Matching Items (743)
Filtering by
- Creators: Computer Science and Engineering Program
Description
Modern AI tools have made the process of developing chatbots easier than ever. This thesis explores designing and developing two chatbot personas for an event planning and networking application as well as a study about the user interactions with the personas in terms of conversational clarity, relevance of information, and user engagement.
The project began with the design of the two unique personas through a psychology framework called the Five Factor Model. Next, the design and architecture of the chatbot was created, using a loose retrieval augmented generation (RAG) structure, and a two layer API call to OpenAI’s API models. The main layer selects an intent function which is responsible for fetching relevant information from the database, and the second uses the returned data to formulate an appropriate response to the user. This backend server had a single endpoint. The frontend was created using React.js.
To conduct the study, users were asked to interact with both chatbots, while reflecting on their interactions with both. Findings from the study indicate that there was no significant difference in users’ perception of conversational clarity or relevance of information between the two chatbot personas which suggests that both were effective in delivering accurate and understandable content. However, there was a noticeable and statistically significant increase in user engagement with the casual chatbot. The results indicate that while clarity and relevance of information may not depend heavily on the persona, engagement is influenced slightly by chatbot persona.
ContributorsPatel, Khushi (Author) / Chavez Echeagaray, Maria Elena (Thesis director) / Clarck, Jo (Committee member) / Barrett, The Honors College (Contributor) / School of Mathematical and Statistical Sciences (Contributor) / Computer Science and Engineering Program (Contributor)
Created2025-05
Description
This honors thesis project is an extension of my computer science capstone project, Almanac: Idea to MVP. The capstone project involves an AI agentic workflow that takes in a product idea and generates a functional MVP, and this thesis project adds to its functionality by allowing a customer persona to provide feedback on the generated MVP and iterate on the final product. This project changes the static generation of MVPs into a dynamic, user-centered approach that allows for product iteration based on customer feedback.
ContributorsKelwalkar, Aditi (Author) / Osburn, Steven (Thesis director) / Kommuri, Sai Charan Tej (Committee member) / Barrett, The Honors College (Contributor) / School of Public Affairs (Contributor) / Computer Science and Engineering Program (Contributor) / Computing and Informatics Program (Contributor)
Created2025-05
Description
Our campus hosts a substantial population of both Arab and Indian international students who both highly value henna as an artistic tool of cultural expression. This appreciation is never more deeply felt than during traditional events and religious holidays. Despite the demand and readily available audience, there is a noticeable lack of accessible and affordable henna services on campus. As a result, students either resort to paying costly prices for professional services off campus or attempt DIY, at-home solutions that more often than not, have inconsistent and undesirable outcomes. This gap in the market presents a unique opportunity for Henna Petals to deliver high-quality and authentic henna designs at student-friendly prices. By offering convenient, on-campus services, Henna Petals aims to encourage students to embrace and celebrate their cultural practices, even while being continents away.
ContributorsSiddappa, Tanu (Author) / Muraweh, Yasmine (Co-author) / Byrne, Jared (Thesis director) / Cazier, Joseph (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2025-05
Description
With the growth of technology globally, the usage for hardware with Mixed Reality functionalities has expanded over the past few years. Specifically, its usage in an educational setting is something that warrants more research. Virtual Reality specifically is a form of experience that transports users into a different landscape for education. This paper explores the intricacies of a game developed in Virtual Reality to explore bartering as an educational tool. Specifically, it explores the game system that could use the benefits of Virtual Reality in educating users through experience. The hypothesis is that Virtual Reality can help facilitate this gaming experience to accomplish the goals aligned in the game overview.
ContributorsKamasamudram, Anuj (Author) / Johnson, Mina (Thesis director) / Wylie, Ruth (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / Thunderbird School of Global Management (Contributor) / Dean, W.P. Carey School of Business (Contributor)
Created2025-05
Description
In today’s digital age, language barriers are a significant obstacle to the accessibility of
high-quality content. While existing translation solutions are functional, they often com-
promise on the human element, particularly the unique voice and personality of the content
itself. This results in either plain text translations (captioning) or robotic voice-overs that
are extremely unengaging.
This thesis presents Translatica, an end-to-end translation platform that revolutionizes
content creation by translating any video while preserving contextual information and the
speaker’s authentic voice. The translation pipeline employs open-source voice conversion
algorithms and a modular architecture that can stay up to date with constantly changing
technology. This implementation delivers a comprehensive translation platform across 20+
languages. This paper will outline the high-level details of the Translatica project, and hone
in on the cloud infrastructure used to develop the project.
As the market demands change, Translatica’s approach addresses the status quo and
also serves a greater purpose: enabling universities like Arizona State University to amplify
their educational voice globally while preserving the human aspect in digital content.
