Accessibility forums and, more recently, generative AI tools have become vital resources for blind users seeking solutions to computer-interaction issues and learning about new assistive technologies, screen reader features, tutorials, and software updates. Understanding user experiences with these resources is essential for identifying and addressing persistent support gaps. Towards this, we interviewed 14 blind users who regularly engage with forums and GenAI tools. Findings revealed that forums often overwhelm users with multiple overlapping topics, redundant or irrelevant content, and fragmented responses that must be mentally pieced together, increasing cognitive load. GenAI tools, while offering more direct assistance, introduce new barriers by producing unreliable answers, including overly verbose or fragmented guidance, fabricated information, and contradictory suggestions that fail to follow prompts, thereby heightening verification demands. Based on these insights, we outlined design opportunities to improve the reliability of assistive resources, aiming to provide blind users with more trustworthy and cognitively-manageable support.

AI tools like ChatGPT and Be-My-AI are increasingly being used by blind individuals. Although prior work has explored their use in some Do-It-Yourself (DIY) tasks by blind individuals, little is known about how they use these tools and the available product-manual resources to assemble, operate, and troubleshoot physical/tangible products – tasks requiring spatial reasoning, structural understanding, and precise execution. We address this knowledge gap via an interview study and a usability study with blind participants, investigating how they leverage AI tools and product manuals for DIY tasks with physical products. Findings show that manuals are essential resources, but product-manual instructions are often inadequate for blind users. AI tools presently do not adequately address this insufficiency, in fact, we observed that they often exacerbate this issue with incomplete, incoherent, or misleading guidance. Lastly, we suggest improvements to AI tools for generating tailored instructions for blind users’ DIY tasks involving tangible products.

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.

Large Language Models (LLMs) are increasingly being adopted in a wide variety of domains, including sensitive domains such as healthcare and finance. However, persistent challenges such as unreliable data sources, privacy breaches, and hallucinated output continue to hinder their usage. We have experimented with several strategies to address these challenges. First, we developed BlockQwen, a blockchain-augmented framework that integrates decentralized trust validation, role-specific access control, and verifiable audit trails into the Qwen 2.5 LLM workflow. Second, we developed PrivAware, a multilayered privacy-enforcement framework, using a fine-tuned Flan-T5 model with self-attention masking, to safeguard data while maintaining high utility. Both systems resulted in significant improvement in mitigating privacy leaks and hallucinations. In this paper, we discuss the challenges that we faced in developing these systems and how these challenges were incrementally overcome. We briefly describe each system, and more importantly, we discuss the lessons learned throughout the development and testing process. It also includes a justification for each of the strategies employed and the benefits gained by such deployments. Finally, we provide guidelines for future development of trustworthy systems using LLMs, with special focus on preventing privacy leaks, minimizing hallucinations, improved authentication and authorization, and immutable audit trails.

The growing demand for computer professionals, driven by the expanding Information Technology industry, has led to numerous inclusive computing education efforts. These efforts have even included blind or visually-impaired (BVI) students, who are being increasingly encouraged to pursue education and a career in computing, despite the visually-oriented nature of the discipline. Extant literature has predominantly focused on identifying and addressing the accessibility barriers faced by BVI students to promote more inclusive learning environments. While few studies have also investigated the accessibility of computing education from the perspectives of BVI learners and instructors, these have been primarily situated in the Global North contexts; there is still a knowledge gap regarding the teaching and learning experiences of instructors and BVI students, respectively, in resource-constrained Global South contexts, where accessibility awareness and inclusion efforts are at nascent stages. To fill this gap, we conducted an interview study with 15 participants in India, where we inquired with BVI students, instructors, and BVI professionals, regarding their challenges, experiences, and needs pertaining to computing education. The study revealed that BVI students face significant difficulty in comprehending the instructional materials, the instructors often deal with courses not progressing as planned despite meticulous preparation, the students heavily depend on peer learning for grasping computing concepts, and they need additional support for managing the cognitively-burdensome task of simultaneously learning computing concepts and screen readers. Informed by the findings, we offer recommendations to improve computing curricula for BVI students and discuss self-learning assistive tools to supplement accessible computing education.

Image memes are a pervasive form of online communication, widely used to convey humor, opinions, and cultural references. Prior work has explored making memes accessible to blind users, primarily through auto-generated descriptive captions. While these approaches improve comprehensibility and sometimes incorporate prosodic or emotional cues, they often fail to capture the humor, narrative structure, and contextual nuances that make memes engaging. We present MemeBuddy, a system that models memes as dialog, generating structured, multi-turn audio representations using role-based speakers. MemeBuddy reinterprets a meme as a conversation between two speakers, integrating extracted meme text with contextual knowledge implicitly inferred by a multimodal LLM (e.g., recognition of common meme templates and cultural references) to convey intent, timing, and implicit meaning through conversational interaction. We evaluate MemeBuddy in a user study with 14 blind participants. Results show that dialog-style meme representations consistently improve engagement and user satisfaction compared to caption-style descriptions, while maintaining comparable comprehension.

