<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:dc="http://purl.org/dc/elements/1.1/" version="2.0">
  <channel>
    <title>BURA Collection:</title>
    <link>http://bura.brunel.ac.uk/handle/2438/210</link>
    <description />
    <pubDate>Sun, 19 Apr 2026 08:55:30 GMT</pubDate>
    <dc:date>2026-04-19T08:55:30Z</dc:date>
    <item>
      <title>Artificial Intelligence &amp; Human-Computer Interaction: The development and deployment of emotionally intelligent, LLM-augmented conversational agent software, utilising generative AI to improve pedagogical and educational management processes</title>
      <link>http://bura.brunel.ac.uk/handle/2438/32953</link>
      <description>Title: Artificial Intelligence &amp; Human-Computer Interaction: The development and deployment of emotionally intelligent, LLM-augmented conversational agent software, utilising generative AI to improve pedagogical and educational management processes
Authors: Yusuf, Habeebullah
Abstract: Background: Viva voce examinations, a form of performance-based assessment (PBA), are valued for their ability to elicit deep insights into student understanding and oral articulation. However, they are often associated with challenges such as increased student anxiety, examiner inconsistency and high teacher workload. While artificial intelligence (AI) has seen broad adoption in education, its application in oral assessments remains limited and underexplored. &#xD;
Objectives: This research investigates the use of emotionally responsive AI conversational agents to address key challenges in formative viva assessments. It aims to develop two such agents; AIvaluate (a teacher-mediated agent) and AIvaluate2 (a fully autonomous agent), and evaluate their impact on student anxiety, teacher burden, assessment quality and student experience. &#xD;
Methods: The research follows a Design Science Research (DSR) methodology and employs the Rapid Application Development (RAD) framework for iterative prototyping. Four empirical studies were conducted in an education setting using a mixed-methods approach. Data collection methods included real-time emotional self-reporting, System Usability Scale (SUS), feedback quality scoring, grade comparisons, surveys and semi-structured interviews. Quantitative data was analysed using statistical methods such as paired-sample comparisons and TOST equivalence testing. Qualitative data was subjected to reflexive thematic analysis. &#xD;
Results: Findings suggest that AIvaluate successfully reduced student anxiety and teacher workload during assessments. AIvaluate2 enhanced perceptions of assessment credibility, fairness and usability, contributing to a more emotionally supportive and consistent student experience. However, certain limitations, such as the absence of human-like empathy and rapport were noted in AI-led formats. &#xD;
Contributions: This thesis contributes: &#xD;
1. A conceptual framework for categorising pedagogical AI conversational agents.                                                                   2. Empirical evidence supporting the educational utility of LLM-augmented AI conversational agents in oral assessments.&#xD;
3. Two validated AI software artefacts (AIvaluate and AIvaluate2) designed for formative viva use.&#xD;
4. Insights into the role of emotional responsiveness and usability in AI-led assessment environments.                    Conclusion: The study advances the application of AI in education by demonstrating how emotionally intelligent conversational agents can reduce affective and operational barriers in formative oral assessments. It offers practical, scalable tools for AI-enabled pedagogy with implications for further and higher education contexts.
