Skip to content

Academic Paper Abstracts

Example Inputs

An important aspect of making the Web accessible to blind users is ensuring that all important web page elements such as links, clickable buttons, and form fields have explicitly assigned labels. Properly labeled content is then correctly read out by screen readers, a dominant assistive technology used by blind users. In particular, improperly labeled form fields can critically impede online transactions such as shopping, paying bills, etc. with screen readers. Very often labels are not associated with form fields or are missing altogether, making form filling a challenge for blind users. Algorithms for associating a form element with one of several candidate labels in its vicinity must cope with the variability of the element's features including label's location relative to the element, distance to the element, etc. Probabilistic models provide a natural machinery to reason with such uncertainties. In this paper we present a Finite Mixture Model (FMM) formulation of the label association problem. The variability of feature values are captured in the FMM by a mixture of random variables that are drawn from parameterized distributions. Then, the most likely label to be paired with a form element is computed by maximizing the log-likelihood of the feature data using the Expectation-Maximization algorithm. We also adapt the FMM approach for two related problems: assigning labels (from an external Knowledge Base) to form elements that have no candidate labels in their vicinity and for quickly identifying clickable elements such as add-to-cart, checkout, etc., used in online transactions even when these elements do not have textual captions (e.g., image buttons w/o alternative text). We provide a quantitative evaluation of our techniques, as well as a user study with two blind subjects who used an aural web browser implementing our approach.
Data quality is critical for many information-intensive applications. One of the best opportunities to improve data quality is during entry. Usher provides a theoretical, data-driven foundation for improving data quality during entry. Based on prior data, Usher learns a probabilistic model of the dependencies between form questions and values. Using this information, Usher maximizes information gain. By asking the most unpredictable questions first, Usher is better able to predict answers for the remaining questions. In this paper, we use Usher's predictive ability to design a number of intelligent user interface adaptations that improve data entry accuracy and efficiency. Based on an underlying cognitive model of data entry, we apply these modifications before, during and after committing an answer. We evaluated these mechanisms with professional data entry clerks working with real patient data from six clinics in rural Uganda. The results show that our adaptations have the potential to reduce error (by up to 78%), with limited effect on entry time (varying between -14% and +6%). We believe this approach has wide applicability for improving the quality and availability of data, which is increasingly important for decision-making and resource allocation.
Scrolling is an essential part of our everyday computing experience. Contemporary scrolling techniques rely on the explicit initiation of scrolling by the user. The act of scrolling is tightly coupled with the user?s ability to absorb information via the visual channel. The use of eye gaze information is therefore a natural choice for enhancing scrolling techniques. We present several gaze-enhanced scrolling techniques for manual and automatic scrolling which use gaze information as a primary input or as an augmented input. We also introduce the use off-screen gaze-actuated buttons for document navigation and control.
The Go-Go immersive interaction technique uses the metaphor of interactively growing the user’s arm and non-linear mapping for reaching and manipulating distant objects. Unlike others, our technique allows for seamless direct manipulation of both nearby objects and those at a distance.
ThinSight is a novel optical sensing system, fully integrated into a thin form factor display, capable of detecting multi-ple fingers placed on or near the display surface. We describe this new hardware in detail, and demonstrate how it can be embedded behind a regular LCD, allowing sensing without degradation of display capability. With our approach, fingertips and hands are clearly identifiable through the display. The approach of optical sensing also opens up the exciting possibility for detecting other physical objects and visual markers through the display, and some initial experiments are described. We also discuss other novel capabilities of our system: interaction at a distance using IR pointing devices, and IR-based communication with other electronic devices through the display. A major advantage of ThinSight over existing camera and projector based optical systems is its compact, thin form-factor making such systems even more deployable. We therefore envisage using ThinSight to capture rich sensor data through the display which can be processed using computer vision techniques to enable both multi-touch and tangible interaction.
Current asynchronous voice messaging interfaces, like voicemail, fail to take advantage of our conversational skills. TalkBack restores conversational turn-taking to voicemail retrieval by dividing voice messages into smaller sections based on the most significant silent and filled pauses and pausing after each to record a response. The responses are composed into a reply, alternating with snippets of the original message for context. TalkBack is built into a digital picture frame; the recipient touches a picture of the caller to hear each segment of the message in turn. The minimal interface models synchronous interaction and facilitates asynchronous voice messaging. TalkBack can also present a voice-annotated slide show which it receives over the Internet.
GELO is a package that supports the interactive graphical display of software systems. Its features include built-in panning and zooming, abstraction of objects too small to see, pick correlation, windowing, and scroll bars. GELO creates a hierarchy of graphical objects that correspond to the components of the structure being displayed. Five flavors of graphical objects are supported, including those for simple structures, tiled layouts, and graph-based layouts. This framework is powerful enough to handle a wide variety of graphical visualizations, and it is general enough that new object flavors can be smoothly integrated in the future.GELO is easy to learn and to use, and is presently employed in two software development environments. Among its current applications are a variety of visual languages, an interactive display of call graphs, an interactive display of data structures, and a graphical representation of module dependencies.
When teaching programming or hardware design, it is pedagogically valuable for students to generate examples of functions, circuits, or system designs. Teachers can be overwhelmed by these types of student submissions when running large residential or recently released massive online courses. The underlying distribution of student solutions submitted in response to a particular assignment may be complex, but the newly available volume of student solutions represents a denser sampling of that distribution. Working with large datasets of students' solutions, I am building systems with user interfaces that allow teachers to explore the variety of their students' correct and incorrect solutions. Forum posts, grading rubrics, and automatic graders can be based on student solution data, and turn massive engineering and computer science classrooms into useful insight and feedback for teachers. In the development process, I hope to describe essential design principles for such systems.
One of the challenges with using mobile touch-screen devices is that they do not provide tactile feedback to the user. Thus, the user is required to look at the screen to interact with these devices. In this paper, we present SemFeel, a tactile feedback system which informs the user about the presence of an object where she touches on the screen and can offer additional semantic information about that item. Through multiple vibration motors that we attached to the backside of a mobile touch-screen device, SemFeel can generate different patterns of vibration, such as ones that flow from right to left or from top to bottom, to help the user interact with a mobile device. Through two user studies, we show that users can distinguish ten different patterns, including linear patterns and a circular pattern, at approximately 90% accuracy, and that SemFeel supports accurate eyes-free interactions.
Multiplayer virtual reality (VR) games introduce the problem of variations in the physical size and shape of each user's space for mapping into a shared virtual space. We propose an asymmetric approach to solve the spatial variation problem, by allowing people to choose roles based on the size of their space. We demonstrate this concept through the implementation of a virtual snowball fight where players can choose from multiple roles, namely the shooter, the target, or an onlooker depending on whether the game is played remotely or together in one large space. In the co-located version, the target stands behind an actuated cardboard fort that responds to events in VR, providing non-VR spectators a way to participate in the experience. During preliminary deployment, users showed extremely positive reactions and the spectators were thrilled.

