List of Titles

An exploratory application of machine learning methods to optimize prediction of responsiveness to digital interventions for eating disorder symptoms

- Linardon, Jake, Fuller-Tyszkiewicz, Matthew, Shatte, Adrian, Greenwood, Christopher

Authors: Linardon, Jake , Fuller-Tyszkiewicz, Matthew , Shatte, Adrian , Greenwood, Christopher
Date: 2022
Type: Text , Journal article
Relation: International Journal of Eating Disorders Vol. 55, no. 6 (2022), p. 845-850
Full Text:
Reviewed:
Description: Objective: Digital interventions show promise to address eating disorder (ED) symptoms. However, response rates are variable, and the ability to predict responsiveness to digital interventions has been poor. We tested whether machine learning (ML) techniques can enhance outcome predictions from digital interventions for ED symptoms. Method: Data were aggregated from three RCTs (n = 826) of self-guided digital interventions for EDs. Predictive models were developed for four key outcomes: uptake, adherence, drop-out, and symptom-level change. Seven ML techniques for classification were tested and compared against the generalized linear model (GLM). Results: The seven ML methods used to predict outcomes from 36 baseline variables were poor for the three engagement outcomes (AUCs = 0.48–0.52), but adequate for symptom-level change (R2 =.15–.40). ML did not offer an added benefit to the GLM. Incorporating intervention usage pattern data improved ML prediction accuracy for drop-out (AUC = 0.75–0.93) and adherence (AUC = 0.92–0.99). Age, motivation, symptom severity, and anxiety emerged as influential outcome predictors. Conclusion: A limited set of routinely measured baseline variables was not sufficient to detect a performance benefit of ML over traditional approaches. The benefits of ML may emerge when numerous usage pattern variables are modeled, although this validation in larger datasets before stronger conclusions can be made. © 2022 The Authors. International Journal of Eating Disorders published by Wiley Periodicals LLC.

Quick View

Digital tax administration: transforming the workforce to deliver

- Bentley, Duncan

Authors: Bentley, Duncan
Date: 2020
Type: Text , Journal article
Relation: eJournal of Tax Research Vol. 18, no. 2 (2020), p. 353-381
Full Text:
Reviewed:
Description: This article provides the global context for digital tax administration and the radical change to the administration workforce. It examines the knowledge, skills, and capabilities to implement digital taxation and identifies the importance of a holistic workforce strategy. The article examines the elements of a data-driven human resource management strategy required to shape and develop an appropriate workforce. It shows that this ranges from revision of classification and role definition to comprehensive training. The article identifies the characteristics of an effective training system and the range of appropriate delivery methods to support strategy implementation. The article demonstrates that, as all tax administrations transform, the effectiveness of that transformation to digital delivery depends on developing a workforce with the right skillset. It shows that despite the competition for skills, a carefully planned and implemented strategy can build depth of capability appropriate to the jurisdiction and its state of development. © 2020. All Rights Reserved.

Taxpayer rights and protections in a digital global environment

- Bentley, Duncan

Authors: Bentley, Duncan
Date: 2019
Type: Text , Book chapter
Relation: Ethics and Taxation p. 251-294
Full Text: false
Reviewed:
Description: This chapter explores the impact on taxpayer rights of digital developments in electronics and systems, artificial intelligence, and security.Using an integrated rights framework comprising principles of tax administration and compliance, together with legal rights, it sets out the challenges and opportunities offered by digital disruption. It addresses issues such as proportionality, discrimination, equity and fairness, transparency and bias in legal and administrative decision-making, security, privacy and confidentiality. The chapter takes a global and comparative perspective in addressing significant legal issues that require detailed research and debate. It emphasises the opportunities for government service obligations to taxpayers, using artificial intelligence and secure systems, to provide advanced assistance to taxpayers and businesses and boost economic growth and trade. The chapter concludes that the opportunities are available to enable global implementation of an integrated rights framework to protect taxpayers even more effectively through digital disruption. © Springer Nature Singapore Pte Ltd. 2020.