Description: This thesis was submitted for the award of Doctor of Philosophy and was awarded by Brunel University London</description>
      <pubDate>Wed, 01 Jan 2025 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">http://bura.brunel.ac.uk/handle/2438/32953</guid>
      <dc:date>2025-01-01T00:00:00Z</dc:date>
    </item>
    <item>
      <title>A novel approach to automating context-driven alternative text generation through purposeful games</title>
      <link>http://bura.brunel.ac.uk/handle/2438/32758</link>
      <description>Title: A novel approach to automating context-driven alternative text generation through purposeful games
Authors: Droutsas, Nikolaos
Abstract: Accessibility of the Web is a pervasive issue, owing to the persistence of accessibility barriers (e.g., poor navigation, lack of/unsuitable alternative text (alt text), complex web forms), with significant impact on users with disabilities. Alt text barriers in particular, are some of the most prevalent web accessibility barriers affecting a wide range of media and are underpinned by a lack of understanding and guidelines on what constitutes suitable alt text. Past work has shown that the ‘context in which the image is used in’ is ironclad for suitability yet loosely defined. Whilst there is a need to automate alt text generation, current solutions disregard context in alt text and are lacklustre with regard to suitability. In this research, an empirical exploratory study that investigates the views of web content creators and visually impaired users on suitability is conducted to bridge the functional gap between experiences and best available practice. The first definition of ‘Alt Text Context’ is proposed providing a systematic way to assess when alt text is necessary and what it should convey. Further, the first crowdsourcing game for context-driven alt text authorship and evaluation—TagALTlong—is presented. TagALTlong’s design is informed by relevant literature, empirical qualitative insights and the proposed definition of context in alt text. Following an empirical user study, 125 non-expert players were recruited to play TagALTlong over a six-week period, resulting in 1208 authored and 1836 rated alt text descriptions, respectively. The resulting dataset was used to fine-tune and train an AI model for automated alt text generation to assess whether average human-level alt text quality can be approximated whilst automating the process. Results indicated the improved performance of the model that was fine-tuned and trained on the GWAP-generated dataset compared to pure image processing, subsequently demonstrating the value of the dataset.
Description: This thesis was submitted for the award of Doctor of Philosophy and was awarded by Brunel University London</description>
      <pubDate>Thu, 01 Jan 2026 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">http://bura.brunel.ac.uk/handle/2438/32758</guid>
      <dc:date>2026-01-01T00:00:00Z</dc:date>
    </item>
    <item>
      <title>Transparency and accountability in government payment systems: Financial transfers in the social security office of Thailand</title>
      <link>http://bura.brunel.ac.uk/handle/2438/31897</link>
      <description>Title: Transparency and accountability in government payment systems: Financial transfers in the social security office of Thailand
Authors: Satjawisate, Saiphit
Abstract: Despite the growing adoption of cash and digital money for government payments,&#xD;
implementing digital payment systems can face acceptance issues such as&#xD;
transparency shortcomings, service delays and accessibility problems that undermine&#xD;
public trust in government payment systems. Across the world, government agencies&#xD;
have begun using digital technologies such as digital payment and e-services to boost&#xD;
public confidence in their financial operations. These steps are, in large part, intended&#xD;
to reduce corruption and improve government services through increased transparency&#xD;
and accountability (T&amp;A). The Social Security Office (SSO) in Thailand is one such&#xD;
organization that has taken this route and has emphasized financial disclosure in order&#xD;
to improve T&amp;A in its claims processes. The intention of this is to empower insured&#xD;
people through feedback channels that foster trust in the payment process.&#xD;
The core objective of this research is to explore the influences that enhance T&amp;A in&#xD;
benefit payment systems. Despite the growing focus on enhancing T&amp;A to bolster&#xD;
credibility among government agencies, the role of T&amp;A and the ways to improve T&amp;A&#xD;
in government payments remain unclear. To address this gap, this thesis reports a study&#xD;
to investigate collaborative work in the payment system and then explores T&amp;A within&#xD;
the benefit payment activities by interpreting participants’ experience of claims in the&#xD;
Thai SSO. The thesis draws on a narrative approach with in-depth interviews in two data&#xD;
collection studies. The first study interviewed insured persons and government officers&#xD;
to understand the work involved in enabling social security payments. We found that&#xD;
although the demand for digital G2P payment systems has increased, some claims were&#xD;
still processed via paper documentation and cash payments due to the inaccessibility of&#xD;
digital services to some claimants. The key finding was the selection of payment&#xD;
methods to facilitate individuals lacking access to the banking system by offering&#xD;
compensation in cash or a postal order instead of digital transfers. Such findings&#xD;
highlight the importance of accommodating diverse needs and circumstances, ensuring&#xD;
that access to essential services remains inclusive and equitable.&#xD;
Building on our understanding of the benefit payment process, we further explored T&amp;A&#xD;
processes and practices within the payment system in a second interview study of public officers and insured persons. These findings reveal the potential T&amp;A in the SSO back&#xD;
and front office systems, which can improve the SSO's work performance and citizen&#xD;
trust in their payment decisions. 'Back-office systems' primarily handle internal&#xD;
processes such as claim processing, while 'front-office systems' directly involve insured&#xD;
person interactions. Data and information generated by back-office systems flow&#xD;
towards front-office operations to facilitate citizens' service and responsiveness, such&#xD;
as SSO regulations and tracking claims. However, attracting citizens to engage with&#xD;
information and services solely through digital platforms posed a significant challenge&#xD;
for the SSO. Hence, social influence surrounding insured persons emerged as a crucial&#xD;
driving force. Furthermore, tracking payment records and incorporating citizen feedback&#xD;
regarding complaints and expressions of opinions about the SSO services fostered a&#xD;
culture of accountability and responsiveness within the organization, ultimately&#xD;
contributing to a more effective T&amp;A mechanisms in the SSO payment service delivery.&#xD;
The outcomes of this research provide contextualized illustrations of the role of T&amp;A in&#xD;
SSO activities and identify T&amp;A guidelines for researchers and designers so that the&#xD;
needs of public officers and insured persons can be foregrounded in the analysis and&#xD;
development of future payment systems. This thesis leverages the findings to discuss&#xD;
research implications regarding systems design and use, and in determining appropriate&#xD;
policy for the design of social security benefit payment systems and services, and egovernment&#xD;
payment systems.
