and should, therefore, be further researched in the future. Collapse

Topics: project management decision making database system

Methods: structured literature research literature study synthesis literature sample business process modeling

Digital consumers and the new ‘search’ practices of born digital organisations

2023 | Information and Organization | Citations: 0

Authors: Hafezieh, Najmeh; Pollock, Neil

Abstract: Consumers play an increasingly central role in born digital organisations, inclu ... Expand

Abstract: Consumers play an increasingly central role in born digital organisations, including driving new approaches to consumer interaction, communication, and marketing. However, we know little about how born digital organise internally to manage and respond to consumer demands. In this paper, we studied an organisation providing online travel services where its aim was to reorganise internally, in relation to consumers, through developing a set of ‘search’ practices. The role of search is particularly salient for born digitals, giving rise to new roles and expertise where or­ ganisations attempt to pre-empt user actions. Through qualitative research, we show how a born digital organisation creates new practices that we label pre-emptive, reactive, reflective and adaptive. Our main finding is that rapidly and constantly reconfiguring practices, what these new experts call ‘constructive disruption’, is essential for born digitals to manage relationships with consumers. Our paper contributes by providing a better understanding of practices within born digital organisations, and specifically the practices born digitals use to navigate unpredictable emerging changes and produce constant novelty for customers. We also contribute to the concept of search and provide examples of how it might be employed to better understand digital organising and digital transformation. Collapse

Topics: marketing management innovation management social media Facebook digital innovation

Methods: qualitative interview field study case study triangulation company material

Co-evolution of neural architectures and features for stock market forecasting: A multi-objective decision perspective

2023 | Decision Support Systems | Citations: 0

Authors: Hafiz, Faizal; Broekaert, Jan; La Torre, Davide; Swain, Akshya

Abstract: In a multi-objective setting, a portfolio manager’s highly consequential decisio ... Expand

Abstract: In a multi-objective setting, a portfolio manager’s highly consequential decisions can benefit from assessing alternative forecasting models of stock index movement. The present investigation proposes a new approach to identify a set of non-dominated neural network models for further selection by the decision-maker. A new coevolution approach is proposed to simultaneously select the features and topology of neural networks (collectively referred to as neural architecture), where the features are viewed from a topological perspective as input neurons. Further, the co-evolution is posed as a multi-criteria problem to evolve sparse and efficacious neural architectures. The well-known dominance and decomposition based multi-objective evolutionary algorithms are augmented with a non-geometric crossover operator to diversify and balance the search for neural architectures across conflicting criteria. Moreover, the co-evolution is augmented to accommodate the data-based implications of distinct market behaviors prior to and during the ongoing COVID-19 pandemic. A detailed comparative evaluation is carried out with the conventional sequential approach of feature selection followed by neural topology design, as well as a scalarized co-evolution approach. The results on three market indices (NASDAQ, NYSE, and S&P500) in pre- and peri-COVID time windows convincingly demonstrate that the proposed co-evolution approach can evolve a set of non-dominated neural forecasting models with better generalization capabilities. Collapse

Topics: covid 19 pandemic decision support system decision making

Methods: computational algorithm artificial neural network data transformation machine learning principal component analysis

Theories: co-evolution theory

Introduction to the Minitrack on Innovation in Organizations: Learning, Unlearning, and Intentional Forgetting

2023 | HICSS | Citations: 0

Authors: Hafner, Julee

Abstract: We welcome you to the 56th Hawaii International Conference on System Sciences ... Expand

Abstract: We welcome you to the 56th Hawaii International Conference on System Sciences conference. This is the sixth year for the newly renamed Innovation in Organizations Minitrack. The Organizational Learning Minitrack and the Intentional Forgetting Minitrack have joined together. Topics that may be related -as many items within knowledge management may trace their roots from topics are all organizationally-based issues. We proudly bring you the latest research focused on the methods to develop and maintain knowledge within organizations. The Knowledge Innovation and Entrepreneurial Systems Track now includes Learning, Unlearning, and Intentional Forgetting to help researchers add to the knowledge regarding systems and processes within companies.The ability to update, change and use current knowledge effectively, especially considering the ongoing knowledge explosion, can be costly for any organization. Organizations that consider themselves "learning" or "knowledge-based" organizations must develop a competent workforce using KM strategies. Success in organizations involves developing a variety of human factors for changing competencies.With technological change, modification and revisions, many skills require updating for a competitive advantage in the marketplace.The focus on new techniques and insights into how individuals and organizations use their knowledge is our focus for the improvement of organizational learning in this Minitrack. Collapse

