arXiv subjects

Matthew Butler

Publications and source records attributed to Matthew Butler.

At least 19 recordsLinked to original sources

arXiv2026

Conversational Tactile Data Interfaces: Co-Designing Accessible Data Experiences with Blind Users Using Refreshable Tactile Displays and Conversational AI

Combining refreshable tactile displays (RTDs) with conversational AI offers a promising approach to accessible data visualization for people who are blind or have low vision (BLV). However, it remains an open question how these modalities should be integrated to support accessible data experiences. We address this through a co-design process with three BLV co-designers. Building on our prior Wizard-of-Oz study, we created a conversational tactile data interface (CTDI) that combines an RTD with an LLM-powered conversational agent, refined through four workshops over eight months. In addition to the resulting system, Graphy, we contribute design knowledge and recommendations for CTDIs. Co-designers used touch as the primary sensemaking channel for spatial understanding of the data's shape, trends, and relationships, reserved the agent for what touch could not resolve (e.g., calculation and analysis), and used the chart on the RTD to verify the agent's responses. Key findings include: a layered presentation that scaffolds chart exploration through progressive, interactive layers; a feedback grammar that distinguishes user- and agent-initiated tactile feedback; and a sequential interaction pattern -- select, confirm, ask, verify -- where each step grounds the last.

cs.HC↗

arXiv2026

FraudFox: Adaptable Fraud Detection in the Real World

The proposed method (FraudFox) provides solutions to adversarial attacks in a resource constrained environment. We focus on questions like the following: How suspicious is `Smith', trying to buy \$500 shoes, on Monday 3am? How to merge the risk scores, from a handful of risk-assessment modules (`oracles') in an adversarial environment? More importantly, given historical data (orders, prices, and what-happened afterwards), and business goals/restrictions, which transactions, like the `Smith' transaction above, which ones should we `pass', versus send to human investigators? The business restrictions could be: `at most $x$ investigations are feasible', or `at most \$$y$ lost due to fraud'. These are the two research problems we focus on, in this work. One approach to address the first problem (`oracle-weighting'), is by using Extended Kalman Filters with dynamic importance weights, to automatically and continuously update our weights for each 'oracle'. For the second problem, we show how to derive an optimal decision surface, and how to compute the Pareto optimal set, to allow what-if questions. An important consideration is adaptation: Fraudsters will change their behavior, according to our past decisions; thus, we need to adapt accordingly. The resulting system, \method, is scalable, adaptable to changing fraudster behavior, effective, and already in \textbf{production} at Amazon. FraudFox augments a fraud prevention sub-system and has led to significant performance gains.

cs.CR↗

arXiv2026

Supporting Multimodal Data Interaction on Refreshable Tactile Displays: An Architecture to Combine Touch and Conversational AI

Combining conversational AI with refreshable tactile displays (RTDs) offers significant potential for creating accessible data visualization for people who are blind or have low vision (BLV). To support researchers and developers building accessible data visualizations with RTDs, we present a multimodal data interaction architecture along with an open-source reference implementation. Our system is the first to combine touch input with a conversational agent on an RTD, enabling deictic queries that fuse touch context with spoken language, such as "what is the trend between these points?" The architecture addresses key technical challenges, including touch sensing on RTDs, visual-to-tactile encoding, integrating touch context with conversational AI, and synchronizing multimodal output. Our contributions are twofold: (1) a technical architecture integrating RTD hardware, external touch sensing, and conversational AI to enable multimodal data interaction; and (2) an open-source reference implementation demonstrating its feasibility. This work provides a technical foundation to support future research in multimodal accessible data visualization.

