Interactive Visual Analytics for Knowledge Integration and Decision Intelligence (CC BY-NC-ND 4.0)

2023 | HICSS | Citations: 0

Authors: Fisher, B.; Gaither, K.; Ebert, D.

Abstract: Interactive Visual Analytics for Knowledge Integration and Decision Intelligenc ... Expand

Abstract: Interactive Visual Analytics for Knowledge Integration and Decision Intelligence seeks to find ways to develop visualization environments and methods for their use that will support human analysis and decision making with interaction with data and statistical and machine learning processes. Visual analytics provides a way to address problems and opportunities that are characterized by complex data that may be uncertain in fact, relevance, location in space and position in time. Knowledge integration comes into play when multiple datasets from different sources must be evaluated and integrated into the decision-making process. Decision intelligence focuses on the decision-making process itself, examining how individuals and groups chose among alternatives in making plans for action. As defined by Gartner, DI "brings together the best of applied data science, social science, and managerial science into a unified field that helps people use data to improve their lives, their businesses, and the world around them."Applications of this approach include many areas where decision-making must consider complex situations, conflicting data, and priorities. Examples include environmental science and technologies, natural resources and energy, health, and related life sciences. safety and security and many business processes. This year we are examining new approaches to integrating data from neural activity into human factors and discussing ways in which organizations from different sectors can partner to provide value for both industry and academia. Key research challenges of interest in this area include studies of visual analytics and decision support for industrial organizations including the integration of domain knowledge and better understanding of opportunities to improve safety and efficiency in aircraft design.The rapid pace and demand of an increasingly more digital world necessarily mandates that analytics play a key role as we increasingly need to make rapid sense of complex and fast changes driven by big, realtime data. We have moved into an era in which being able to "see" the information in the data is no longer optional and sophisticated visualization methods facilitating rapid understanding is a necessary and critical piece of the "competitive edge". The focus in this minitrack goes beyond analytics to include rich, powerful visualization techniques for turning data into actionable information and ways to better support the decision-making process.This minitrack builds upon earlier HICSS minitracks on visual analytics, mobile computing, and digital media at scale, focusing more decision analytics on various applications from business to science, and public safety. Our first paper seeks to find ways to use machine learning analysis of EEG data to better assess the cognitive load of a task on analysts and decisionmakers. They compare this measure to the humanfactors standard for cognitive load estimation, the NASA-TLX. The second paper gives a retrospective account of an exemplary research collaboration between two universities in Canada and Boeing, a large and technologically sophisticated industry partner, on a focused research effort to integrate visual analytics into Boeing's manufacturing and safety analysis processes. Multiple departments and fields of study relating to analysis, visualization, and decision-making participated in this process, and funding from multiple government agencies supported this effort. Our third paper aims to contribute novel transparency enhancing grounded theory model illustrations annotated with discussion and suggestions that others can adapt for their purposes.These papers show a wide range of applications of visualization and analytics in complex decision-making environments and provide valuable insights into the design, production, and deployment of visual analytics applicable to most decision and discovery tasks across a broad spectrum of applications. Moreover, they clearly demonstrate effective ways to harness and tame big data for discovery, insight, management, and action in realworld, actionable environments. We hope you will join us for interesting presentations and lively discussions on new visual analytics techniques and solutions for our evolving landscape of societal problems requiring rapid and reliable decision making. Collapse

Topics: visual analytics decision making

Methods: exploratory data analysis grounded theory electroencephalography machine learning

Pair Analytics in a Visual Analytics Context

2023 | HICSS | Citations: 0

Authors: Fisher, B.; Kasik, D.

Abstract: This case study details the development of "pair analytics" as practical approa ... Expand

Abstract: This case study details the development of "pair analytics" as practical approach to applied analysis and as a scientific research method. The hybrid research project itself was part of a larger research program approved for the Canadian government for their offset program and supported by Federal and Provincial research internships. As a real-world analysis approach, the pair analysis sessions conduced actionable causal chain analysis of aircraft safety. As a scientific method, pair analytics advanced our knowledge of the cognitive science of interpersonal communication in Joint Activities. The paper describes how aerospace researchers and cognitive scientists were able to design a research approach that met constraints from both areas. It concludes with discussion of the implications of this work for highly integrated basic and responsive research in other areas of visualization and analytics. Collapse

Topics: visual analytics crowdsourcing

Methods: exploratory data analysis ethnography case study laboratory experiment grounded theory

Theories: activity theory theory of distributed cognition

Beyond Dashboards? Designing Data Stories for Effective Use in Business Intelligence and Analytics

2023 | European Conference On Information Systems | Citations: 0

Authors: Gunklach, Jonas; Jacob, Katharina; Michalczyk, Sven

Abstract: With the proliferation of Business Intelligence and Analytics, data storytellin ... Expand

