Digital Commons Network^™

A Rule-Based Hybrid Translation Model For Context-Aware Speech To Indian Sign Language Tasks, Dania Jaison

Master's Projects

In India, one of the most significant tools to communicate with the Deaf and Hard of Hearing (DHH) communities is Indian Sign Language(ISL). The issue of a scarcity of computational resources for ISL is even more pronounced when it comes to the translation of written or spoken English into ISL. This paper proposes a rule-based model for translation where the spoken english sentences are translated into ISL by focusing on the specific syntactic and grammatical differences between these two languages. ISL uses a simplified syntax unlike the nuanced sentence structures in English — we omit most of the auxiliary verbs …

Teaching Children Programming Concepts Through Video Games, Kayla Musleh

Master's Projects

Children have a tendency to lose focus when they are presented with something that does not entertain them or tailor to their personal interests; such as studying [1], [3], [10]. The research performed for this project focuses on studying how much more children can comprehend and focus on learning educational material if they are learning through playing a video game rather than being taught information directly in a typical classroom manner. For this study I created a computer game designed to introduce educational subjects such as mathematics and programming concepts to the child playing the game. By completing the tasks …

Leading From The Middle: Arts Administrators' Beliefs About The Impact Of Arts Education On High-Needs Students, Sofia Fojas

Dissertations

Research on arts education notes the positive impact of arts education on educational outcomes for students, particularly students of color, students in poverty, and students needing additional academic support. Students living in low-income communities receive different educational opportunities than those in high-wealth districts. This disparity is especially true for highly mobile and high-needs students of color. Arts education has made positive differences in student outcomes. This qualitative study examined the beliefs of county arts leads, leaders in the middle, situated between the California Department of Education and their local school districts, and how they can be empowered to be change …

Whose Vote Is It Anyway? A Geospatial Analysis Of The California Voter's Choice Act Ballot Drop Box Criteria In Santa Cruz County, Judith Heher

Master's Projects

The way Californians vote is changing. While some of the laws surrounding these changes are close to a decade old, the events of 2020 surrounding the November Presidential Election and the COVID-19 pandemic both accelerated and expanded the adoption of contactless voting approaches such as vote-by-mail and the ballot drop box. Neither tool is new to California voters. Vote-by-mail was introduced to the state in 1962 (CA Secretary of State, unknown) and ballot drop boxes were first used in 2014 (Sherman, 2020). In 2016 California Senate Bill 450 (SB-450, 2016) was signed into law. Also known as the Voters Choice …

Emotion Detection Using Ensemble Learning, Priya Harika Yerapothu

Master's Projects

Emotion detection is gaining exponential necessity in today’s technological age. This research seeks to delve into ways conversational AI could be enhanced by integrating emotional intelligence using an ensemble learning approach. Traditional machine learning along with advanced neural network architectures are implemented to improve the understanding and intricacies of emotion detection from textual data. The dataset we use is GoEmotions dataset, annotated with 27 emotional labels, to conduct a detailed analysis of emotion recognition. Various machine learning models, such as HistGradientBoosting, LightGBM, CatBoost, and MLP, will be evaluated side by side with advanced models of Bidirectional Long Short-Term Memory (BiLSTM) …

Opinion Graphs Construction For Reviews Using Transfer Learning And Large Language Models, Yichen Lin

Master's Projects

With the rapid development of the Internet, reading online reviews before making a purchase, booking a hotel, or making a restaurant reservation has become a part of daily life. Customers often consider reviews as crucial supplementary information before making decisions on how to spend their money. However, reading many reviews to gain helpful information takes time and effort. This project proposes a new method OpinionGraphGenerator that aims to create opinion graphs from hotel reviews to reduce the high volume of text in reviews while preserving essential insights. In an opinion graph, vertices are semantically similar opinions, where each opinion consists …

Exploring Gender Bias In Large Language Models: Cross-Linguistic Comparisons And Evaluation Letters Analysis, Athira Kumar

Master's Projects

Large language models (LLMs) play a significant role in modern human-computer interaction. They have exploded in popularity recently, becoming widely used for various tasks. However, concerns persist regarding potential biases within these models. This project investigates gender bias in the popular LLMs - GPT-3.5, GPT-4, Gemini, and LLAMA. The first part of our study focuses on analyzing biases using ambiguous sentences across three languages - English, Malayalam, and Tamil. We evaluate the LLMs to see if they associate occupations with commonly held gender stereotypes, by using specific professions within our test sentences. Through the use of two low-resource languages, this …

Deciphering Speech Through Vision: A Deep Learning Lip Reading System, Srujith Rao Ambati

