Online discussions have become integral to how people exchange ideas, form opinions, and participate in collective deliberation. While sighted users can comfortably engage with online discussions, blind users who are dependent on screen readers are forced to listen to long threads narrated in a single, monotonic voice that lacks prosodic variation, rhythm, or emotion. This robotic auditory experience not only deteriorates the user engagement with the content but also increases cognitive strain, by making it difficult to remain attentive and discern meaning beyond literal words. In an interview study, most blind participants reported that monotonous narration hindered their ability to detect salient information, perceive emotional cues, and comprehend content authors’ intents in discussions. Many described experiencing mental fatigue when listening to ‘flat’, ‘uninspiring’ voices, noting that their attention tended to diminish quickly over time. The participants also indicated that they often tried to ‘add’ prosodic variation or emotional inflection themselves in their minds, but characterized this compensatory effort as mentally taxing and cognitively demanding. To address this issue, we introduce VoxVista, a multi-voice design framework driven by a large language model that leverages a custom voice-preference dataset to assign personalized voice profiles to user posts in discussions, thereby replacing the traditional monotone narration in screen readers with a more expressive, dynamic, and contextually-aware narration. In a study with 20 blind participants, we observed that VoxVista significantly improved user engagement, comprehension, and willingness to continue listening to longer discussions.

While online shopping platforms provide convenience and autonomy to blind users, their non-visual interactions remain underexplored at a micro-behavioral level. Existing studies have primarily emphasized accessibility and usability challenges but have overlooked how fine-grained, screen reader-driven keystroke-level behaviors reflect users’ cognitive strategies. In this paper, we present the findings of a longitudinal study with 25 blind participants to examine their micro-behavioral patterns, using keyboard activity and screen reader logs on both familiar and unfamiliar e-commerce websites. We complemented this study with semi-structured interviews to contextualize the uncovered micro-behavioral patterns. Our results revealed patterns in how blind users draw upon cognitive maps and well-established shortcut routines developed on familiar websites to streamline navigation on unfamiliar platforms. However, unfamiliar websites, even when structurally accessible, often introduced elevated navigation entropy, increased shortcut failures, and induced more exploratory behavior, as users worked to reconstruct new mental models. Additionally, we also identified a strong preferential structure in keyboard shortcut use, where users maintain a personalized and often chronologically-ranked sequence of keystrokes. Furthermore, most users approached shopping with pre-planned objectives, relying on targeted search queries rather than broad ad-hoc product exploration for securing the ‘best deals’. Based on the study insights, we discuss design considerations for assistive technology developers and e-commerce websites to further improve the online shopping experience for blind users.

Coordinating viewpoints with another person during a collaborative task can provide informative cues on human behavior. Despite the massive shift of collaborative spaces into virtual environments, versatile setups that enable eye-tracking in an online collaborative environment (distributed eye-tracking) remain unexplored. In this study, we present DisETrac- a versatile setup for eye-tracking in online collaborations. Further, we demonstrate and evaluate the utility of DisETrac through a user study. Finally, we discuss the implications of our results for future improvements. Our results indicate promising avenue for developing versatile setups for distributed eye-tracking.

Video accessibility is crucial for blind screen-reader users as online videos are increasingly playing an essential role in education, employment, and entertainment. While there exist quite a few techniques and guidelines that focus on creating accessible videos, there is a dearth of research that attempts to characterize the accessibility of existing videos. Therefore in this paper, we define and investigate a diverse set of video and audio-based accessibility features in an effort to characterize accessible and inaccessible videos. As a ground truth for our investigation, we built a custom dataset of 600 videos, in which each video was assigned an accessibility score based on the number of its wins in a Swiss-system tournament, where human annotators performed pairwise accessibility comparisons of videos. In contrast to existing accessibility research where the assessments are typically done by blind users, we recruited sighted users for our effort, since videos comprise a special case where sight could be required to better judge if any particular scene in a video is presently accessible or not. Subsequently, by examining the extent of association between the accessibility features and the accessibility scores, we could determine the features that significantly (positively or negatively) impact video accessibility and therefore serve as good indicators for assessing the accessibility of videos. Using the custom dataset, we also trained machine learning models that leveraged our handcrafted features to either classify an arbitrary video as accessible/inaccessible or predict an accessibility score for the video. Evaluation of our models yielded an F1 score of 0.675 for binary classification and a mean absolute error of 0.53 for score prediction, thereby demonstrating their potential in video accessibility assessment while also illuminating their current limitations and the need for further research in this area.