ContributorsRamani, Krishna (Author, Co-author) / Hsu, Jeffrey (Co-author) / Jhaj, Baaz (Co-author) / Osburn, Steven (Thesis director) / Zhu, Haolin (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2025-05
Description
This project presents an attempt to recognise single, handwritten alphanumeric characters with a machine learning-based approach. Using a dataset of 131,600 handwritten characters, I trained a custom convolutional neural network (CNN), which achieved a 87.94% accuracy rate, and I applied the ResNet-152–a well-known published model, which achieved a 87.13% accuracy rate, for comparison. A full-stack web application was also developed in conjunction with the model for demonstration. These results signify that the depth of the model was not the main culprit for the systematic failure of recognising some pairs of characters, and that a different approach must be attempted.
ContributorsHo, Timothy (Author) / Menees, Jodi (Thesis director) / Srinivasan, Aravind (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2025-05
Description
Businesses and advertising agencies today often promote their products and services through advertisements across various online services such as Google, Meta, Microsoft, and others. Online advertising plays a crucial part in acquiring new clients, resulting in the business's success. However, the interpretation of essential advertising data, such as cost per click and conversion rate, across these advertising platforms presents a challenge to smaller businesses and advertising agencies that manage various client accounts across multiple platforms. This project resolves inefficiencies in digital marketing reporting by delivering a study on the design, development, and evaluation of the Advertising Analytics Dashboard, which provides businesses and agencies such as Vloe, a Quebec-based advertising agency, a unified platform for retrieving tracking analysis and advertising metrics for multiple accounts across multiple online advertising platforms (Vloe, n.d.). Users through the Advertising Analytics Dashboard can detect embedded tracking tags such as Google Analytics and Meta Pixel, and connect their advertising accounts to retrieve data across Google Analytics, Google Ads, Meta Ads, and Microsoft Ads. The platform supports OAuth login, query saving, PDF report generation, and dynamic localization in English and Canadian French. Upon deploying the website, an usability study with 14 participants indicated that users found the dashboard intuitive and the retrieved data accurate. The project successfully delivered and demonstrated how the user-friendly, simplified, and streamlined Advertising Analytics Dashboard provides value to small businesses and advertising agencies for viewing and analyzing tracking and advertising data across multiple platforms in one centralized location.
ContributorsMahajan, Neil (Author) / Chavez Echeagaray, Maria Elena (Thesis director) / Dansereau, Christine (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2025-05
Description
This thesis presents the design, implementation, and evaluation of Beacon, a self-hosted error
monitoring platform developed for ASU Online. Beacon addresses the challenges of observability in digital learning environments by providing comprehensive error tracking, real-time alerting, and customizable dashboards while ensuring data sovereignty, cost efficiency, and scalability. Built on an event-driven architecture using open standards, Beacon aims to improve issue resolution times, enhance student experience, and reduce operational costs compared to commercial alternatives. The system leverages OpenTelemetry for data collection, Kafka for event processing, and Elasticsearch for storage, demonstrating how these technologies can be integrated to create a robust observability solution tailored to educational technology needs.
ContributorsJuntilla, Ben (Author) / Menees, Jodi (Thesis director) / Jagannath, Shruthi (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2025-05
Description
The Robotics Design Fundamentals Educational VR Experience is a game designed to help players learn and understand the concepts of robot configuration, basic kinematics, and forward kinematics through an embodied approach in virtual reality. This Virtual Reality (VR) experience focuses on reinforcing player's understanding of the Denavit-Hartenberg (DH) parameter derivation process, a key step in developing forward kinematic models. Forward kinematic models are extensively used in the field of robotics, since they act as an intermediate step in the development of more complex models, such as inverse kinematic models, so it is important for students to be able to quickly and confidently derive forward kinematic models. By analyzing VR game design best practices, characteristics of effective embodied learning approaches, and current educational robotics simulators, The Robotics Design Fundamentals Educational VR Experience aims to be an effective tool for students to practice the process of deriving DH parameters and forward kinematic models.
ContributorsJung, Damon (Author) / Johnson, Mina (Thesis director) / LiKamWa, Robert (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor) / Computing and Informatics Program (Contributor)
Created2025-05
Description
The perfect anti-cheat software for a first person shooter that balances protecting user privacy and effective cheat detection in a modern age where dishonest methods of gameplay are rampant within competitive games. By utilizing the inherent protections servers have against third party attacks, by removing the software off of the client, all of the detection methods are placed in an external area, where cheaters are determined by behavior that is tracked through statistical trackers placed in the game. By measuring multiple key features including Illegal Trace Time, Trigger Time, and Mouse Flick Speed. Each of these measured attributes relate to commonly used cheats in first person shooters, which is the target for this anti-cheat machine learning model. By gathering a wide range of statistics and figuring out the average player’s statistics, it would be possible to determine if a player is using external programs to gain an unfair advantage.
ContributorsKim, James (Author) / Kobayashi, Yoshihiro (Thesis director) / Baek, Jaejong (Committee member) / Barrett, The Honors College (Contributor) / Computer Science and Engineering Program (Contributor)
Created2025-05