Search

This article discusses the need for artificial intelligence (AI) practitioners to shift their focus from a purely technical mindset toward a more human-centered approach. Technical experts are trained to consider the technical aspects of their work, which can cause them to overlook important socio–technical considerations and implications, resulting in a socio–technical gap in AI-based systems. Unhelpful practitioner cultures can lead to them “rejecting practices or downplaying the importance of values or the possible threats of ignoring them”. While efforts are being made to create ethical and more human-centered AI systems, there is a need for corresponding changes in the attitudes and perceptions of AI practitioners. Practitioners need to move away from a sole focus on compliance with responsible AI guidelines and regulations toward active reflection and empathy based on a true understanding of the profound effects their decisions can have on different stakeholders. However, one problematic barrier to beginning work on interventions that target practitioners’ mindsets and attitudes is the lack of a standardized method for evaluating or measuring the effectiveness of design interventions on their attitudes and perceptions. This article suggests the need for clearer metrics within the human–computer interaction (HCI) community for looking at practitioners’ attitudes toward socio–technical factors in AI design. [ABSTRACT FROM AUTHOR]

BackgroundMobile health (mHealth) apps offer a scalable option for treating sleep disturbances at a population level. However, there is a lack of clarity about the development and evaluation of evidence-based mHealth apps. ObjectiveThe aim of this systematic review was to provide evidence for the design engineering and clinical implementation and evaluation of mHealth apps for sleep disturbance. MethodsA systematic search of studies published from the inception of databases through February 2020 was conducted using 5 databases (MEDLINE, Embase, Cochrane Library, PsycINFO, and CINAHL). ResultsA total of 6015 papers were identified using the search strategy. After screening, 15 papers were identified that examined the design engineering and clinical implementation and evaluation of 8 different mHealth apps for sleep disturbance. Most of these apps delivered cognitive behavioral therapy for insomnia (CBT-I, n=4) or modified CBT-I (n=2). Half of the apps (n=4) identified adopting user-centered design or multidisciplinary teams in their design approach. Only 3 papers described user and data privacy. End-user acceptability and engagement were the most frequently assessed implementation metrics. Only 1 app had available evidence assessing all 4 implementation metrics (ie, acceptability, engagement, usability, and adherence). Most apps were prototype versions (n=5), with few matured apps. A total of 6 apps had supporting papers that provided a quantitative evaluation of clinical outcomes, but only 1 app had a supporting, adequately powered randomized controlled trial. ConclusionsThis is the first systematic review to synthesize and examine evidence for the design engineering and clinical implementation and evaluation of mHealth apps for sleep disturbance. The minimal number of apps with published evidence for design engineering and clinical implementation and evaluation contrasts starkly with the number of commercial sleep apps available. Moreover, there appears to be no standardization and consistency in the use of best practice design approaches and implementation assessments, along with very few rigorous efficacy evaluations. To facilitate the development of successful and evidence-based apps for sleep disturbance, we developed a high-level framework to guide researchers and app developers in the end-to-end process of app development and evaluation.

BackgroundDecisions of whether to disclose mental health conditions are extremely personal and require the consideration of multiple factors associated with the disclosure process (eg, weighing the risks and benefits). Decision aid tools help people make these complex decisions. Such an aid needs to be confidential, easily accessible, and easy to use with the potential to access the tool on multiple occasions. Web programs are well suited to meet these requirements and, if properly developed, can provide feasible, accessible, affordable, and effective workplace interventions. ObjectiveThis study aims to gain insights from potential end users, in this case both employees and organizations, into what type of components including language, style, and content would avoid potential stigma and ensure that elements of clear value for users would be built into a web-based decision aid tool that aims to assist employees in making decisions about the disclosure of their mental health condition at work. MethodsA participatory design approach was used to allow developers, researchers, experts, and end users to collaborate in co-designing the tool. During the user research phase of the development of the web-based tool, a participatory design workshop approach was selected as a part of a larger study of focus groups. Australian employees and managers in rural, suburban, and urban locations participated in an exploratory qualitative study involving participatory workshops designed to elicit their perspectives and preferences for a decision aid tool. ResultsA total of 2 workshops were conducted with 13 participants. The majority were from a transport company (9/13, 69%), male (8/13, 62%), and employed full time (11/13, 85%). Six employees had previous experience disclosing their own mental health condition, and 7 were in a supervisory role and had previously been disclosed to. In any co-design development, there are certain trade-offs that need to be made between the views of experts, developers, end users, and the available budget. In this specific instance of a very delicate, personal decision, the end users provided valuable design insights into key areas such as language, and they were very antipathetic to a key feature, the avatar, which was thought to be desirable by experts and developers. Findings including aspects of the tool where all stakeholders were in agreement, aspects where some stakeholders disagreed and adaptations were implemented, where disagreements could not be implemented because of financial constraints, and misalignment between stakeholders and how to decide on a balance were shared. ConclusionsThe co-design with a lived experience approach is useful for contributing much to the design, language, and features. The key in this study was balancing the needs of the workers and the potential impact for the managers and organizations, while ensuring legislation and regulation requirements were upheld.