Master's Projects

Lip-reading, a ubiquitous field between computer vision and speech processing, focuses on identifying what spoken words a person generates depending on their uttering lip movements. This paper presents a streamlined lip-reading solution that employs machine learning and deep learning. First, Our work utilizes the Multi-Task Cascaded Convo- lutional Networks to detect facial “landmarks,” including the face and lips region, and the aligns the face. The aligned faces are segmented to get the lip images. Lip images are preprocessed using the Real-Enhanced Super Resolution Generative Adversarial Network to enhance image resolution to identify subtle lip movement in video images: a critical …

Deception Detection Models From Speech, Tien Nguyen

Master's Projects

Recently, researchers have shown an increased interest in automatically detecting deceptive actions. The attention given to this area can be attributed to the many potential applications of deception detection, especially in the field of criminology. To contribute to the deception detection research, this project investigates textual and audio data extracted from spoken and written words. We evaluated and compared the traditional linguistic models with advanced Large Language Models (LLMs) while using Natural Language Processing (NLP) techniques. Additionally, various feature selection techniques were applied to assess the importance of linguistic features. We conducted extensive experiments to evaluate the effectiveness of both …

Multi-Platform Cyberbullying Detection Using Nlp And Machine Learning, Chinmayi Lokeshwar Hegde

Master's Projects

The issue of cyberbullying is growing due to the online anonymity and due to online platforms having less repercussions. This research proposes for proactive measures to detect and prevent such behavior before it reaches the victim. By using data from various social media platforms and employing machine learning techniques, this research proposes an innovative system aimed at identifying and thwarting cyberbullying incidents preemptively. While existing methods have primarily focused on prediction and detection of cyberbullying incidents, there remains a significant gap in research regarding prevention strategies. This project aims to address this gap by leveraging machine learning, natural language processing …

Implicit Personality Detection From User Behaviour In Recommendation Systems, Uzma Zubair Shaikh

Master's Projects

Recommendation systems are an integral part of any business, and a crucial factor in determining their success as these systems help businesses in marketing their products to the right kind of audience. Conventional methods of building recommendation systems such as collaborative filtering and content-based recommendation, although effective, suffer from limitations such as cold start and the data sparsity problems. Moreover, these methods aim at finding similar products as user’s past interactions rather than personalizing the recommendations. The upsurge in use of social media, over-the-top content (OTT), and e-commerce platforms has made the task of personalizing recommendations imperative, leading to the …

Leveraging Large Language Models For Transforming Student Information Into Actionable Data, Sree Hari Karri

Master's Projects

Admission season places significant demands on university committees, necessitating the review of vast arrays of documents to assess students’ competence. This project advances the development of an automated system designed to streamline this process by evaluating application materials such as Letters of Recommendation (LoRs), Statements of Purpose (SoPs), and resumes. Utilizing a variety of advanced Natural Language Processing (NLP) techniques, the system compares the performance of several Large Language Model (LLM) approaches. It also experiments with different data handling strategies, including the use of vector stores versus traditional context-based processing, to optimize model efficiency and accuracy. Special attention is given …

Exploring The Use And Misuse Of Large Language Models (Llms), Hezekiah Paul D. Valdez

Master's Projects

Large Language Models (LLMs) have quickly gone from simple rule-based systems to complex knowledge bases capable of tackling many different tasks across a variety of fields. What began as an exercise in human-computer interaction has become the basis for artificial intelligence in a variety of mediums. When attached to larger systems, LLMs become generative assistants that can perform highly on human proficiency assessments and other benchmark skill assessments. This increase in proficiency has led these systems to be deployed in fields such as cybersecurity, business, and programming to help improve productivity and efficiency. However, such a wide availability has allowed …

Knowledge Graph-Based Multiple-Choice Question Generation, Durga Muralidharan

Master's Projects

Knowledge-based tests are widely used to assess knowledge on a specific subject and have many applications in education and professional certifications. These tests usually consist of Multiple Choice Questions (MCQs), where a question with a few possible answers is given. Along with the correct answer, three or more incorrect answers are provided, which are called distractors. MCQs are a popular method for these tests because they are easy to grade. These tests can check different levels of comprehension ranging from beginners to advanced by creating distractors that may confuse unprepared test takers. This project proposes the Knowledge Graph Multiple Choice …

Assumptions, Resources, And Inputs To Case Management: Implications For California’S Regional Center System, Jonathan Flint

Master's Projects

This project adds to knowledge of case management assumptions, resources, and inputs for California’s Regional Center system by surveying members of the Service Access and Equity working group, formed by the Department of Developmental Services (DDS). It recommends development of a logic model to evaluate case management activities because their intended societal impacts are difficult to directly measure. Additionally, it adds to the debate on health equity and racial disparities in Medicaid long-term services and supports (LTSS). In 1969, passage of the Lanterman Developmental Disabilities Services Act (The Lanterman Act) led to the first and still only entitlement to community-based …

Suburban Bay Area City Approaches To Diversity, Equity, And Inclusion (Dei), