Human-data Interaction Research Articles

Human-Data Interaction as a critical enabler of Electronic Performance Monitoring at construction sites

Human-Data Interaction (HDI) revolves around how humans generate, process, and utilise data. HDI plays a crucial role in evaluating data collection and use in the context of the construction industry, considering the impact on stakeholders such as site managers and labourers. One significant application of HDI is in on-site Electronic Performance Monitoring (EPM), which aims to leverage workplace innovations to enhance productivity, safety, and health. However, the integration and implications of HDI and EPM lack comprehensive understanding. This research seeks to bridge this knowledge gap by presenting a human-data perspective on sensored construction sites, emphasising the challenges and opportunities for driving innovative EPM initiatives. Through a combination of literature review, surveys with HDI experts, and the authors' perspectives and abduction, conceptual frameworks are developed that cluster HDI and EPM. The study's implications are multifaceted, impacting both theoretical understanding and practical applications. The findings highlight the key actors and the data they generate and manipulate across different platforms during EPM deployment. Through the lens of explanatory theories, sociomateriality, and work sociology, the research contributes to understanding the fragmented nature of HDI and EPM as a managerial issue embedded in the work environment. It sheds light on the interactions of actors using digital EPM devices and relevant data streams influenced by the limited agency of specific stakeholders, such as labourers, and the potential neglect of factors related to their well-being. This research distinguishes itself by focusing on the less explored intersection of HDI and EPM in the construction industry. It offers a novel perspective by considering the sensored environment of construction sites as a venue for analysing human-data interactions.

Adopting Human-data Interaction Guidelines and Participatory Practices for Supporting Inexperienced Designers in Information Visualization Applications

Nowadays, voluminous data support may influence decision-making. People with varied profiles need to interact with data to gain valuable insights. There is a need for software tools to support the understanding and management of information to favor Human-Data Interaction (HDI) with a richer user experience. This study explores the combination of HDI design guidelines and participatory approaches to improve user experience in data interaction. We defined a design process to support the activities and adapted participatory practices to facilitate HDI design. We conducted workshops with inexperienced designers developing information visualization applications for common-sense domains. They generated and analyzed several application prototypes. Results suggest that design guidelines help generate HDI-based prototypes with a good user experience.

‘Making you Aware of your Own Breathing’: Human Data Interaction, Disadvantage and Skills in the Community

‘Making you Aware of your Own Breathing’: Human Data Interaction, Disadvantage and Skills in the Community

Review of Sarah Hayes, Michael Jopling, Stuart Connor, and Matthew Johnson (Eds.). (2023). Human Data Interaction, Disadvantage and Skills in the Community: Enabling Cross-Sector Environments for Postdigital Inclusion

Review of Sarah Hayes, Michael Jopling, Stuart Connor, and Matthew Johnson (Eds.). (2023). Human Data Interaction, Disadvantage and Skills in the Community: Enabling Cross-Sector Environments for Postdigital Inclusion

Human-Data Interaction Syllabus for Undergraduate and Graduate Courses

The phenomenon of the data deluge is a reality and the volume of data produced by people and companies is much greater than what can be handled and analyzed. Data play a crucial role in guiding the efficient utilization of technological resources for companies, aiding them in product and service management. Moreover, individuals who have become adept data producers and consumers are increasingly orienting their lives toward data. To address this evolving trend, there is a growing imperative to educate Computing professionals. These professionals are required to design technology solutions that facilitate the synergy between individuals and data, a phenomenon known as Human-Data Interaction (HDI). This paper introduces a suggested minimum syllabus for HDI courses, with the aim of addressing the key themes associated with the interaction between individuals and data. The complexity and depth of HDI topics justify a dedicated course, preventing the risk of essential content being fragmented or inadequately covered if dispersed across different courses.

Promoting data use through understanding user behaviors: A model for human open government data interaction

AbstractRecent dramatic increases in the ability to generate, collect, and use datasets have inspired numerous academic and policy discussions regarding the emerging field of human data interaction (HDI). Given the challenges in interacting with open government data (OGD) and the existing research gap in this field, our study intends to explore HDI in the OGD domain and investigate ways HDI can further contribute to OGD promotion. Building upon two existing behavioral models, we proposed an initial conceptual model for OGD interaction, then using this model, conducted two studies to empirically examine users' behaviors when interacting with OGD. Ultimately, we refined this model for OGD interaction and invited three experts to validate it to enhance its understandability, comprehensiveness, and reasonableness. This comprehensive model for human OGD interaction will contribute to the theoretical work of the HDI field as well as the practical design of OGD platforms and data literacy education.