Description: This thesis was submitted for the award of Doctor of Philosophy and was awarded by Brunel University London</description>
      <pubDate>Wed, 01 Jan 2025 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">http://bura.brunel.ac.uk/handle/2438/31897</guid>
      <dc:date>2025-01-01T00:00:00Z</dc:date>
    </item>
    <item>
      <title>Blockchain Financial Statements (BFS): A transaction to financial statements accounting system for central bank to business liquidity</title>
      <link>http://bura.brunel.ac.uk/handle/2438/31505</link>
      <description>Title: Blockchain Financial Statements (BFS): A transaction to financial statements accounting system for central bank to business liquidity
Authors: Dashkevich, Natalia
Abstract: This thesis introduces the concept of Blockchain Financial Statements (BFS), an innovative accounting&#xD;
system designed to bridge the liquidity needs between central banks and businesses&#xD;
through blockchain technology. The focus lies on streamlining the transaction to financial statement&#xD;
processes in a secure, transparent and efficient manner.&#xD;
Context: Amidst evolving financial landscapes and the pressing need for more robust financial&#xD;
reporting mechanisms, the BFS framework emerges as a solution to enhance the liquidity management&#xD;
between central banks and businesses, underpinned by a more direct and verifiable approach&#xD;
to financial transactions and reporting.&#xD;
Aim: The primary goal of this research is to design, develop and validate a blockchain-based&#xD;
accounting prototype - the BFS - that can transform traditional transaction data into comprehensive&#xD;
financial statements, facilitating central bank to business liquidity in a secure and efficient&#xD;
manner.&#xD;
Methods: Employing a Design Science Research Methodology, this study constructs a BFS&#xD;
artefact, incorporating Domain-Driven Design to architect a system that harmonises with accounting&#xD;
standards, blockchain technology and business orchestration. The validation of the BFS artefact&#xD;
is conducted through a simulated environment, reflecting real-world transactional and accounting&#xD;
operations.&#xD;
Results: The Java PoC implementation of BFS demonstrates a successful integration of&#xD;
blockchain technology into accounting practices, showing potential in real-time validation of transactions,&#xD;
immutable record-keeping and enhancing the transparency and efficiency of financial reporting.&#xD;
Conclusion: The BFS framework and its PoC artefact, signifies an advancement in the application&#xD;
of blockchain technology for financial reporting and liquidity management. It offers a&#xD;
functional solution for enhancing transparency, accuracy and efficiency of financial transactions&#xD;
between central banks and businesses. The research underlines the necessity for further exploration&#xD;
into blockchain’s potential within accounting systems, suggesting a promising direction for&#xD;
future innovations in financial reporting and liquidity management.
Description: This thesis was submitted for the award of Doctor of Philosophy and was awarded by Brunel University London</description>
      <pubDate>Wed, 01 Jan 2025 00:00:00 GMT</pubDate>
      <guid isPermaLink="false">http://bura.brunel.ac.uk/handle/2438/31505</guid>
      <dc:date>2025-01-01T00:00:00Z</dc:date>
    </item>
  </channel>
</rss>