E-commerce platforms generate extensive multi-modal data, including product descriptions, images, and customer reviews, which significantly influence consumer purchasing. However, discrepancies between seller claims and buyer experiences often lead to mistrust, dissatisfaction, and financial loss. Traditional e-commerce analytics approaches, including text-based sentiment analysis, standalone image classification, and rudimentary summarization, often fail to capture the complex interplay between modalities and therefore overlook nuanced discrepancies across textual and visual inputs. To address these limitations, we introduce ReViewQwen, a novel multimodal discrepancy detection and summarization framework leveraging the advanced Qwen2-VL Vision-Language Model. ReViewQwen integrates textual and visual inputs (product images from both buyer and seller) into a unified embedding space to systematically detect and contextualize discrepancies. Our comprehensive evaluation demonstrates that ReViewQwen outperforms state-of-the-art models such as LLaMA 3.2, Phi-3.5, and PaLiGemma 2, achieving superior precision, recall, and F1-score. Notably, the proposed system achieves accuracy improvement over the best-performing baseline from 51.15% to 88.00%. Additionally, our method promotes fairness in e-commerce review analytics by substantially reducing model biases and hallucinated content, thereby ensuring more trustworthy and balanced explanations. To access source code, data, and Prompts used https://github.com/domsoos/reviewqwen

Significant changes in the digital employment landscape, driven by rapid technological advancements and the COVID-19 pandemic, have introduced new opportunities for blind and visually impaired (BVI) individuals in developing countries like India. However, a significant portion of the BVI population in India remains unemployed despite extensive accessibility advancements and job search interventions. Therefore, we conducted semi-structured interviews with 20 BVI persons who were either pursuing or recently sought employment in the digital industry. Our findings reveal that despite gaining digital literacy and extensive training, BVI individuals struggle to meet industry requirements for fulfilling job openings. While they engage in self-reflection to identify shortcomings in their approach and skills, they lack constructive feedback from peers and recruiters. Moreover, the numerous job intervention tools are limited in their ability to meet the unique needs of BVI job seekers. Our results, therefore, provide key insights that inform the design of future collaborative intervention systems that offer personalized feedback for BVI individuals, effectively guiding their self-reflection process and subsequent job search behaviors, and potentially leading to improved employment outcomes.

The importance of data charts is self-evident, given their ability to express complex data in a simple format that facilitates quick and easy comparisons, analysis, and consumption. However, the inherent visual nature of the charts creates barriers for people with visual impairments to reap the associated benefits to the same extent as their sighted peers. While extant research has predominantly focused on understanding and addressing these barriers for blind screen reader users, the needs of low-vision screen magnifier users have been largely overlooked. In an interview study, almost all low-vision participants stated that it was challenging to interact with data charts on small screen devices such as smartphones and tablets, even though they could technically "see" the chart content. They ascribed these challenges mainly to the magnification-induced loss of visual context that connected data points with each other and also with chart annotations, e.g., axis values. In this paper, we present a method that addresses this problem by automatically transforming charts that are typically non-interactive images into personalizable interactive charts which allow selective viewing of desired data points and preserve visual context as much as possible under screen enlargement. We evaluated our method in a usability study with 26 low-vision participants, who all performed a set of representative chart-related tasks under different study conditions. In the study, we observed that our method significantly improved the usability of charts over both the status quo screen magnifier and a state-of-the-art space compaction-based solution.

Large language models (LLMs), such as the pioneering GPT technology by OpenAI, have undeniably become one of the most significant innovations in recent history. They have achieved phenomenal success across a broad spectrum of applications in numerous industries, transforming how we interact with the digital world. Notwithstanding these remarkable successes, applying LLMs within the realm of accessibility has largely been unexplored. We introduce Savant, as a demonstration of the potential of LLMs for accessibility. Specifically, Savant leverages the impressive text comprehension abilities of LLMs to provide uniform interaction for screen reader users across various applications, mitigating the significant interaction burden imposed by the heterogeneity in user interfaces for blind screen reader users. Savant automates screen reader actions on control elements like buttons, text fields, and drop-down menus via spoken natural language commands (NLCs). Interpreting the NLC, identifying the correct control element, and formulating the action sequence are facilitated by LLMs. Few-shot prompts supply context and guidance for the LLMs to produce appropriate responses, specifically converting the NLC into a correct series of actions on the user interface elements, which are then performed automatically. The demonstration will exhibit Savant’s capability across a variety of exemplar applications, emphasizing its versatility.

Blind individuals, who by necessity depend on screen readers to interact with computers, face considerable challenges in navigating the diverse and complex graphical user interfaces of different computer applications. The heterogeneity of various application interfaces often requires blind users to remember different keyboard combinations and navigation methods to use each application effectively. To alleviate this significant interaction burden imposed by heterogeneous application interfaces, we present Savant, a novel assistive technology powered by large language models (LLMs) that allows blind screen reader users to interact uniformly with any application interface through natural language. Novelly, Savant can automate a series of tedious screen reader actions on the control elements of the application when prompted by a natural language command from the user. These commands can be flexible in the sense that the user is not strictly required to specify the exact names of the control elements in the command. A user study evaluation of Savant with 11 blind participants demonstrated significant improvements in interaction efficiency and usability compared to current practices.

Bar charts are widely used for their simplicity in data representation, prompting numerous studies to explore and model how users interact with and perceive bar chart information. However, these studies have predominantly focused on sighted users, with a few also targeting blind screen-reader users, whereas the graphical perception of low-vision screen magnifier users is still an uncharted research territory. We fill this knowledge gap in this paper by designing four experiments for a laboratory study with 25 low-vision participants to examine their graphical perception while interacting with bar charts. For our investigation, we built a custom screen magnifier-based logger that captured micro-interaction details such as zooming and panning. Our findings indicate that low-vision users invest significant time counteracting blurring and contrast effects when analyzing charts. We also observed that low-vision users struggle more in interpreting bars within a single-column stack compared to other stacked bar configurations, and moreover, for a few participants, the perception accuracy is lower when comparing separated bars than when comparing adjacent bars.