Example

LLooM Logo

Outputs

Select seed. The seed term can steer concept induction towards more specific areas of interest. Try out one of the options below:

ExperimentalValidationInformalFeedbackPerformanceMetricsAlgorithmEvaluation020↑ Number of documents

Experimental Validation

Criteria: Does the example involve experimental validation to measure system performance or accuracy?

Summary: Our experiments and user studies validate the effectiveness and feasibility of various interactive technologies and systems.

Informal Feedback

Criteria: Is informal feedback or evaluation from users or researchers mentioned?

Summary: Informal feedback from users and researchers positively influences the development and evaluation of various interactive systems.

Performance Metrics

Criteria: Does the text example detail specific performance metrics or outcomes from an evaluation?

Summary: We demonstrate various performance metrics improvements in VR, animation creation, data visualization, user interaction, software development, and motion recognition.

Algorithm Evaluation

Criteria: Does this text discuss evaluating an algorithm's performance or effectiveness?

Summary: Evaluation methods such as controlled experiments and user studies are crucial for assessing algorithm performance and user interaction.

Analysis

➡️ Try out analyzing this data with LLooM on this Colab notebook.

LLooM, Academic Paper Abstracts Notebook

Task: Explore a research community's interests and impact

What impact has HCI research had on industry? A recent large-scale measurement study from Cao et al. investigated HCI's influence on industry through the lens of patent citations. This prior work used LDA topics to describe trends among research that influenced patents. We can use LLooM to characterize research from the past 30 years and further explore the connections between HCI research topics, methods, and industry impact.

Dataset: ACM UIST paper abstracts, 1989-2018

We use the dataset from this prior research, which consists of paper abstracts from major HCI venues (CHI, CSCW, UIST, and UbiComp) from 1989 to 2018. We filter to UIST papers because they displayed an extremely outsized proportion of patent citations. We sought to better understand the nature of UIST research over time and potential factors underlying its high industry impact. To aid comparisons across time periods, we gathered a stratified random sample across each decade from 1989-1998, 1999-2008, and 2009-2018 with 70 papers from each decade for a total sample of 210 papers for this exploratory analysis.