BackgroundThe workplace represents a unique setting for mental health interventions. Due to range of job-related factors, employees in male-dominated industries are at an elevated risk. However, these at-risk groups are often overlooked. HeadGear is a smartphone app–based intervention designed to reduce depressive symptoms and increase well-being in these populations. ObjectiveThis paper presents the development and pilot testing of the app’s usability, acceptability, feasibility, and preliminary effectiveness. MethodsThe development process took place from January 2016 to August 2017. Participants for prototype testing (n=21; stage 1) were recruited from industry partner organizations to assess acceptability and utility. A 5-week effectiveness and feasibility pilot study (n=84; stage 2) was then undertaken, utilizing social media recruitment. Demographic data, acceptability and utility questionnaires, depression (Patient Health Questionnaire-9), and other mental health measures were collected. ResultsThe majority of respondents felt HeadGear was easy to use (92%), easily understood (92%), were satisfied with the app (67%), and would recommend it to a friend (75%; stage 1). Stage 2 found that compared with baseline, depression and anxiety symptoms were significantly lower at follow-up (t30=2.53; P=.02 and t30=2.18; P=.04, respectively), days of sick leave in past month (t28=2.38; P=.02), and higher self-reported job performance (t28=−2.09; P=.046; stage 2). Over 90% of respondents claimed it helped improve their mental fitness, and user feedback was again positive. Attrition was high across the stages. ConclusionsOverall, HeadGear was well received, and preliminary findings indicate it may provide an innovative new platform for improving mental health outcomes. Unfortunately, attrition was a significant issue, and findings should be interpreted with caution. The next stage of evaluation will be a randomized controlled trial. If found to be efficacious, the app has the potential to reduce disease burden and improve health in this at-risk group.

Engagement is critical to the success of learning activities such as writing, and can be promoted with appropriate feedback. Current engagement measures rely mostly on data collected by observers or self-reported by the participants. In this paper, we describe a learning analytic system called Tracer, which derives behavioral engagement measures and creates visualizations of behavioral patterns of students writing on a cloud-based application. The tool records the intermediate stages of document development and uses this data to measure learners' behavioral engagement and derive three visualizations. Writers (N = 23 University students) participated in a controlled one-hour writing session in which they post-facto self-reported their level of behavioral engagement. Results show that the level of behavioral engagement automatically estimated by the system correlates with the level reported by the participants. Additionally, users stated that the visualizations were coherent with their writing activity and were useful to help them reflect on the writing process.

Critical review skill is one important aspect of academic writing. Generic trigger questions have been widely used to support this activity. When students have a concrete topic in mind, trigger questions are less effective if they are too general. This article presents a learning-to-rank based system which automatically generates specific trigger questions from citations for critical review support. The performance of the proposed question ranking models was evaluated and the quality of generated questions is reported. Experimental results showed an accuracy of 75.8% on the top 25% ranked questions. These top ranked questions are as useful for self-reflection as questions generated by human tutors and supervisors. A qualitative analysis was also conducted using an information seeking question taxonomy in order to further analyze the questions generated by humans. The analysis revealed that explanation and association questions are the most frequent question types and that the explanation questions are considered the most valuables by student writers.