Exploring Human-Data Interaction in Clinical Decision-making Using Scenarios: Co-design Study.

BackgroundWhen caring for patients with chronic conditions such as chronic obstructive pulmonary disease (COPD), health care professionals (HCPs) rely on multiple data sources to make decisions. Collating and visualizing these data, for example, on clinical dashboards, holds the potential to support timely and informed decision-making. Most studies on data-supported decision-making (DSDM) technologies for health care have focused on their technical feasibility or quantitative effectiveness. Although these studies are an important contribution to the literature, they do not further our limited understanding of how HCPs engage with these technologies and how they can be designed to support specific contexts of use. To advance our knowledge in this area, we must work with HCPs to explore this space and the real-world complexities of health care work and service structures.ObjectiveThis study aimed to qualitatively explore how DSDM technologies could support HCPs in their decision-making regarding COPD care. We created a scenario-based research tool called Respire, which visualizes HCPs’ data needs about their patients with COPD and services. We used Respire with HCPs to uncover rich and nuanced findings about human-data interaction in this context, focusing on the real-world challenges that HCPs face when carrying out their work and making decisions.MethodsWe engaged 9 respiratory HCPs from 2 collaborating health care organizations to design Respire. We then used Respire as a tool to investigate human-data interaction in the context of decision-making about COPD care. The study followed a co-design approach that had 3 stages and spanned 2 years. The first stage involved 5 workshops with HCPs to identify data interaction scenarios that would support their work. The second stage involved creating Respire, an interactive scenario-based web app that visualizes HCPs’ data needs, incorporating feedback from HCPs. The final stage involved 11 one-to-one sessions with HCPs to use Respire, focusing on how they envisaged that it could support their work and decisions about care.ResultsWe found that HCPs trust data differently depending on where it came from and who recorded it, sporadic and subjective data generated by patients have value but create challenges for decision-making, and HCPs require support in interpreting and responding to new data and its use cases.ConclusionsOur study uncovered important lessons for the design of DSDM technologies to support health care contexts. We show that although DSDM technologies have the potential to support patient care and health care delivery, important sociotechnical and human-data interaction challenges influence the design and deployment of these technologies. Exploring these considerations during the design process can ensure that DSDM technologies are designed with a holistic view of how decision-making and engagement with data occur in health care contexts.

Untidy Data: The Unreasonable Effectiveness of Tables.

Working with data in table form is usually considered a preparatory and tedious step in the sensemaking pipeline; a way of getting the data ready for more sophisticated visualization and analytical tools. But for many people, spreadsheets - the quintessential table tool - remain a critical part of their information ecosystem, allowing them to interact with their data in ways that are hidden or abstracted in more complex tools. This is particularly true for data workers [61], people who work with data as part of their job but do not identify as professional analysts or data scientists. We report on a qualitative study of how these workers interact with and reason about their data. Our findings show that data tables serve a broader purpose beyond data cleanup at the initial stage of a linear analytic flow: users want to see and "get their hands on" the underlying data throughout the analytics process, reshaping and augmenting it to support sensemaking. They reorganize, mark up, layer on levels of detail, and spawn alternatives within the context of the base data. These direct interactions and human-readable table representations form a rich and cognitively important part of building understanding of what the data mean and what they can do with it. We argue that interactive tables are an important visualization idiom in their own right; that the direct data interaction they afford offers a fertile design space for visual analytics; and that sense making can be enriched by more flexible human-data interaction than is currently supported in visual analytics tools.

