Browsing by Author "Butler, Patrick Julian Carey"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Designing Human-Centered Collaborative Systems for School Redistricting
    Sistrunk, Virginia Andreea (Virginia Tech, 2024-07-24)
    In a multitude of nations, the provision of education is predominantly facilitated through public schooling systems. These systems are structured in accordance with school districts, which are geographical territories where educational institutions share identical administrative frameworks and frequently coincide with the confines of a city or county. To enhance the operational efficiency of these schooling systems, the demarcations of public schools undergo periodic modifications. This procedure, also known as school redistricting, invariably engenders a myriad of tensions within the associated communities. This dissertation addresses the potential and necessity to integrate geographically-enabled crowd-sourced input into the redistricting process, and concurrently presents and evaluates a feasible solution. The pivotal contributions of this dissertation encompass: i) the delineation of the interdisciplinary sub-field at the nexus of HCI, CSCW, and education policy, ii) the identification of requirements from participants proficient in traditional, face-to-face deliberations, representing a diverse array of stakeholder groups, iii) the conception of a self-serve interactive boundary optimization system, and iv) a comprehensive user study conducted during a live public school rezoning deliberation utilizing the newly proposed hybrid approach. The live study specifically elucidates the efficacy of key design choices and the representation and rationalization of intricate user constraints in civic deliberations and educational policy architecture. My research looks into four primary areas of exploration: (i) the application of computer science usability-design principles to augment and expedite the visual deconstruction of intricate multi-domain data, thereby enhancing comprehension for novice users, (ii) the identification of salient elements of experiential learning within the milieu of visual scaffolding, (iii) the development of a preliminary platform designed to expand the capacity for crowd-sourcing novice users in the act of reconciling geo-spatial constraints, and finally, (iv) the utilization of Human-Computer Interaction (HCI) and data-driven analysis to discern, consolidate, and inaugurate novel communication channels that foster the restoration of trust within communities. To do so, I analyzed the previous work that was done in the domain, proposed a new direction, and created a web-application, called Redistrict. This an on-line platform allows the user to generate and explore "what if" scenarios, express opinions, and participate asynchronously in proximity-based public school boundary deliberations. I first evaluated the perceived value added by Redistrict through a user study with 12 participants experienced in traditional in-person deliberations, representing multiple stakeholder groups. Subsequently, I expanded the testing to an online rezoning. As a result of all interactions and the use of the web application, the participants reported a better understanding of geographically enabled projections, proposals from public officials, and increased consideration of how difficult it is to balance multidisciplinary constraints. Here, I present the design possibilities used and the effective online aid for the issue of public school rezoning deliberations and redistricting. This data-driven approach aids the school board and decision makers by offering automated strategies, a straightforward, visual, and intuitive method to comprehend intricate geographical limitations. The users demonstrated the ability to navigate the interface without iii any previous training or explanation. In this work, I propose the following three new concepts: (i) A new interdisciplinary subfield for Human Computing Interaction -Computer Supported Cooperative Work that combines Computer Science, Geography, and Education Policy. We explain and demonstrate how single domain approach failed in supporting this field and how complex geo-spatial problems require intensive technology to simultaneously balance all education policy constraints. This sits only at the intersection of a multi-domain approach. (ii) A sophisticated deconstruction of intricate data sets is presented through this methodology. It enables users to assimilate, comprehend, and formulate decisions predicated on the information delineated on a geospatial representation, leveraging preexisting knowledge of geographical proximity, and engaging in scenario analysis. Each iterative attempt facilitates incremental understanding, epitomizing the concept of information scaffolding. The efficacy of this process is demonstrated by its ability to foster independent thought and comprehension, obviating the need for explicit instructions. This technique is henceforth referred to as 'visual scaffolding'. (iii) In our most recent investigation, we engage in an introspective analysis of the observed input in civic decision making. We present the proposition of integrating digital civic engagement with user geolocation data. We advocate for the balance of this input, as certain geographical areas may be disproportionately represented in civic deliberations. The introduction of a weighting mechanism could facilitate a deeper understanding of the foundational premises on which civic decisions are based. We coin the term 'digital geo-civics' to characterize this pioneering approach.
  • Thumbnail Image
    Information Extraction of Technical Details From Scholarly Articles
    Kaushal, Kulendra Kumar (Virginia Tech, 2021-06-16)
    Researchers have made significant progress in information extraction from short documents in the last few years, including social media interaction, news articles, and email excerpts. This research aims to extract technical entities like hardware resources, computing platforms, compute time, programming language, and libraries from scholarly research articles. Research articles are generally long documents having both salient as well as non-salient entities. Analyzing the cross-sectional relation, filtering the relevant information, measuring the saliency of mentioned entities, and extracting novel entities are some of the technical challenges involved in this research. This work presents a detailed study about the performance, effectiveness, and scalability of rule-based weakly supervised algorithms. We also develop an automated end-to-end Research Entity and Relationship Extractor (E2R Extractor). Additionally, we perform a comprehensive study about the effectiveness of existing deep learning-based information extraction tools like Dygie, Dygie++, SciREX. The research also contributes a dataset containing novel entities annotated in BILUO format and represents the baseline results using the E2R extractor on the proposed dataset. The results indicate that the E2R extractor successfully extracts salient entities from research articles.
  • Thumbnail Image
    Knowledge Discovery in Intelligence Analysis
    Butler, Patrick Julian Carey (Virginia Tech, 2014-06-03)
    Intelligence analysts today are faced with many challenges, chief among them being the need to fuse disparate streams of data, as well as rapidly arrive at analytical decisions and quantitative predictions for use by policy makers. These problems are further exacerbated by the sheer volume of data that is available to intelligence analysts. Machine learning methods enable the automated transduction of such large datasets from raw feeds to actionable knowledge but successful use of such methods require integrated frameworks for contextualizing them within the work processes of the analyst. Intelligence analysts typically distinguish between three classes of problems: collections, analysis, and operations. This dissertation specifically focuses on two problems in analysis: i) the reconstruction of shredded documents using a visual analytic framework combining computer vision techniques and user input, and ii) the design and implementation of a system for event forecasting which allows an analyst to not just consume forecasts of significant societal events but also understand the rationale behind these alerts and the use of data ablation techniques to determine the strength of conclusions. This work does not attempt to replace the role of the analyst with machine learning but instead outlines several methods to augment the analyst with machine learning. In doing so this dissertation also explores the responsibilities of an analyst in evaluating complex models and decisions made by these models. Finally, this dissertation defines a list of responsibilities for models designed to aid the analyst's work in evaluating and verifying the models.