Search for: All records

Video-sharing platforms offer a unique avenue for people with disabilities (PWDs) to highlight their experiences, including the challenges and accessibility barriers they face. While creators with disabilities effectively use these platforms to share their life struggles and advocate for societal changes, the scope of research exploring the nature of the discourse activities related to disability challenges remains limited. Our study addresses this gap by conducting a comprehensive qualitative content analysis of 468 videos posted by YouTubers with a range of disabilities, including vision, speech, mobility, hearing, and cognitive and neural impairments. Our findings reveal a predominant discussion on stigma and lack of support. YouTube is also used to share difficulties related to communication and systemic problems. Creators with disabilities also share experiences with technologies and public and private environments, through which they discuss accessibility issues and solutions. Building on our analysis, we propose future research directions aimed at enhancing the experience and support for disability communities on video-sharing platforms. 

This paper explores the application of sensemaking theory to support non-expert crowds in intricate data annotation tasks. We investigate the influence of procedural context and data context on the annotation quality of novice crowds, defining procedural context as completing multiple related annotation tasks on the same data point, and data context as annotating multiple data points with semantic relevance. We conducted a controlled experiment involving 140 non-expert crowd workers, who generated 1400 event annotations across various procedural and data context levels. Assessments of annotations demonstrate that high procedural context positively impacts annotation quality, although this effect diminishes with lower data context. Notably, assigning multiple related tasks to novice annotators yields comparable quality to expert annotations, without costing additional time or effort. We discuss the trade-offs associated with procedural and data contexts and draw design implications for engaging non-experts in crowdsourcing complex annotation tasks. 

Interactive dimensionality reduction helps analysts explore the high dimensional data based on their personal needs and domain-specific problems. Recently, expressive nonlinear models are employed to support these tasks. However, the interpretation of these human steered nonlinear models during human-in-the-loop analysis has not been explored. To address this problem, we present a new visual explanation design called semantic explanation. Semantic explanation visualizes model behaviors in a manner that is similar to users’ direct projection manipulations. This design conforms to the spatial analytic process and enables analysts better understand the updated model in response to their interactions. We propose a pipeline to empower interactive dimensionality reduction with semantic explanation using counterfactuals. Based on the pipeline, we implement a visual text analytics system with nonlinear dimensionality reduction powered by deep learning via the BERT model. We demonstrate the efficacy of semantic explanation with two case studies of academic article exploration and intelligence analysis. 

In this paper, we design novel interactive deep learning methods to improve semantic interactions in visual analytics applications. The ability of semantic interaction to infer analysts’ precise intents during sensemaking is dependent on the quality of the underlying data representation. We propose the DeepSIfinetune framework that integrates deep learning into the human-in-the-loop interactive sensemaking pipeline, with two important properties. First, deep learning extracts meaningful representations from raw data, which improves semantic interaction inference. Second, semantic interactions are exploited to fine-tune the deep learning representations, which then further improves semantic interaction inference. This feedback loop between human interaction and deep learning enables efficient learning of user- and task-specific representations. To evaluate the advantage of embedding the deep learning within the semantic interaction loop, we compare DeepSIfinetune against a state-of-the-art but more basic use of deep learning as only a feature extractor pre-processed outside of the interactive loop. Results of two complementary studies, a human-centered qualitative case study and an algorithm-centered simulation-based quantitative experiment, show that DeepSIfinetune more accurately captures users’ complex mental models with fewer interactions.