Data chart visualizations and text are often paired in news articles, online blogs, and academic publications to present complex data. While chart visualizations offer graphical summaries of the data, the accompanying text provides essential context and explanation. Associating information from text and charts is straightforward for sighted users but presents significant challenges for individuals with low vision, especially on small-screen devices such as smartphones. The visual nature of charts coupled with the layout of the text inherently makes it difficult for low vision users to mentally associate chart data with text and comprehend the content due to their dependence on screen magnifier assistive technology, which only displays a small portion of the screen at any instant due to content enlargement. To address this problem, in this paper, we present a smartphone-based multimodal mixed-initiative interface that transforms static data charts and the accompanying text into an interactive slide show featuring frames containing “magnified views” of relevant data point combinations. The interface also includes a narration component that delivers tailored information for each “magnified view”. The design of our interface was informed by a user study with 10 low-vision participants, aimed at uncovering low vision interaction challenges and user-interface requirements with multimodal documents that integrate text and chart visualizations. Our interface was also evaluated in a subsequent study with 12 low-vision participants, where we observed significant improvements in chart usability compared to both status-quo screen magnifiers and a state-of-the-art solution.

While gesture typing is widely adopted on touchscreen keyboards, its support for low vision users is limited. We have designed and implemented two keyboard prototypes, layout-magnified and key-magnified keyboards, to enable gesture typing for people with low vision. Both keyboards facilitate uninterrupted access to all keys while the screen magnifier is active, allowing people with low vision to input text with one continuous stroke. Furthermore, we have created a kinematics-based decoding algorithm to accommodate the typing behavior of people with low vision. This algorithm can decode the gesture input even if the gesture trace deviates from a pre-defined word template, and the starting position of the gesture is far from the starting letter of the target word. Our user study showed that the key-magnified keyboard achieved 5.28 words per minute, 27.5% faster than a conventional gesture typing keyboard with voice feedback.

Perusing web data items such as shopping products is a core online user activity. To prevent information overload, the content associated with data items is typically dispersed across multiple webpage sections over multiple web pages. However, such content distribution manifests an unintended side effect of significantly increasing the interaction burden for blind users, since navigating to-and-fro between different sections in different pages is tedious and cumbersome with their screen readers. While existing works have proposed methods for the context of a single webpage, solutions enabling usable access to content distributed across multiple webpages are few and far between. In this paper, we present InstaFetch, a browser extension that dynamically generates an alternative screen reader-friendly user interface in real-time, which blind users can leverage to almost instantly access different item-related information such as description, full specification, and user reviews, all in one place, without having to tediously navigate to different sections in different webpages. Moreover, InstaFetch also supports natural language queries about any item, a feature blind users can exploit to quickly obtain desired information, thereby avoiding manually trudging through reams of text. In a study with 14 blind users, we observed that the participants needed significantly lesser time to peruse data items with InstaFetch, than with a state-of-the-art solution.

Although menu selection has been extensively studied in HCI, most existing studies have focused on sighted users, leaving blind users’ menu selection under-studied. In this paper, we propose a computational model that can simulate blind users’ menu selection performance and strategies, including the way they use techniques like swiping, gliding, and direct touch. We assume that selection behavior emerges as an adaptation to the user’s memory of item positions based on experience and feedback from the screen reader. A key aspect of our model is a model of long-term memory, predicting how a user recalls and forgets item position based on previous menu selections. We compare simulation results predicted by our model against data obtained in an empirical study with ten blind users. The model correctly simulated the effect of the menu length and menu arrangement on selection time, the action composition, and the menu selection strategy of the 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.

Accessibility forums enable individuals with visual impairments to connect and collaboratively seek solutions to technical issues, as well as share reviews, best practices, and latest news. However, these forums are presently built on legacy systems that were primarily designed for sighted users, and are difficult to navigate with non-visual assistive technologies like screen-readers. Accessibility forum threads are “entangled”, with multiple sub-conversations interleaved with each other. This does not gel with the predominantly linear navigation of screen-readers. Screen-reader users often listen to reams of irrelevant posts while foraging for nuggets of interest. To address this and improve non-visual interaction efficiency, we present TASER, a browser extension that leverages a state-of-the-art conversation disentanglement algorithm to automatically identify and separate sub-conversations in a forum thread, and then presents these sub-conversations to the user via a custom interface specifically tailored for efficient and usable screen-reader interaction. In a user study with 11 screen-reader users, we observed that TASER significantly reduced the average user input actions and interaction times by and respectively along with a significant drop in cognitive load ( lower NASA-TLX score) compared to the status quo while performing representative information foraging tasks on accessibility forums.

Web data items such as shopping products, classifieds, and job listings are indispensable components of most e-commerce websites. The information on the data items are typically distributed over two or more webpages, e.g., a ‘Query-Results’ page showing the summaries of the items, and ‘Details’ pages containing full information about the items. While this organization of data mitigates information overload and visual cluttering for sighted users, it however increases the interaction overhead and effort for blind users, as back-and-forth navigation between webpages using screen reader assistive technology is tedious and cumbersome. Existing usability-enhancing solutions are unable to provide adequate support in this regard as they predominantly focus on enabling efficient content access within a single webpage, and as such are not tailored for content distributed across multiple webpages. As an initial step towards addressing this issue, we developed AutoDesc, a browser extension that leverages a custom extraction model to automatically detect and pull out additional item descriptions from the ‘details’ pages, and then proactively inject the extracted information into the ‘Query-Results’ page, thereby reducing the amount of back-and-forth screen reader navigation between the two webpages. In a study with 16 blind users, we observed that within the same time duration, the participants were able to peruse significantly more data items on average with AutoDesc, compared to that with their preferred screen readers as well as with a state-of-the-art solution.