cs.HC↗

arXiv2025

WRAVAL -- WRiting Assist eVALuation

The emergence of Large Language Models (LLMs) has shifted language model evaluation toward reasoning and problem-solving tasks as measures of general intelligence. Small Language Models (SLMs) -- defined here as models under 10B parameters -- typically score 3-4 times lower than LLMs on these metrics. However, we demonstrate that these evaluations fail to capture SLMs' effectiveness in common industrial applications, such as tone modification tasks (e.g., funny, serious, professional). We propose an evaluation framework specifically designed to highlight SLMs' capabilities in non-reasoning tasks where predefined evaluation datasets don't exist. Our framework combines novel approaches in data generation, prompt-tuning, and LLM-based evaluation to demonstrate the potential of task-specific finetuning. This work provides practitioners with tools to effectively benchmark both SLMs and LLMs for practical applications, particularly in edge and private computing scenarios. Our implementation is available at: https://github.com/amazon-science/wraval.

cs.CL↗

arXiv2025

From Vision to Touch: Bridging Visual and Tactile Principles for Accessible Data Representation

Tactile graphics are widely used to present maps and statistical diagrams to blind and low vision (BLV) people, with accessibility guidelines recommending their use for graphics where spatial relationships are important. Their use is expected to grow with the advent of commodity refreshable tactile displays. However, in stark contrast to visual information graphics, we lack a clear understanding of the benefits that well-designed tactile information graphics offer over text descriptions for BLV people. To address this gap, we introduce a framework considering the three components of encoding, perception and cognition to examine the known benefits for visual information graphics and explore their applicability to tactile information graphics. This work establishes a preliminary theoretical foundation for the tactile-first design of information graphics and identifies future research avenues.

cs.HC↗

arXiv2025

Accessible Data Access and Analysis by People who are Blind or Have Low Vision

Our work aims to develop new assistive technologies that enable blind or low vision (BLV) people to explore and analyze data readily. At present, barriers exist for BLV people to explore and analyze data, restricting access to government, health and personal data, and limiting employment opportunities. This work explores the co-design and development of an innovative system to support data access, with a focus on the use of refreshable tactile displays (RTDs) and conversational agents. The envisaged system will use a combination of tactile graphics and speech to communicate with BLV users, and proactively assist with data analysis tasks. As well as addressing significant equity gaps, our work expects to produce innovations in assistive technology, multimodal interfaces, dialogue systems, and natural language understanding and generation.

cs.HC↗

arXiv2025

Using AI to Summarize US Presidential Campaign TV Advertisement Videos, 1952-2012

This paper introduces the largest and most comprehensive dataset of US presidential campaign television advertisements, available in digital format. The dataset also includes machine-searchable transcripts and high-quality summaries designed to facilitate a variety of academic research. To date, there has been great interest in collecting and analyzing US presidential campaign advertisements, but the need for manual procurement and annotation led many to rely on smaller subsets. We design a large-scale parallelized, AI-based analysis pipeline that automates the laborious process of preparing, transcribing, and summarizing videos. We then apply this methodology to the 9,707 presidential ads from the Julian P. Kanter Political Commercial Archive. We conduct extensive human evaluations to show that these transcripts and summaries match the quality of manually generated alternatives. We illustrate the value of this data by including an application that tracks the genesis and evolution of current focal issue areas over seven decades of presidential elections. Our analysis pipeline and codebase also show how to use LLM-based tools to obtain high-quality summaries for other video datasets.

cs.MM↗

arXiv2025

Sensing Movement: Contemporary Dance Workshops with People who are Blind or have Low Vision and Dance Teachers

Dance teachers rely primarily on verbal instructions and visual demonstrations to convey key dance concepts and movement. These techniques, however, have limitations in supporting students who are blind or have low vision (BLV). This work explores the role technology can play in supporting instruction for BLV students, as well as improvisation with their instructor. Through a series of design workshops with dance instructors and BLV students, ideas were generated by physically engaging with probes featuring diverse modalities including tactile objects, a body tracked sound and musical probe, and a body tracked controller with vibrational feedback. Implications for the design of supporting technologies were discovered for four contemporary dance learning goals: learning a phrase; improvising; collaborating through movement; and awareness of body and movement qualities. We discuss the potential of numerous multi-sensory methods and artefacts, and present design considerations for technologies to support meaningful dance instruction and participation.

cs.HC↗

arXiv2025

"It Brought the Model to Life": Exploring the Embodiment of Multimodal I3Ms for People who are Blind or have Low Vision