Topics: innovation management digital innovation industry 4.0 production management organization learning

Digital Detox Research: An Analysis of Applied Methods and Implications for Future Studies

2023 | International Conference on Business Informatics | Citations: 0

Authors: Hager, Nina; Stangl, Fabian J.; Riedl, René

Abstract: The development and increasing use of technology worldwide can lead to potentia ... Expand

Abstract: The development and increasing use of technology worldwide can lead to potential negative consequences for individuals' well-being and productivity. To counteract negative consequences, both scientific research and practice have shown increasing interest in digital detox research, a rising phenomenon of abstinence and temporary or complete disengagement from digital technologies. To lay a foundation for future research, we conducted a systemic literature review with a focus on the methodological aspects of the existing empirical digital detox studies. Our literature search process revealed a total of 65 studies. Our analyses of this literature basis revealed five different research fields (communication, education, tourism, well-being and health, work environment), and we analyzed the empirical studies in these fields regarding applied research approach, research method, and sample size. This review provides methodological insights to advance the scientific inquiry on digital detox research, a relatively nascent, yet increasingly relevant research topic. Collapse

Topics: internet technology database system individual productivity Facebook IS discipline

Methods: literature study experiment mixed method survey experimental group

A Mid-Range Theory for Designing Sustainable Safe Spaces of Immersive Learning Environments: A Design-Science Based Gamification Approach

2023 | DESRIST | Citations: 0

Authors: Haj-Bolouri, Amir; Katende, Jesse; Rossi, Matti

Abstract: Gamification provides a prominent technique that can be used to provide Immersiv ... Expand

Abstract: Gamification provides a prominent technique that can be used to provide Immersive Learning Environments (ILEs) for domains, where it is dangerous or expensive to learn in real environments. Especially industrial organizations (e.g., manufacturing, mining, construction) are a promising domain for implementing ILEs that combine gamification concepts with a pedagogical design to facilitate safety training under secure circumstances. Although there are design research studies that exemplify the utility of gamification of learning activities, or how to improve organizational safety training through gamification, there is a need to address how sustainable safe spaces can be designed for enhanced safety training in ILEs. Safe spaces are key elements of a successful safety training experience in ILEs as they provide safe and secure training environments, which in the physical world are typically considered too dangerous with high risk of injuring the training participants. This study reports findings from an ongoing DSR project that stresses the design of ILEs for sustainable safety training. Within the project, an artifact for immersive fire safety training in virtual reality has been designed, developed, and evaluated together with employees of a train operator company. The research responds to the need of producing design knowledge that moves beyond the highly contextualized designs principles that are particular for IVR applications. We use gamification concepts as a kernel theory for developing a mid-range theory of designing immersive virtual safety training environments. Collapse

Topics: gamification virtual reality communities of practice

Methods: kernel theory design artifact design science qualitative interview design process

The Experience of Immersive Virtual Reality: A Phenomenology Inspired Inquiry

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

Authors: Haj-Bolouri, Amir

Abstract: Immersive Virtual Reality (IVR) technology is becoming central for Information ... Expand