Online discussion forums have become an integral component of news, entertainment, information, and video-streaming websites, where people all over the world actively engage in discussions on a wide range of topics including politics, sports, music, business, health, and world affairs. Yet, little is known about their usability for blind users, who aurally interact with the forum conversations using screen reader assistive technology. In an interview study, blind users stated that they often had an arduous and frustrating interaction experience while consuming conversation threads, mainly due to the highly redundant content and the absence of customization options to selectively view portions of the conversations. As an initial step towards addressing these usability concerns, we designed PView - a browser extension that enables blind users to customize the content of forum threads in real time as they interact with these threads. Specifically, PView allows the blind users to explicitly hide any post that is irrelevant to them, and then PView automatically detects and filters out all subsequent posts that are substantially similar to the hidden post in real time, before the users navigate to those portions of the thread. In a user study with blind participants, we observed that compared to the status quo, PView significantly improved the usability, workload, and satisfaction of the participants while interacting with the forums.

Web data records are usually accompanied by auxiliary webpage segments, such as filters, sort options, search form, and multi-page links, to enhance interaction efficiency and convenience for end users. However, blind and visually impaired (BVI) persons are presently unable to fully exploit the auxiliary segments like their sighted peers, since these segments are scattered all across the screen, and as such assistive technologies used by BVI users, i.e., screen reader and screen magnifier, are not geared for efficient interaction with such scattered content. Specifically, for blind screen reader users, content navigation is predominantly one-dimensional despite the support for skipping content, and therefore navigating to-and-fro between different parts of the webpage is tedious and frustrating. Similarly, low vision screen magnifier users have to continuously pan back-and-forth between different portions of a webpage, given that only a portion of the screen is viewable at any instant due to content enlargement. The extant techniques to overcome inefficient web interaction for BVI users have mostly focused on general web-browsing activities, and as such they provide little to no support for data record-specific interaction activities such as filtering and sorting – activities that are equally important for facilitating quick and easy access to desired data records. To fill this void, we present InSupport, a browser extension that: (i) employs custom machine learning-based algorithms to automatically extract auxiliary segments on any webpage containing data records; and (ii) provides an instantly accessible proxy one-stop interface for easily navigating the extracted auxiliary segments using either basic keyboard shortcuts or mouse actions. Evaluation studies with 14 blind participants and 16 low vision participants showed significant improvement in web usability with InSupport, driven by increased reduction in interaction time and user effort, compared to the state-of-the-art solutions.

Most people who are blind interact with social media content with the assistance of a screen reader, a software that converts text to speech. However, the language used in social media is well-known to contain several informal out-of-vocabulary words (e.g., abbreviations, wordplays, slang), many of which do not have corresponding standard pronunciations. The narration behavior of screen readers for such out-of-vocabulary words and the corresponding impact on the social media experience of blind screen reader users are still uncharted research territories. Therefore we seek to plug this knowledge gap by examining how current popular screen readers narrate different types of out-of-vocabulary words found on Twitter, and also, how the presence of such words in tweets influences the interaction behavior and comprehension of blind screen reader users. Our investigation showed that screen readers rarely autocorrect out-of-vocabulary words, and moreover they do not always exhibit ideal behavior for certain prolific types of out-of-vocabulary words such as acronyms and initialisms. We also observed that blind users often rely on tedious and taxing workarounds to comprehend actual meanings of out-of-vocabulary words. Informed by the observations, we finally discuss methods that can potentially reduce this interaction burden for blind users on social media.

Reading plays a vital role in updating the researchers on recent developments in the field, including but not limited to solutions to various problems and collaborative studies between disciplines. Prior studies identify reading patterns to vary depending on the level of expertise of the researcher on the content of the document. We present a pilot study of eye-tracking measures during a reading task with participants across different areas of expertise with the intention of characterizing the reading patterns using both eye movement and pupillary information.

Interaction with web data records typically involves accessing auxiliary webpage segments such as filters, sort options, search form, and multi-page links. As these segments are usually scattered all across the screen, it is arduous and tedious for blind users who rely on screen readers to access the segments, given that content navigation with screen readers is predominantly one-dimensional, despite the available support for skipping content via either special keyboard shortcuts or selective navigation. The extant techniques to overcome inefficient web screen reader interaction have mostly focused on general web content navigation, and as such they provide little to no support for data record-specific interaction activities such as filtering and sorting – activities that are equally important for enabling quick and easy access to the desired data records. To fill this void, we present InSupport, a browser extension that: (i) employs custom-built machine learning models to automatically extract auxiliary segments on any webpage containing data records, and (ii) provides an instantly accessible proxy one-stop interface for easily navigating the extracted segments using basic screen reader shortcuts. An evaluation study with 14 blind participants showed significant improvement in usability with InSupport, driven by increased reduction in interaction time and the number of key presses, compared to state-of-the-art solutions.

For many blind users, interaction with computer applications using screen reader assistive technology is a frustrating and time-consuming affair, mostly due to the complexity and heterogeneity of applications’ user interfaces. An interview study revealed that many applications do not adequately convey their interface structure and controls to blind screen reader users, thereby placing additional burden on these users to acquire this knowledge on their own. This is often an arduous and tedious learning process given the one-dimensional navigation paradigm of screen readers. Moreover, blind users have to repeat this learning process multiple times, i.e., once for each application, since applications differ in their interface designs and implementations. In this paper, we propose a novel push-based approach to make non-visual computer interaction easy, efficient, and uniform across different applications. The key idea is to make screen reader interaction ‘structure-agnostic’, by automatically identifying and extracting all application controls and then instantly ‘pushing’ these controls on demand to the blind user via a custom overlay dashboard interface. Such a custom overlay facilitates uniform and efficient screen reader navigation across all applications. A user study showed significant improvement in user satisfaction and interaction efficiency with our approach compared to a state-of-the-art screen reader.

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.

Gliding a finger on touchscreen to reach a target, that is, touch exploration, is a common selection method of blind screen-reader users. This paper investigates their gliding behavior and presents a model for their motor performance. We discovered that the gliding trajectories of blind people are a mixture of two strategies: 1) ballistic movements with iterative corrections relying on non-visual feedback, and 2) multiple sub-movements separated by stops, and concatenated until the target is reached. Based on this finding, we propose the mixture pointing model, a model that relates movement time to distance and width of the target. The model outperforms extant models, improving R2 from 0.65 for Fitts’ law to 0.76, and is superior in cross-validation and information criteria. The model advances understanding of gliding-based target selection and serves as a tool for designing interface layouts for screen-reader based touch exploration.