3D-printed models are increasingly used to provide people who are blind or have low vision (BLV) with access to maps, educational materials, and museum exhibits. Recent research has explored interactive 3D-printed models (I3Ms) that integrate touch gestures, conversational dialogue, and haptic vibratory feedback to create more engaging interfaces. Prior research with sighted people has found that imbuing machines with human-like behaviours, i.e., embodying them, can make them appear more lifelike, increasing social perception and presence. Such embodiment can increase engagement and trust. This work presents the first exploration into the design of embodied I3Ms and their impact on BLV engagement and trust. In a controlled study with 12 BLV participants, we found that I3Ms using specific embodiment design factors, such as haptic vibratory and embodied personified voices, led to an increased sense of liveliness and embodiment, as well as engagement, but had mixed impact on trust.

cs.HC↗

arXiv2025

3D Printed Maps and Icons for Inclusion: Testing in the Wild by People who are Blind or have Low Vision

The difficulty and consequent fear of travel is one of the most disabling consequences of blindness and severe vision impairment, affecting confidence and quality of life. Traditional tactile graphics are vital in the Orientation and Mobility training process, however 3D printing may have the capacity to enable production of more meaningful and inclusive maps. This study explored the use of 3D printed maps on site at a public event to examine their suitability and to identify guidelines for the design of future 3D maps. An iterative design process was used in the production of the 3D maps, with feedback from visitors who are blind or have low vision informing the recommendations for their design and use. For example, it was found that many representational 3D icons could be recognised by touch without the need for a key and that such a map helped form mental models of the event space. Complex maps, however, require time to explore and should be made available before an event or at the entrance in a comfortable position. The maps were found to support the orientation and mobility process, and importantly to also promote a positive message about inclusion and accessibility.

cs.HC↗

arXiv2024

Understanding Challenges and Opportunities in Body Movement Education of People who are Blind or have Low Vision

Actively participating in body movement such as dance, sports, and fitness activities is challenging for people who are blind or have low vision (BLV). Teachers primarily rely on verbal instructions and physical demonstrations with limited accessibility. Recent work shows that technology can support body movement education for BLV people. However, there is limited involvement with the BLV community and their teachers to understand their needs. By conducting a series of two surveys, 23 interviews and four focus groups, we gather the voices and perspectives of BLV people and their teachers. This provides a rich understanding of the challenges of body movement education. We identify ten major themes, four key design challenges, and propose potential solutions. We encourage the assistive technologies community to co-design potential solutions to these identified design challenges promoting the quality of life of BLV people and supporting the teachers in the provision of inclusive education.

cs.HC↗

arXiv2024

When Refreshable Tactile Displays Meet Conversational Agents: Investigating Accessible Data Presentation and Analysis with Touch and Speech

Despite the recent surge of research efforts to make data visualizations accessible to people who are blind or have low vision (BLV), how to support BLV people's data analysis remains an important and challenging question. As refreshable tactile displays (RTDs) become cheaper and conversational agents continue to improve, their combination provides a promising approach to support BLV people's interactive data exploration and analysis. To understand how BLV people would use and react to a system combining an RTD with a conversational agent, we conducted a Wizard-of-Oz study with 11 BLV participants, where they interacted with line charts, bar charts, and isarithmic maps. Our analysis of participants' interactions led to the identification of nine distinct patterns. We also learned that the choice of modalities depended on the type of task and prior experience with tactile graphics, and that participants strongly preferred the combination of RTD and speech to a single modality. In addition, participants with more tactile experience described how tactile images facilitated a deeper engagement with the data and supported independent interpretation. Our findings will inform the design of interfaces for such interactive mixed-modality systems.

cs.HC↗

arXiv2024

TactIcons: Designing 3D Printed Map Icons for People who are Blind or have Low Vision

Visual icons provide immediate recognition of features on print maps but do not translate well for touch reading by people who are blind or have low vision due to the low fidelity of tactile perception. We explored 3D printed icons as an equivalent to visual icons for tactile maps addressing these problems. We designed over 200 tactile icons (TactIcons) for street and park maps. These were touch tested by blind and sighted people, resulting in a corpus of 33 icons that can be recognised instantly and a further 34 icons that are easily learned. Importantly, this work has informed the creation of detailed guidelines for the design of TactIcons and a practical methodology for touch testing new TactIcons. It is hoped that this work will contribute to the creation of more inclusive, user-friendly tactile maps for people who are blind or have low vision.

