WLA4ND: a Wearable Dataset of Learning Activities for Young Adults with Neurodiversity to Provide Support in Education

Zheng, Hui; Mahapasuthanon, Pattiya; Chen, Yujing; Rangwala, Huzefa; Evmenova, Anya S.; Motti, Vivian Genaro

doi:10.1145/3441852.3471220

Cited by 5 publications

(6 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Reported. The categories we found delineating racial composition were mostly 'White' and 'Black' [144], with variations of reporting them as 'White-Caucasian' or 'Caucasian' and 'African-American' [160,182,191]. For other racial groups, data were ambiguously grouped together (e.g., "62% Caucasian, 30% African-American and 10% other" [160]) or can be extrapolated by subtracting what was reported as the proportion of the 'white' category only [190].…”

Section: What Ismentioning

confidence: 87%

See 1 more Smart Citation

Data Representativeness in Accessibility Datasets: A Meta-Analysis

Kamikubo,

Wang,

Marte

et al. 2022

Preprint

View full text Add to dashboard Cite

As data-driven systems are increasingly deployed at scale, ethical concerns have arisen around unfair and discriminatory outcomes for historically marginalized groups that are underrepresented in training data. In response, work around AI fairness and inclusion has called for datasets that are representative of various demographic groups. In this paper, we contribute an analysis of the representativeness of age, gender, and race & ethnicity in accessibility datasets-datasets sourced from people with disabilities and older adults-that can potentially play an important role in mitigating bias for inclusive AI-infused applications. We examine the current state of representation within datasets sourced by people with disabilities by reviewing publicly-available information of 190 datasets, we call these accessibility datasets. We find that accessibility datasets represent diverse ages, but have gender and race representation gaps. Additionally, we investigate how the sensitive and complex nature of demographic variables makes classification difficult and inconsistent (e.g., gender, race & ethnicity), with the source of labeling often unknown. By reflecting on the current challenges and opportunities for representation of disabled data contributors, we hope our effort expands the space of possibility for greater inclusion of marginalized communities in AI-infused systems.

show abstract

Section: What Ismentioning

confidence: 87%

“…Thus, we could not verify the source of classifications (such as for gender). Few datasets explicitly documented that the reported information was e.g., "according to self-reports" [191].…”

Section: Reflections On Limitationsmentioning

confidence: 99%

Data Representativeness in Accessibility Datasets: A Meta-Analysis

Kamikubo,

Wang,

Marte

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The most specific is the coincidence of the three impairments: IDD, speech, and orientation, which are the main topic of the research by Caro et al [75]. Moreover, neurodiversity [80] is closely related to cognitive, cognitive, and motor impairment. In total, one-third of all the selected papers cover several symptoms in parallel, proving that they should never be treated in isolation.…”

Section: Theme 1: Variety Of Disabilitiesmentioning

confidence: 99%

“…Another group of researchers conducted relevant work to study persons having complex communicative needs by implementing aided augmented communication systems [72]. Finally, neurodiversity conditions with variations in the abilities of individuals in cognitive, motor, and communications skills are addressed [80].…”

Section: Theme 1: Variety Of Disabilitiesmentioning

confidence: 99%

“…The selected 24 papers propose a wide variety of different inclusiveness approaches, including the augmented tabletop game for children with cognitive disabilities [67], the authoring system for personalized sensory stimulation [65], virtual reality and robots [25], eye-hand coordination and a pre-literacy skills [75] digital whiteboard interface that support DS students learn addition and subtraction [61], beacon technology that supports DS persons on orientation tasks [27], and data-driven wearable smartwatch sensors [80]. These were mainly used in regular schools by children with different disabilities, including Down syndrome, as well as by their mates with no disabilities.…”

Section: Theme 4: Variety Of Inclusiveness Approachmentioning

confidence: 99%

See 1 more Smart Citation

Impact of Assistive Technologies to Inclusive Education and Independent Life of Down Syndrome Persons: A Systematic Literature Review and Research Agenda

2022

View full text Add to dashboard Cite

Since the beginning of the 21st century, the lifespan of people born with Down syndrome (DS) has increased. They now outlive their parents and rely on their relatives who usually sacrifice their own families to care for their disabled siblings. To reduce the pressure on families and the wider community, it is crucial to prepare DS people for independent life from early childhood. Emerging technologies can significantly support the process of acquiring the skills that are necessary for solving real-life problems at home and work. To assess their impact and estimate how much they are implemented in inclusive education, a review of 564 papers published after 2015 was done using the PRISMA review model. After gradual exclusion, 24 papers were used for the final review. Thematic analysis resulted in four themes with one common concept: variety. The results of examining the four research questions defined in the paper’s background confirm that the synergy of emerging assistive technologies and inclusive education has the potential of becoming a very effective strategy for creating an independent life for DS individuals. Many questions remain open, mainly related to a DS persons’ specific needs and capabilities. The acceptance of the proposed synergy will depend on them.

show abstract