Many people with low vision rely on screen-magnifier assistive technology to interact with productivity applications such as word processors, spreadsheets, and presentation software. Despite the importance of these applications, little is known about their usability with respect to low-vision screen-magnifier users. To fill this knowledge gap, we conducted a usability study with 10 low-vision participants having different eye conditions. In this study, we observed that most usability issues were predominantly due to high spatial separation between main edit area and command ribbons on the screen, as well as the wide span grid-layout of command ribbons; these two GUI aspects did not gel with the screen-magnifier interface due to lack of instantaneous WYSIWYG (What You See Is What You Get) feedback after applying commands, given that the participants could only view a portion of the screen at any time. Informed by the study findings, we developed MagPro, an augmentation to productivity applications, which significantly improves usability by not only bringing application commands as close as possible to the user's current viewport focus, but also enabling easy and straightforward exploration of these commands using simple mouse actions. A user study with nine participants revealed that MagPro significantly reduced the time and workload to do routine command-access tasks, compared to using the state-of-the-art screen magnifier.

People with low vision use screen magnifiers to interact with computers. They usually need to zoom and pan with the screen magnifier using predefined keyboard and mouse actions. When using office productivity applications (e.g., word processors and spreadsheet applications), the spatially distributed arrangement of UI elements makes interaction a challenging proposition for low vision users, as they can only view a fragment of the screen at any moment. They expend significant chunks of time panning back-and-forth between application ribbons containing various commands (e.g., formatting, design, review, references, etc.) and the main edit area containing user content. In this demo, we will demonstrate MagPro, an interface augmentation to office productivity tools, that not only reduces the interaction effort of low-vision screen-magnifier users by bringing the application commands as close as possible to the users' current focus in the edit area, but also lets them easily explore these commands using simple mouse actions. Moreover, MagPro automatically synchronizes the magnifier viewport with the keyboard cursor, so that users can always see what they are typing, without having to manually adjust the magnifier focus every time the keyboard cursor goes of screen during text entry.

People with visual impairments typically rely on screen-magnifier assistive technology to interact with webpages. As screen-magnifier users can only view a portion of the webpage content in an enlarged form at any given time, they have to endure an inconvenient and arduous process of repeatedly moving the magnifier focus back-and-forth over different portions of the webpage in order to make comparisons between data records, e.g., comparing the available fights in a travel website based on their prices, durations, etc. To address this issue, we designed and developed TableView, a browser extension that leverages a state-of-the art information extraction method to automatically identify and extract data records and their attributes in a webpage, and subsequently presents them to a user in a compactly arranged tabular format that needs significantly less screen space compared to that currently occupied by these items in the page. This way, TableView is able to pack more items within the magnifier focus, thereby reducing the overall content area for panning, and hence making it easy for screen-magnifier users to compare different items before making their selections. A user study with 16 low vision participants showed that with TableView, the time spent on panning the data records in webpages was significantly reduced by 72.9% (avg.) compared to that with just a screen magnifier, and 66.5% compared to that with a screen magnifier using a space compaction method.

Filling out PDF forms with screen readers has always been a challenge for people who are blind. Many of these forms are not interactive and hence are not accessible; even if they are interactive, the serial reading order of the screen reader makes it difficult to associate the correct labels with the form fields. This demo will present TransPAc[5], an assistive technology that enables blind people to fill out PDF forms. Since blind people are familiar with web browsing, TransPAc leverages this fact by faithfully transforming a PDF document with forms into a HTML page. The blind user fills out the form fields in the HTML page with their screen reader and these filled-in data values are transparently transferred onto the corresponding form fields in the PDF document. TransPAc thus addresses a long standing problem in PDF form accessibility.

People with low vision who use screen magnifiers to interact with computing devices find it very challenging to interact with dynamically changing digital content such as videos, since they do not have the luxury of time to manually move, i.e., pan the magnifier lens to different regions of interest (ROIs) or zoom into these ROIs before the content changes across frames. In this paper, we present SViM, a first of its kind screen-magnifier interface for such users that leverages advances in computer vision, particularly video saliency models, to identify salient ROIs in videos. SViM's interface allows users to zoom in/out of any point of interest, switch between ROIs via mouse clicks and provides assistive panning with the added flexibility that lets the user explore other regions of the video besides the ROIs identified by SViM. Subjective and objective evaluation of a user study with 13 low vision screen magnifier users revealed that overall the participants had a better user experience with SViM over extant screen magnifiers, indicative of the former's promise and potential for making videos accessible to low vision screen magnifier users.

Navigating webpages with screen readers is a challenge even with recent improvements in screen reader technologies and the increased adoption of web standards for accessibility, namely ARIA. ARIA landmarks, an important aspect of ARIA, lets screen reader users access different sections of the webpage quickly, by enabling them to skip over blocks of irrelevant or redundant content. However, these landmarks are sporadically and inconsistently used by web developers, and in many cases, even absent in numerous web pages. Therefore, we propose SaIL, a scalable approach that automatically detects the important sections of a web page, and then injects ARIA landmarks into the corresponding HTML markup to facilitate quick access to these sections. The central concept underlying SaIL is visual saliency, which is determined using a state-of-the-art deep learning model that was trained on gaze-tracking data collected from sighted users in the context of web browsing. We present the findings of a pilot study that demonstrated the potential of SaIL in reducing both the time and effort spent in navigating webpages with screen readers.