Abstract: With the proliferation of Business Intelligence and Analytics, data storytelling has gained increasing importance to improve communicating analytical insights to business users and support decision-making. While conceptual research on data storytelling suggests that these techniques can help improve decisionmaking, there is a lack of prescriptive knowledge on how to design data stories in Business Intelligence and Analytics. Moreover, it is not understood how data stories can facilitate effective use and support decision-making of business users. To address this challenge, we conduct a Design Science Research (DSR) project. Drawing on the theory of effective use and data storytelling techniques, we propose three design principles that we instantiate in a prototype. The results of two focus groups indicate that enhancing dashboards with data storytelling techniques increases transparent interaction and representational fidelity. Our DSR project contributes novel design knowledge for data stories that facilitate effective use. Collapse

Topics: digital dashboard data visualization analytical information system database system decision making

Methods: literature study focus group qualitative interview literature sample design principle

Theories: theory of effective use

Guidance in Business Intelligence & Analytics Systems: A Review and Research Agenda

2023 | European Conference On Information Systems | Citations: 0

Authors: Gunklach, Jonas; Nadj, Mario

Abstract: While the data amount grows exponentially, the number of people with analytical ... Expand

Abstract: While the data amount grows exponentially, the number of people with analytical and technical skills is only slowly increasing. This skill gap is putting pressure on the labor market and increasing the need for personnel with these skills. At the same time, companies are forced to think of alternative ways to empower their less-skilled workforce to take on Business Intelligence and Analytics (BI&A) tasks. One promising attempt to address these challenges may turn to the concept of guidance. However, the current body of research on guidance in BI&A systems is scattered and lacks a structured investigation from which future research avenues can be derived. To address this gap, this article analyzes five categories, namely BI&A phases, guidance degree, guidance generation, user roles, and interactivity form. Reviewing 82 articles, our contribution is to synopsize articles on guidance in BI&A systems and to suggest five research avenues. Collapse

Topics: analytical information system data visualization data quality business intelligence artificial intelligence

Methods: exploratory data analysis machine learning literature sample time series analysis longitudinal research

Visual Analytics: Transferring, Translating and Transforming Knowledge from Analytics Experts to Non-technical Domain Experts in Multidisciplinary Teams

2023 | Information Systems Frontiers | Citations: 0

Authors: Marjanovic, Olivera; Patmore, Greg; Balnave, Nikola

Abstract: Today’s complex problems call for multidisciplinary analytics teams comprising o ... Expand

Abstract: Today’s complex problems call for multidisciplinary analytics teams comprising of both analytics and non-technical domain (i.e. subject matter) experts. Recognizing the difference between data visualisaion (DV) (i.e. static visual outputs) and visual analytics (VA) (i.e. a process of interactive visual data exploration, guided by user’s domain and contextual knowledge), this paper focuses on VA for non-technical domain experts. By seeking to understand knowledge sharing from VA experts to non-technical users of VA in a multidisciplinary team, we aim to explore how these domain experts learn to use VA as a thinking tool, guided by their knowing-in-practice. The research described in this paper was conducted in the context of a long-term industry-wide research project called the ‘Visual Historical Atlas of the Australian Co-operatives’, led by a multidisciplinary VA team who faced the challenge tackled by this research. Using Action Design Research (ADR) and the combined theoretical lens of boundary objects and secondary design, the paper theorises a three-phase method for knowledge transfer, translation and transformation from VA experts to domain experts using different types of VA-related boundary objects. Together with the proposed set of design principles, the three-phase model advances the well-established stream of research on organizational use of analytics, extending it to the emerging area of visual analytics for non-technical decision makers. Collapse

Topics: knowledge sharing data visualization implicit knowledge knowledge management participatory design

Methods: kernel theory design science action design research exploratory data analysis theory development

Theories: boundary objects theory

MediCoSpace: Visual Decision-Support for Doctor-Patient Consultations using Medical Concept Spaces from EHRs

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

Authors: van der Linden, Sanne; Sevastjanova, Rita; Funk, Mathias; El-Assady, Mennatallah

Abstract: Healthcare systems are under pressure from an aging population, rising costs, an ... Expand

Abstract: Healthcare systems are under pressure from an aging population, rising costs, and increasingly complex conditions and treatments. Although data are determined to play a bigger role in how doctors diagnose and prescribe treatments, they struggle due to a lack of time and an abundance of structured and unstructured information. To address this challenge, we introduce MediCoSpace, a visual decision-support tool for more efficient doctor-patient consultations. The tool links patient reports to past and present diagnoses, diseases, drugs, and treatments, both for the current patient and other patients in comparable situations. MediCoSpace uses textual medical data, deep-learning supported text analysis and concept spaces to facilitate a visual discovery process. The tool is evaluated by five medical doctors. The results show that MediCoSpace facilitates a promising, yet complex way to discover unlikely relations and thus suggests a path toward the development of interactive visual tools to provide physicians with more holistic diagnoses and personalized, dynamic treatments for patients. Collapse