Using Nominal Group Technique to Identify Key Ethical Concerns Regarding Hearing Aids With Machine Learning

Purpose: Machine learning (ML) in new-generation hearing aid technology presents a beneficial opportunity for development in audiology. It is, however, important to balance new applications against the audiologist's professional ethics to protect the client from any harm. This study aimed to identify the key ethical concerns related to the latest digital hearing aid technology that incorporates ML that could potentially impact the client and/or the audiologist. Method: A nominal group technique was conducted with the audiologist to generate and prioritize a list of key ethical concerns related to human data interaction, with specific focus on hearing aids. Results: Five categories were identified in relation to the potential impact on the client: (a) privacy and confidentiality, (b) relationship and trust, (c) nonmaleficence, (d) informed decision making, and (e) financial gain. An additional five categories were identified in relation to the potential impact on the audiologist: (a) privacy and confidentiality, (b) professional responsibility, (c) relationship and trust, (d) financial gain, and (e) trust technology. Privacy and confidentiality were ranked as the highest priority that should be considered when supplying clients with the latest hearing aid technology. Conclusions: Hearing aid technology has evolved considerably, and audiologists need to keep abreast of and master the general technological developments and the associated ethical challenges that may arise. Discussions on the ethics related to ML and hearing aid fittings will help identify the key ethical concerns involved and, thereby, enhance the ethical sensitivity of the profession.

VERONICA: Visual Analytics for Identifying Feature Groups in Disease Classification

The use of data analysis techniques in electronic health records (EHRs) offers great promise in improving predictive risk modeling. Although useful, these analysis techniques often suffer from a lack of interpretability and transparency, especially when the data is high-dimensional. The emergence of a type of computational system known as visual analytics has the potential to address these issues by integrating data analysis techniques with interactive visualizations. This paper introduces a visual analytics system called VERONICA that utilizes the natural classification of features in EHRs to identify the group of features with the strongest predictive power. VERONICA incorporates a representative set of supervised machine learning techniques—namely, classification and regression tree, C5.0, random forest, support vector machines, and naive Bayes to support users in developing predictive models using EHRs. It then makes the analytics results accessible through an interactive visual interface. By integrating different sampling strategies, analytics algorithms, visualization techniques, and human-data interaction, VERONICA assists users in comparing prediction models in a systematic way. To demonstrate the usefulness and utility of our proposed system, we use the clinical dataset stored at ICES to identify the best representative feature groups in detecting patients who are at high risk of developing acute kidney injury.

Data through Movement: Designing Embodied Human-Data Interaction for Informal Learning

Abstract When you picture human-data interactions (HDI), what comes to mind? The datafication of modern life, along with open data initiatives advocating for transparency and access to current and ...

Exploring Value Propositions to Drive Self-Sovereign Identity Adoption

This paper presents research exploring the balancing of interactive friction and value proposition in the context of Self-Sovereign Identity (SSI) technology adoption. This work extends a related investigation of a full agency engagement with a User-Centred Data Ecosystem utilising what is described as a Sovereign Boundary Mechanism (SBM). An SBM is a standardised collection of SSI interactions, which can collectively be described as a metaphorical ring of sovereignty between the participant and the wider network. Within this model participants control identity, relationships, credentials, data streams, and access control. This related work concludes that the developing trend poses significant interactive friction, and that clear and substantive value proposition would be required to drive and sustain participant adoption. This paper explores potential value propositions for SSI, considering theory relating to Privacy, Surveillance Capitalism, and Human Data Interaction; in parallel opinions are drawn from the thematic analysis of interviews with experts in the decentralised field and results from a public survey. This research concludes that the value proposition is unlikely to come from the direct perceived protection of privacy. Also, that the decentralised technologies cannot be marketed solely on the fact that it is decentralised. Instead, value will emerge from the capability of SSI functionality to supersede the centralised model, offering innovation and reduced transactional friction across individual, business and wider society. This research suggests that the SSI community needs to develop a cohesive design strategy, a clear narrative and vocabulary. Value needs to be defined across cultural context, while targeting accessible, high value niche opportunities to build momentum toward sustainable adoption.