Visual `point-and-click' interaction artifacts such as mouse and touchpad are tangible input modalities, which are essential for sighted users to conveniently interact with computer applications. In contrast, blind users are unable to leverage these visual input modalities and are thus limited while interacting with computers using a sequentially narrating screen-reader assistive technology that is coupled to keyboards. As a consequence, blind users generally require significantly more time and effort to do even simple application tasks (e.g., applying a style to text in a word processor) using only keyboard, compared to their sighted peers who can effortlessly accomplish the same tasks using a point-and-click mouse. This paper explores the idea of repurposing visual input modalities for non-visual interaction so that blind users too can draw the benefits of simple and efficient access from these modalities. Specifically, with word processing applications as the representative case study, we designed and developed NVMouse as a concrete manifestation of this repurposing idea, in which the spatially distributed word-processor controls are mapped to a virtual hierarchical `Feature Menu' that is easily traversable non-visually using simple scroll and click input actions. Furthermore, NVMouse enhances the efficiency of accessing frequently-used application commands by leveraging a data-driven prediction model that can determine what commands the user will most likely access next, given the current `local' screen-reader context in the document. A user study with 14 blind participants comparing keyboard-based screen readers with NVMouse, showed that the latter significantly reduced both the task-completion times and user effort (i.e., number of user actions) for different word-processing activities.

Interacting with long web documents such as wiktionaries, manuals, tutorials, blogs, novels, etc., is easy for sighted users, as they can leverage convenient pointing devices such as a mouse/touchpad to quickly access the desired content either via scrolling with visual scanning or clicking hyperlinks in the available Table of Contents (TOC). Blind users on the other hand are unable to use these pointing devices, and therefore can only rely on keyboard-based screen reader assistive technology that lets them serially navigate and listen to the page content using keyboard shortcuts. As a consequence, interacting with long web documents with just screen readers, is often an arduous and tedious experience for the blind users.To bridge the usability divide between how sighted and blind users interact with web documents, in this paper, we present iTOC, a browser extension that automatically identifies and extracts TOC hyperlinks from the web documents, and then facilitates on-demand instant screen-reader access to the TOC from anywhere in the website. This way, blind users need not manually search for the desired content by moving the screen-reader focus sequentially all over the webpage; instead they can simply access the TOC from anywhere using iTOC, and then select the desired hyperlink which will automatically move the focus to the corresponding content in the document. A user study with 15 blind participants showed that with iTOC, both the access time and user effort (number of user input actions) were significantly lowered by as much as 42.73% and 57.9%, respectively, compared to that with another state-of-the-art solution for improving web usability.

PDF forms are ubiquitous. Businesses big and small, government agencies, health and educational institutions and many others have all embraced PDF forms. People use PDF forms for providing information to these entities. But people who are blind frequently find it very difficult to fill out PDF forms with screen readers, the standard assistive software that they use for interacting with computer applications. Firstly, many of the them are not even accessible as they are non-interactive and hence not editable on a computer. Secondly, even if they are interactive, it is not always easy to associate the correct labels with the form fields, either because the labels are not meaningful or the sequential reading order of the screen reader misses the visual cues that associate the correct labels with the fields. In this paper we present a solution to the accessibility problem of PDF forms. We leverage the fact that many people with visual impairments are familiar with web browsing and are proficient at filling out web forms. Thus, we create a web form layer over the PDF form via a high fidelity transformation process that attempts to preserve all the spatial relationships of the PDF elements including forms, their labels and the textual content. Blind people only interact with the web forms, and the filled out web form fields are transparently transferred to the corresponding fields in the PDF form. An optimization algorithm automatically adjusts the length and width of the PDF fields to accommodate arbitrary size field data. This ensures that the filled out PDF document does not have any truncated form-field values, and additionally, it is readable. A user study with fourteen users with visual impairments revealed that they were able to populate more form fields than the status quo and the self-reported user experience with the proposed interface was superior compared to the status quo.

Gesture typing--entering a word by gliding the finger sequentially over letter to letter-- has been widely supported on smartphones for sighted users. However, this input paradigm is currently inaccessible to blind users: it is difficult to draw shape gestures on a virtual keyboard without access to key visuals. This paper describes the design of accessible gesture typing, to bring this input paradigm to blind users. To help blind users figure out key locations, the design incorporates the familiar screen-reader supported touch exploration that narrates the keys as the user drags the finger across the keyboard. The design allows users to seamlessly switch between exploration and gesture typing mode by simply lifting the finger. Continuous touch-exploration like audio feedback is provided during word shape construction that helps the user glide in the right direction of the key locations constituting the word. Exploration mode resumes once word shape is completed. Distinct earcons help distinguish gesture typing mode from touch exploration mode, and thereby avoid unintended mix-ups. A user study with 14 blind people shows 35% increment in their typing speed, indicative of the promise and potential of gesture typing technology for non-visual text entry.

Filling out printed forms (e.g., checks) independently is currently impossible for blind people, since they cannot pinpoint the locations of the form fields, and quite often, they cannot even figure out what fields (e.g., name) are present in the form. Hence, they always depend on sighted people to write on their behalf, and help them affix their signatures. Extant assistive technologies have exclusively focused on reading, with no support for writing. In this paper, we introduce WiYG, a Write-it-Yourself guide that directs a blind user to the different form fields, so that she can independently fill out these fields without seeking assistance from a sighted person. Specifically, WiYG uses a pocket-sized custom 3D printed smartphone attachment, and well-established computer vision algorithms to dynamically generate audio instructions that guide the user to the different form fields. A user study with 13 blind participants showed that with WiYG, users could correctly fill out the form fields at the right locations with an accuracy as high as 89.5%.