Topics: decision support knowledge base visual analytics knowledge representation healthcare data

Methods: qualitative interview qualitative content analysis exploratory data analysis ontological modelling usability testing

Managing AI is managing complexity - An interview with Rahul C. Basole

2022 | Electronic Markets | Citations: 0

Authors: Alt, Rainer

Abstract: ... Expand

Abstract: Collapse

Topics: artificial intelligence digital transformation digital twin visual analytics human centered design

Methods: exploratory data analysis design methodology

Predicting aspect-based sentiment using deep learning and information visualization: The impact of COVID-19 on the airline industry

2022 | Information & Management | Citations: 0

Authors: Chang, Yung-Chun; Ku, Chih-Hao; Nguyen, Duy-Duc Le

Abstract: This study investigates customer satisfaction through aspect-level sentiment ana ... Expand

Abstract: This study investigates customer satisfaction through aspect-level sentiment analysis and visual analytics. We collected and examined the flight reviews on TripAdvisor from January 2016 to August 2020 to gauge the impact of COVID-19 on passenger travel sentiment in several aspects. Till now, information systems, management, and tourism research have paid little attention to the use of deep learning and word embedding techniques, such as bidirectional encoder representations from transformers, especially for aspect-level sentiment analysis. This paper aims to identify perceived aspect-based sentiments and predict unrated sentiments for various categories to address this research gap. Ultimately, this study complements existing sentiment analysis methods and extends the use of data-driven and visual analytics approaches to better understand customer satisfaction in the airline industry and within the context of the COVID-19. Our proposed method outperforms baseline comparisons and therefore contributes to the theoretical and managerial literature. Collapse

Topics: pandemic customer satisfaction visual analytics cloud computing data visualization

Methods: BERT deep learning natural language processing exploratory data analysis sentiment analysis

Theories: construal level theory appraisal theory

THE LIFE CYCLE OF DATA LABELS IN ORGANIZATIONAL LEARNING: A CASE STUDY OF THE AUTOMOTIVE INDUSTRY

2022 | European Conference On Information Systems | Citations: 0

Authors: Eirich, Joscha; Fischer-Pressler, Diana

Abstract: Data labels are an integral input to develop machine learning (ML) models. In c ... Expand

Abstract: Data labels are an integral input to develop machine learning (ML) models. In complex domains, labels represent the externalized product of complex knowledge. While prior research discussed labels typically as input of ML models, we explore their role in organizational learning (OL). Based on a case study of a German car manufacturer, we contextualize a framework of OL to the use of labels in organizations informing about organizational members who work with labels, requirements of labelbased tools, label-related tasks, and impediments of label-related task performance. From our findings, we derive propositions about the role of labels in OL and outline future research opportunities. Our results inform theory about the role of labels in OL and can guide practitioners leveraging labels to create and transfer knowledge within organizations. Collapse

Topics: task productivity explicit knowledge organization learning knowledge sharing intrinsic motivation

Methods: case study qualitative interview random forest classification decision tree classification business process modeling

Theories: sociotechnical systems theory

Visualizing the Maturing Global API Ecosystem

2022 | HICSS | Citations: 1

Authors: Heshmatisafa, Saeid; Huhtamäki, Jukka; Seppänen, Marko

Abstract: Platform boundary resources are prominent digital strategy tools for companies t ... Expand

Abstract: Platform boundary resources are prominent digital strategy tools for companies to disclose business assets to partners and consumers. However, the platform boundary resources of API ecosystems are dependent on API usage and characteristics as well as the social environment around them. This study focuses on the global API ecosystem guided by two assumptions: 1) geographic proximity is distorted, and the global API ecosystem is decentralized in a digitally connected world, and 2) open co-innovation is somewhat prone to geographic nearness and centralized. A data-driven network analysis was utilized to depict the global and regional geolocation of more than 22,000 APIs and 6,000 mashups. First, the global locations of API providers were examined. Next, the connectivity of API mashups at global and regional levels was studied. The findings suggest that APIs are distributed globally, and the API ecosystem has moved from emerging to mature; however, the distribution is skewed towards entrepreneurial regions in North America. Finally, the theoretical and managerial implications are discussed. Collapse

Topics: application programming interface Python productivity missing data Tableau software

Methods: computational algorithm exploratory data analysis cluster analysis network analysis