Toward privacy-sensitive human–robot interaction: Privacy terms and human–data interaction in the personal robot era

Abstract Can we have personal robots without giving away personal data? Besides, what is the role of a robots Privacy Policy in that question? This work explores for the first time privacy in the context of consumer robotics through the lens of information communicated to users through Privacy Policies and Terms and Conditions. Privacy, personal and non-personal data are discussed under the light of the human–robot relationship, while we attempt to draw connections to dimensions related to personalization, trust, and transparency. We introduce a novel methodology to assess how the “Organization for Economic Cooperation and Development Guidelines Governing the Protection of Privacy and Trans-Border Flows of Personal Data” are reflected upon the publicly available Privacy Policies and Terms and Conditions in the consumer robotics field. We draw comparisons between the ways eight consumer robotic companies approach privacy principles. Current findings demonstrate significant deviations in the structure and context of privacy terms. Some practical dimensions in terms of improving the context and the format of privacy terms are discussed. The ultimate goal of this work is to raise awareness regarding the various privacy strategies used by robot companies while ultimately creating a usable way to make this information more relevant and accessible to users.

Multiple Regression Analysis and Frequent Itemset Mining of Electronic Medical Records: A Visual Analytics Approach Using VISA_M3R3

Medication-induced acute kidney injury (AKI) is a well-known problem in clinical medicine. This paper reports the first development of a visual analytics (VA) system that examines how different medications associate with AKI. In this paper, we introduce and describe VISA_M3R3, a VA system designed to assist healthcare researchers in identifying medications and medication combinations that associate with a higher risk of AKI using electronic medical records (EMRs). By integrating multiple regression models, frequent itemset mining, data visualization, and human-data interaction mechanisms, VISA_M3R3 allows users to explore complex relationships between medications and AKI in such a way that would be difficult or sometimes even impossible without the help of a VA system. Through an analysis of 595 medications using VISA_M3R3, we have identified 55 AKI-inducing medications, 24,212 frequent medication groups, and 78 medication groups that are associated with AKI. The purpose of this paper is to demonstrate the usefulness of VISA_M3R3 in the investigation of medication-induced AKI in particular and other clinical problems in general. Furthermore, this research highlights what needs to be considered in the future when designing VA systems that are intended to support gaining novel and deep insights into massive existing EMRs.

Issues and challenges of user and data interaction in healthcare-related IoT

PurposeThe Internet of Things (IoT), which enables smart objects to collect and exchange data, has a variety of application domains used in everyday life including healthcare. As a set of promising next-generation technologies in the healthcare domain, Healthcare-related Internet of Things (H-IoT) promises to facilitate better healthcare by offering data-driven insights. While effective in practice at large, emerging data concerns arise because of the inscrutable black-box systems. Inspired by the notion of human data interaction, this paper seeks to understand how people engage with the H-IoT data that is about and produced by themselves and to elucidate the main data issues and challenges involved in the development of H-IoT.Design/methodology/approachThis work conducted a comprehensive survey and integrated the method of content analysis by systematically review the recently published H-IoT research work in the healthcare domain.FindingsThis study thoroughly surveyed more than 300 research studies published in the last decades and classified seven H-IoT end-user groups, and three H-IoT data types that are important to H-IoT comprehension. Attention to human data interaction, our study also highlights several critical issues associated with this notion in the context of H-IoT.Originality/valueThis study will support H-IoT research by characterizing the data issues and challenges exist in the context of H-IoT user and data interaction. The findings will provide insights in designing for effective interactions with data in the H-IoT.

VARTTA: A Visual Analytics System for Making Sense of Real-Time Twitter Data

Through social media platforms, massive amounts of data are being produced. As a microblogging social media platform, Twitter enables its users to post short updates as “tweets” on an unprecedented scale. Once analyzed using machine learning (ML) techniques and in aggregate, Twitter data can be an invaluable resource for gaining insight into different domains of discussion and public opinion. However, when applied to real-time data streams, due to covariate shifts in the data (i.e., changes in the distributions of the inputs of ML algorithms), existing ML approaches result in different types of biases and provide uncertain outputs. In this paper, we describe VARTTA (Visual Analytics for Real-Time Twitter datA), a visual analytics system that combines data visualizations, human-data interaction, and ML algorithms to help users monitor, analyze, and make sense of the streams of tweets in a real-time manner. As a case study, we demonstrate the use of VARTTA in political discussions. VARTTA not only provides users with powerful analytical tools, but also enables them to diagnose and to heuristically suggest fixes for the errors in the outcome, resulting in a more detailed understanding of the tweets. Finally, we outline several issues to be considered while designing other similar visual analytics systems.