Writing assignments are ubiquitous in higher education. Writing develops not only communication skills, but also higher-level cognitive processes that facilitate deep learning. Cognitive visualizations, such as concept maps, can also be used as part of learning activities including as a form of scaffolding, or to trigger reflection by making conceptual understanding visible at different stages of the learning process. We present Concept Map Miner (CMM), a tool that automatically generates Concept Maps from students' compositions, and discuss its design and implementation, its integration to a writing support environment and its evaluation on a manually annotated corpora of university essays (N=43). Results show that complete CM, with concepts and labeled relationships, are possible and its precision depends the level of summarization (number of concepts) chosen. (Contains 5 figures.)

Visualizing how the parts of a document relate to each other and producing automatically generated quality measures that people can understand are means that writers can use to improve the quality of their compositions. This paper presents a novel document visualization technique and a measure of quality based on the average semantic distance between parts of a document. We show how the visualization helps tutors mark essays more efficiently and reliably, and how a distance index calculated for the visualizations correlates with grades. The technique is further evaluated using three dimensionality reduction techniques. The results provide evidence that the degree of topic flow between consecutive sentences and paragraphs is related to essay quality. (Contains 3 figures and 5 tables.)

This study describes a set of institutional indicators that suggest minimum standards for the quality assurance of learning supported by learning management systems in blended contexts. The indicators are evaluated by comparing seven universities that use a common learning management system to support student learning experiences. The responses to a qualitative questionnaire provide evidence of how the participating universities approach leadership, policy making, development, and evaluation as they relate to the quality assurance of learning management systems. A comparison among the universities reveals that they tend to have a better understanding of technical rather than educational issues related to quality assurance. A case is made for the need for universities to address key areas in order to reliably assure the quality of learning supported by learning management systems. (Contains 4 tables.)

Purpose: The purpose of this paper is to describe Beehive, a new web application framework for designing and supporting synchronous collaborative learning. Design/methodology/approach: Our web engineering approach integrates educational design expertise into a technology for building tools for collaborative learning activities. Beehive simplifies the development of the collaboration tools required to implement proven educational design strategies. The methodology consists of a framework model that has three abstraction layers: pedagogical techniques, patterns, and computer supported collaborative learning components. Findings: Building eLearning systems that are informed by the educational research in design patterns, can lead to a better, richer and more flexible, infrastructure. Beehive's design enables teachers to design and use synchronous collaborative learning activities, either by using well tested research-based learning designs or by creating their own. Research limitations/implications: The system will need to be used by a large number of teachers and learners before evaluation and usability tests are possible. Originality/value: The paper presents an integrated solution application that enables teachers and students to design and carry out synchronous collaborative learning activities in a very simple manner. (Contains 1 table and 4 figures.)

Longhorn beetles are often categorized as diurnal, crepuscular or nocturnal depending on the diel (day-night) time window at which adults are active. A precise knowledge of the diel activity pattern in these species is essential to understand the selective forces involved in, and the adaptations resulting from, the evolution of circadian rhythms. The genus Cerambyx includes both diurnal and crepuscular/nocturnal species. In the case of Cerambyx miles Bonelli, 1812, a usually scarce and localised species, diel activity remains poorly understood. While for some authors this longhorn is diurnal, for others it is crepuscular/nocturnal. In order to resolve this historical discrepancy, we studied the diel activity of C. miles in the wild in 2020 and 2021 using ad hoc devised phototraps (with and without capture) and we examine to what extent our field results conformed to literature. Our data (n = 139 captures/sightings) show that about 94% of the activity of C. miles is diurnal, 5% crepuscular, and less than 1% nocturnal. Diel activity started at dawn, raised progressively during the morning, peaked in the late afternoon (17.00-20.00 h) and declined abruptly just before dusk. Our field results were not consistent with literature data (n = 103 diel activity records retrieved from 79 references), in which diel activity was scored as 60% diurnal, 26% crepuscular and 14% nocturnal. We argue possible causes involved in the literature bias and we discuss the diel activity of C. miles from a behavioural, ecological and evolutionary perspective. [ABSTRACT FROM AUTHOR]