Web browsing has never been easy for blind people, primarily due to the serial press-and-listen interaction mode of screen readers -- their "go-to'' assistive technology. Even simple navigational browsing actions on a page require a multitude of shortcuts. Auto-suggesting the next browsing action has the potential to assist blind users in swiftly completing various tasks with minimal effort. Extant auto-suggest feature in web pages is limited to filling form fields; in this paper, we generalize it to any web screen-reading browsing action, e.g., navigation, selection, etc. Towards that, we introduce SuggestOmatic, a personalized and scalable unsupervised approach for predicting the most likely next browsing action of the user, and proactively suggesting it to the user so that the user can avoid pressing a lot of shortcuts to complete that action. SuggestOmatic rests on two key ideas. First, it exploits the user's Action History to identify and suggest a small set of browsing actions that will, with high likelihood, contain an action which the user will want to do next, and the chosen action is executed automatically. Second, the Action History is represented as an abstract temporal sequence of operations over semantic web entities called Logical Segments - a collection of related HTML elements, e.g., widgets, search results, menus, forms, etc.; this semantics-based abstract representation of browsing actions in the Action History makes SuggestOmatic scalable across websites, i.e., actions recorded in one website can be used to make suggestions for other similar websites. We also describe an interface that uses an off-the-shelf physical Dial as an input device that enables SuggestOmatic to work with any screen reader. The results of a user study with 12 blind participants indicate that SuggestOmatic can significantly reduce the browsing task times by as much as 29% when compared with a hand-crafted macro-based web automation solution.

Low-vision users struggle to browse the web with screen magnifiers. Firstly, magnifiers occlude significant portions of the webpage, thereby making it cumbersome to get the webpage overview and quickly locate the desired content. Further, magnification causes loss of spatial locality and visual cues that commonly define semantic relationships in the page; reconstructing semantic relationships exclusively from narrow views dramatically increases the cognitive burden on the users. Secondly, low-vision users have widely varying needs requiring a range of interface customizations for different page sections; dynamic customization in extant magnifiers is disruptive to users' browsing. We present SteeringWheel, a magnification interface that leverages content semantics to preserve local context. In combination with a physical dial, supporting simple rotate and press gestures, users can quickly navigate different webpage sections, easily locate desired content, get a quick overview, and seamlessly customize the interface. A user study with 15 low-vision participants showed that their web-browsing efficiency improved by at least 20 percent with SteeringWheel compared to extant screen magnifiers.

Working with non-digital, standard printed materials has always been a challenge for blind people, especially writing. Blind people very often depend on others to fill out printed forms, write checks, sign receipts and documents. Extant assistive technologies for working with printed material have exclusively focused on reading, with little to no support for writing. Also, these technologies employ special-purpose hardware that are usually worn on fingers, making them unsuitable for writing. In this paper, we explore the idea of using off-the-shelf smartwatches (paired with smartphones) to assist blind people in both reading and writing paper forms including checks and receipts. Towards this, we performed a Wizard-of-Oz evaluation of different smartwatch-based interfaces that provide user-customized audio-haptic feedback in real-time, to guide blind users to different form fields, narrate the field labels, and help them write straight while filling out these fields. Finally, we report the findings of this study including the technical challenges and user expectations that can potentially inform the design of Write-it-Yourself aids based on smartwatches.

Sighted people can browse the Web almost exclusively using a mouse. This is because web browsing mostly entails pointing and clicking on some element in the web page, and these two operations can be done almost instantaneously with a computer mouse. Unfortunately, people with vision impairments cannot use a mouse as it only provides visual feedback through a cursor. Instead, they are forced to go through a slow and tedious process of building a mental map of the web page, relying primarily on a screen reader's keyboard shortcuts and its serial audio readout of the textual content of the page, including metadata. This can often cause content and cognitive overload. This paper describes our Speed-Dial system which uses an off-the-shelf physical Dial as a surrogate for the mouse for non-visual web browsing. Speed-Dial interfaces the physical Dial with the semantic model of a web page, and provides an intuitive and rapid access to the entities and their content in the model, thereby bringing blind people's browsing experience closer to how sighted people perceive and interact with the Web. A user study with blind participants suggests that with Speed-Dial they can quickly move around the web page to select content of interest, akin to pointing and clicking with a mouse.

Ubiquitous access is an increasingly common vision of computing, wherein users can interact with any computing device or service from anywhere, at any time. In the era of personal computing, users with visual impairments required special-purpose, assistive technologies, such as screen readers, to interact with computers. This paper investigates whether technologies like screen readers have kept pace with, or have created a barrier to, the trend toward ubiquitous access, with a specific focus on desktop computing as this is still the primary way computers are used in education and employment. Towards that, the paper presents a user study with 21 visually-impaired participants, specifically involving the switching of screen readers within and across different computing platforms, and the use of screen readers in remote access scenarios. Among the findings, the study shows that, even for remote desktop access-an early forerunner of true ubiquitous access-screen readers are too limited, if not unusable. The study also identifies several accessibility needs, such as uniformity of navigational experience across devices, and recommends potential solutions. In summary, assistive technologies have not made the jump into the era of ubiquitous access, and multiple, inconsistent screen readers create new practical problems for users with visual impairments.

A screen reader's sequential press-and-listen interface makes for an unsatisfactory and often times painful web-browsing experience for blind people. To help alleviate this situation, we introduce Web Screen Reading Automation Assistant (SRAA) for automating users' screen-reading actions (e.g., finding price of an item) on demand, thereby letting them focus on what they want to do rather than on how to get it done. The key idea is to elevate the interaction from operating on (syntactic) HTML elements, as is done now, to operating on web entities (which are semantically meaningful collections of related HTML elements, e.g., search results, menus, widgets, etc.). SRAA realizes this idea of semantic abstraction by constructing a Web Entity Model (WEM), which is a collection of web entities of the underlying webpage, using an extensive generic library of custom-designed descriptions of commonly occurring web entities across websites. The WEM brings blind users closer to how sighted people perceive and operate on web entities, and together with a natural-language user interface, SRAA relieves users from having to press numerous shortcuts to operate on low-level HTML elements - the principal source of tedium and frustration. This paper describes the design and implementation of SRAA. Evaluation with 18 blind subjects demonstrates its usability and effectiveness.