Ontologies as nested facet systems for human–data interaction

Ontologies as nested facet systems for human–data interaction

The Online Vaccine Debate: Study of a Visual Analytics System

Online debates, specifically the ones about public health issues (e.g., vaccines, medications, and nutrition), occur frequently and intensely, and are having an impact on our world. Many public health topics are debated online, one of which is the efficacy and morality of vaccines. When people examine such online debates, they encounter numerous and conflicting sources of information. This information forms the basis upon which people take a position on such debates. This has profound implications for public health. It necessitates a need for public health stakeholders to be able to examine online debates quickly and effectively. They should be able to easily perform sense-making tasks on the vast amount of online information, such as sentiments, online presence, focus, or geographic locations. In this paper, we report the results of a user study of a visual analytic system (VAS), and whether and how this VAS can help with such sense-making tasks. Specifically, we report a usability evaluation of VINCENT (VIsual aNalytiCs systEm for investigating the online vacciNe debaTe), a VAS previously described. To help the reader, we briefly discuss VINCENT’s design in this paper as well. VINCENT integrates webometrics, natural language processing, data visualization, and human-data interaction. In the reported study, we gave users tasks requiring them to make sense of the online vaccine debate. Thirty-four participants were asked to perform these tasks by investigating data from 37 vaccine-focused websites. Half the participants were given access to the system, while the other half were not. Selected study participants from both groups were subsequently asked to be interviewed by the study administrator. Examples of questions and issues discussed with interviewees were: how they went about completing specific tasks, what they meant by some of the feedback they provided, and how they would have performed on the tasks if they had been placed in the other group. Overall, we found that VINCENT was a highly valuable resource for users, helping them make sense of the online vaccine debate much more effectively and faster than those without the system (e.g., users were able to compare websites similarities, identify emotional tone of websites, and locate websites with a specific focus). In this paper, we also identify a few issues that should be taken into consideration when developing VASes for online public health debates.

Standardizing Social Justice in Digital Health

The bivalent nature of technology and its potential for adverse impacts are giving impetus to global efforts to ensure that the outcomes of technology are consistent with societal values and desired futures. Instruments such as legislation, standards, and ethical frameworks are being employed towards this end. This research investigates the domain of digital health, specifically health informatics, and asks the questions: What values should inform technical solutions in this domain? How can data justice, the infusing of social justice imperatives in data systems, be standardized in this domain? The paper presents findings from a review of data justice in health informatics supported by findings from a survey that explored key considerations for health data collection, processing, use, sharing, and exchange. The paper then presents the operationalization of the human data interaction framework through a health informatics system architecture to illustrate how the principles of legibility, agency, and negotiability can be standardized, mainstreamed, and embedded in health informatics.

Towards Adaptive Ontology Visualization — Predicting User Success from Behavioral Data

Ontology visualization plays an important role in human data interaction by offering clarity and insight for complex structured datasets. Recent usability studies of ontology visualization techniques have added to our understanding of desired features when assisting users in the interactive process. However, user behavioral data such as eye gaze and event logs have largely been used as indirect evidence to explain why a user may have carried out certain tasks in a controlled environment, as opposed to direct input that informs the underlying visualization system. Although findings from usability studies have contributed to the refinement of ontology visualizations as a whole, the visualization techniques themselves remain a one-size-fits-all approach, where all users are presented with the same visualizations and interactive features. By contrast, this paper investigates the feasibility of using behavioral data, such as user gaze and event logs, as real-time indicators of how appropriate or effective a given visualization may be for a specific user at a moment in time, which in turn may be used to inform the adaptation of the visualization to the user on the fly. To this end, we apply established predictive modeling techniques in Machine Learning to predict user success using gaze data and event logs. We present a detailed analysis from a controlled experiment and demonstrate such predictions are not only feasible, but can also be significantly better than a baseline classifier during visualization usage. These predictions can then be used to drive the adaptations of visual systems in providing ad hoc visualizations on a per user basis, which in turn may increase individual user success and performance. Furthermore, we demonstrate the prediction performance using several different feature sets, and report on the results generated from several notable classifiers, where a decision tree-based learning model using a boosting algorithm produced the best overall results.