Abstract: Immersive Virtual Reality (IVR) technology is becoming central for Information Systems (IS) research. However, existing studies in IS fall short of providing insights into how the IVR experience becomes meaningful for end-users.To increase granularity and specificity in this regard, researchers have suggested that the IVR experience can become meaningful due to its fleeting feeling of escapism. In this paper, I explore and characterize how individuals use the IVR experience to create meaning in the context of meaningful escapism, by undertaking a phenomenology inspired inquiry, based on Heideggerian views on meaning, meaningfulness, and world. Interviews and analysis were conducted within an empirical case of IVR fire safety training. As a result, four characteristics of the IVR experience as a meaningful form of escapism were unveiled: a sense of content, a sense of familiarity, a sense of mood, and a sense of care. Throughout this study, I offer a nuanced perspective on how the characteristics contribute to clarifying the distinctions and relationship between meaning and meaningfulness, as well as how the IVR experience becomes a meaningful escapism that provides an alternative of individual's being-in-the-world, into a being-in-the-virtual-world, also known as Virtual Dasein. Further, this study contributes to the IS field by advancing the current discourse on IVR research and escapism, from a phenomenological perspective.which then might find its place into our lifeworld and thus makes the experience feel meaningful. It is against this background that this paper asks the following research question: RQ1: How do individuals use the IVR experience to create meaning in the context of meaningful escapism?This study deliberately asks 'how' rather than 'what', because how the IVR individuals use the IVR experience to create meaning is a subject matter for inquiring about the lifeworld of an individual (Van Manen, 2017), which deals with the sensory perception (also known as 'qualia') of the feeling of meaningfulness. In other words, the emphasis is on the meaningful user activity in the context of meaningful escapism rather than on the category of a 'meaningful way of escaping the world'.Meaningfulness is in such terms, as will be explicated in the latter parts of this paper, felt through a mood derived from how the IVR experience matters to the end-user's lifeworld , rather than being a fact that the experience is meaningful (Freeman & Elpidorou, 2015). Hence, the becoming part of the research question is central to exploring how the IVR experience can be perceived or felt as a meaningful escapism by end-users of IVR technology. As such, the research question motivates a phenomenological inquiry that helps this study to address the question, because phenomenology studies the lived experience of sensory perceptions and the phenomena that contribute to meaning and meaningfulness in our lifeworld (Van Manen, 2016.More specifically, this study employed a phenomenological inquiry based on Martin Heidegger's (1962) phenomenology with a particular focus on meaning, meaningfulness, and the notion of 'world'. Moreover, this study applied a phenomenological approach to interviewing and data analysis (Bevan, 2014). The phenomenological interviews were conducted together with participants of IVR fire safety training, participants who, on a daily basis, work as train operators and train drivers for Sweden's largest train operator company. In summary, the phenomenological inquiry helped this study to (i) identify situations where the participants of the fire safety training feel that the IVR experience urges them to escape the world; (ii) unveil and characterize how the IVR experience becomes an escapism; and (iii) provide a discussion about the IVR experience in IS, which goes beyond the ontological assumptions of representationalismbeing the ontological view that has dominated extant Collapse

Topics: virtual world virtual reality

Methods: qualitative interview phenomenological method qualitative coding case study grounded theory

Fraud Detection in Mobile Payment Systems using an XGBoost-based Framework

2023 | Information Systems Frontiers | Citations: 0

Authors: Hajek, Petr; Abedin, Mohammad Zoynul; Sivarajah, Uthayasankar

Abstract: Mobile payment systems are becoming more popular due to the increase in the numb ... Expand

Abstract: Mobile payment systems are becoming more popular due to the increase in the number of smartphones, which, in turn, attracts the interest of fraudsters. Extant research has therefore developed various fraud detection methods using supervised machine learning. However, sufficient labeled data are rarely available and their detection performance is negatively affected by the extreme class imbalance in financial fraud data. The purpose of this study is to propose an XGBoost-based fraud detection framework while considering the financial consequences of fraud detection systems. The framework was empirically validated on a large dataset of more than 6 million mobile transactions. To demonstrate the effectiveness of the proposed framework, we conducted a comparative evaluation of existing machine learning methods designed for modeling imbalanced data and outlier detection. The results suggest that in terms of standard classification measures, the proposed semi-supervised ensemble model integrating multiple unsupervised outlier detection algorithms and an XGBoost classifier achieves the best results, while the highest cost savings can be achieved by combining random under-sampling and XGBoost methods. This study has therefore financial implications for organizations to make appropriate decisions regarding the implementation of effective fraud detection systems. Collapse

Topics: fraud detection mobile system mobile payment electronic payment Python

Methods: XGBoost machine learning anomaly detection supervised learning experiment