Nagging, noobs and new tricks - students' perceptions of school as a context for digital technology use

- Bulfin, Scott, Johnson, Nicola, Nemorin, Selena, Selwyn, Neil

Authors: Bulfin, Scott , Johnson, Nicola , Nemorin, Selena , Selwyn, Neil
Date: 2016
Type: Text , Journal article
Relation: Educational Studies Vol. 42, no. 3 (Jul 2016), p. 239-251
Full Text: false
Reviewed:
Description: While digital technology is an integral feature of contemporary education, schools are often presumed to constrain and compromise students' uses of technology. This paper investigates students' experiences of school as a context for digital technology use. Drawing upon survey data from three Australian secondary schools (n=1174), this paper considers the various ways in which students use digital devices and applications in school and for school. After highlighting trends and differences across a range of digital devices and practices, the paper explores the ways in which students perceive school as a limiting and/or enabling setting for technology use. The findings point to a number of ways that schools act to extend as well as curtail student engagement with technology. This paper concludes by considering the possible ways that schools might work to further support and/or enhance students' technology experiences.

Quick View

Collaboration success in the dataverse : Libraries as digital humanities research partners

- Owen, Sue, Verhoeven, Deb, Horn, Anne, Robertson, Sabina

Authors: Owen, Sue , Verhoeven, Deb , Horn, Anne , Robertson, Sabina
Date: 2014
Type: Text , Conference proceedings , Conference paper
Relation: 35th International Association of Scientific and Technological University Libraries Conference (IATUL 2014); Espoo, Finland; 2nd-5th June 2014 p. 1-9
Full Text:
Reviewed:
Description: At Deakin, the Humanities Networked Infrastructure project (HuNI), has paved new ground for facilitating the effective use and re-use of humanities research data. HuNI is one of the first largescale eResearch infrastructure projects for the humanities in Australia and the first national, crossdisciplinary Virtual Laboratory (VL) worldwide. HuNI provides new information infrastructure services for both humanities researchers and members of the public. Its development has been funded by the National eResearch Collaboration Tools and Resources project (NeCTAR) and undertaken by a consortium of thirteen institutions led by Deakin University. A Deakin University Library team with skills in data description, curation, retrieval and preservation is exploring with digital humanities researchers and developers effective means to support and maintain the HuNI project. HuNI ingests and aggregates data from a total of 31 different Australian cultural datasets which cover a wide range of disciplines in the humanities and creative arts. The HuNI VL also provides a number of online research capabilities for humanities researchers to discover and work with the large-scale aggregation of data. The HuNI VL enables researchers to create, save and publish selections of data; to analyse and manipulate the data; share findings and to export the data for reuse in external environments. In a major innovation, HuNI also enables researchers to assert relationships between entities in the form of ‘socially linked’ data. This capability contributes to the building of a ‘vernacular’ network of associations between HuNI records that embody diverse perspectives on knowledge and ramify avenues for research discovery beyond keyword and phrase searches. This paper reports on key milestones in this project, the future role of Libraries as digital humanities research partners and the challenges and sustainability issues that face national digital humanities research projects that are developed in strategic library settings.

Left to their own devices : The everyday realities of one-to-one classrooms

- Selwyn, Neil, Nemorin, Selena, Bulfin, Scott, Johnson, Nicola

Authors: Selwyn, Neil , Nemorin, Selena , Bulfin, Scott , Johnson, Nicola
Date: 2017
Type: Text , Journal article
Relation: Oxford Review of Education Vol. 43, no. 3 (2017), p. 289-310
Full Text: false
Reviewed:
Description: The past decade has seen the expansion of personal digital technologies into schools. With many students and teachers now possessing smartphones, tablets, and laptops, schools are initiating one-to-one and ‘Bring Your Own Device’ (BYOD) policies aiming to make use of these ‘personal devices’ in classrooms. While often discussed in terms of possible educational benefits and/or organisational risks, the actual presence of personal devices in schools tends to be more mundane in nature and effect. Drawing upon ethnographic studies of three Australian high schools, this paper details ways in which the proliferation of digital devices has come to bear upon everyday experiences of school. In particular, the paper highlights the ways in which staff and students negotiate (in)appropriate technology engagement; the ordinary (rather than extraordinary) ways that students make use of their devices in classrooms; and the device-related tensions now beginning to arise in schools. Rather than constituting a radically ‘transformational’ form of schooling, the paper considers how the heightened presence of personal technologies is becoming subsumed into existing micro-politics of school organisation and control. © 2017 Informa UK Limited, trading as Taylor & Francis Group.

Showing items 1 - 8 of 8