cs.HC↗

arXiv2024

Design Considerations for Automatic Musical Soundscapes of Visual Art for People with Blindness or Low Vision

Music has been identified as a promising medium to enhance the accessibility and experience of visual art for people who are blind or have low vision (BLV). However, composing music and designing soundscapes for visual art is a time-consuming, resource intensive process - limiting its scalability for large exhibitions. In this paper, we investigate the use of automated soundscapes to increase the accessibility of visual art. We built a prototype system and ran a qualitative study to evaluate the aesthetic experience provided by the automated soundscapes with 10 BLV participants. From the study, we identified a set of design considerations that reveal requirements from BLV people for the development of automated soundscape systems, setting new directions in which creative systems could enrich the aesthetic experience conveyed by these.

cs.HC↗

arXiv2024

Refreshable Tactile Displays for Accessible Data Visualisation

Refreshable tactile displays (RTDs) are predicted to soon become a viable option for the provision of accessible graphics for people who are blind or have low vision (BLV). This new technology for the tactile display of braille and graphics, usually using raised pins, makes it easier to generate and access a large number of graphics. However, it differs from existing tactile graphics in terms of scale, height and fidelity. Here, we share the perspectives of four key stakeholders -- blind touch readers, vision specialist teachers, accessible format producers and assistive technology providers -- to explore the potential uses, advantages and needs relating to the introduction of RTDs. We also provide advice on what role the data visualisation community can take to help ensure that people who are BLV are best able to benefit from the introduction of affordable RTDs.

cs.HC↗

arXiv2023

Designing Conversational Multimodal 3D Printed Models with People who are Blind

3D printed models have been used to improve access to graphical information by people who are blind, offering benefits over conventional accessible graphics. Here we investigate an interactive 3D printed model (I3M) that combines a conversational interface with haptic vibration and touch to provide more natural and accessible experiences. Specifically, we co-designed a multimodal model of the Solar System with nine blind people and evaluated the prototype with another seven blind participants. We discuss our journey from a design perspective, focusing on touch, conversational and multimodal interactions. Based on our experience, we suggest design recommendations that consider blind users' desire for independence and control, customisation, comfort and use of prior experience

cs.HC↗

arXiv2021

Technology Developments in Touch-Based Accessible Graphics: A Systematic Review of Research 2010-2020

This paper presents a systematic literature review of 292 publications from 97 unique venues on touch-based graphics for people who are blind or have low vision, from 2010 to mid-2020. It is the first review of its kind on touch-based accessible graphics. It is timely because it allows us to assess the impact of new technologies such as commodity 3D printing and low-cost electronics on the production and presentation of accessible graphics. As expected our review shows an increase in publications from 2014 that we can attribute to these developments. It also reveals the need to: broaden application areas, especially to the workplace; broaden end-user participation throughout the full design process; and conduct more in situ evaluation. This work is linked to an online living resource to be shared with the wider community.

cs.HC↗

arXiv2020

"Hey Model!" - Natural User Interactions and Agency in Accessible Interactive 3D Models

While developments in 3D printing have opened up opportunities for improved access to graphical information for people who are blind or have low vision (BLV), they can provide only limited detailed and contextual information. Interactive 3D printed models (I3Ms) that provide audio labels and/or a conversational agent interface potentially overcome this limitation. We conducted a Wizard-of-Oz exploratory study to uncover the multi-modal interaction techniques that BLV people would like to use when exploring I3Ms, and investigated their attitudes towards different levels of model agency. These findings informed the creation of an I3M prototype of the solar system. A second user study with this model revealed a hierarchy of interaction, with BLV users preferring tactile exploration, followed by touch gestures to trigger audio labels, and then natural language to fill in knowledge gaps and confirm understanding.

cs.HC↗