Remote desktop technology, the enabler of access to applications hosted on remote hosts, relies primarily on scraping the pixels on the remote screen and redrawing them as a simple bitmap on the client's local screen. Such a technology will simply not work with screen readers since the latter are innately tied to reading text. Since screen readers are locked-in to a specific OS platform, extant solutions that enable remote access with screen readers such as NVDARemote and JAWS Tandem require homogeneity of OS platforms at both the client and remote sites. This demo will present Sinter, a system that eliminates this requirement. With Sinter, a blind Mac user, for example, can now access a remote Windows application with VoiceOver, a scenario heretofore not possible.

Graphical user interfaces (GUIs) are widely used on smartphones, tablets, and laptops. While GUIs are convenient for sighted users, their accessibility for blind people, who use screen readers to interact with GUIs, remains to be problematic. Even the most screen-reader accessible GUIs are far less usable for blind people compared to sighted people, because the former group cannot benefit from the geometric layout of GUIs. As a result, blind people often have to listen through a lot of irrelevant content before they find what they are looking for. Haptic interfaces (those providing tactile feedback) have the potential to make GUI interfaces more accessible and usable for blind people. Alas, mainstream computer devices do not have haptic screens that would enable high-resolution tactile feedback, and specialized haptic devices are very limited and/or are exuberantly expensive and bulky.

Web browsing with screen readers is tedious and frustrating, largely due to the inability of blind screen-reader users to get spatial information about the structure of web pages and utilize it for effective navigation. Haptic interfaces have the potential to provide blind users with a tactile --feel-- for the 2-D layout of web pages and help them focus screen reading on specific parts of the webpage. In this preliminary work, we explore the utility of a simple haptic web-browsing interface -- tactile overlays, and report on a preliminary user study with 10 blind participants who performed various web-browsing tasks with and without these overlays. We also analyzed the user-interaction behavior and explored the appropriate design choices and their tradeoffs in the space of haptic-interface design for accessible web browsing

People with severe vision impairments generally interact with web pages via screen readers that provide keyboard shortcuts for navigating through the content. However, this traditional press- and-listen mode of interaction has several drawbacks, notably: time wasted listening to irrelevant content, extensive use of the keyboard to navigate the content, and the need to remember numerous keyboard shortcuts and browsing strategies. Augmenting traditional screen reading with a speech interface has the potential to alleviate many of the above limitations. This work describes Capti-Speak, an accessible web-browsing interface that supports both speech commands and standard screen-reader shortcuts. A user study with a dozen blind participants showed that Capti-Speak was significantly more usable and efficient compared to the conventional screen readers, especially for ad-hoc browsing, searching, and navigating to the content of interest.

Speech-enabled dialogue systems have the potential to enhance the ease with which blind individuals can interact with the Web beyond what is possible with screen read-ers- the currently available assistive tech-nology which narrates the textual content on the screen and provides shortcuts to navigate the content. In this paper, we present a dialogue act model towards de-veloping a speech enabled browsing sys-tem. The model is based on the corpus data that was collected in a wizard-of-oz study with 24 blind individuals who were assigned a gamut of browsing tasks. The development of the model included exten-sive experiments with assorted feature sets and classifiers; the outcomes of the exper-iments and the analysis of the results are presented. 1

Predicting the success of literary works is a curious question among publishers and aspiring writers alike.We examine the quantitative connection, if any, between writing style and successful literature.Based on novels over several different genres, we probe the predictive power of statistical stylometry in discriminating successful literary works, and identify characteristic stylistic elements that are more prominent in successful writings.Our study reports for the first time that statistical stylometry can be surprisingly effective in discriminating highly successful literature from less successful counterpart, achieving accuracy up to 84%.Closer analyses lead to several new insights into characteristics of the writing style in successful literature, including findings that are contrary to the conventional wisdom with respect to good writing style and readability.

Positioning or tracking in VANET is currently based on GPS. However, GPS is known to be prone to failure in case of emergencies. In addition, the current market penetration rate of GPS devices is low. Vehicles with built-in cellular communication capability are expected to be a part of the near future. Therefore, it is reasonable to assume that any vehicle possesses the functionality of a mobile unit (MU). The principal contribution of this paper is the proposed novel concept that employs the existing cellular RSS measurements as the basis for position estimation in VANET in situations where GPS services are unavailable. The proposed localization technique involves sampling the signal beacons received from three base stations surrounding the mobile unit for a very small time duration. Each of the RSS samples are then mapped to a sample of distance estimates based on shadowing radio propagation model. The medians of the generated distance sets are then used by a state of the art technique to produce a final location estimate. One of the important contributions of this work is justifying the selection of median over mean. An extremely small sampling duration negates the impact of mobile unit movement while the median selection neutralizes the deviation caused by time varying radio channel characteristics. All computation is restricted to mobile unit, thereby ensuring privacy. Simulation results demonstrate the efficiency of the proposed algorithm.

Acquiring and securing position information is of fundamental importance in vehicular ad hoc networks and their applications. Recently, it has been shown that securing position information can be achieved by enlisting the help of on-board radar devices that have seen a phenomenal penetration of the vehicular market. However, most on-board radar devices have a static range and this can cause a number of insecurities and can add to communication delay. The main contribution of this work is a novel low-cost radar model which can dynamically tune its range by changing the signal sample size. As it turns out, the dynamically-tunable radar considerably enhances position security.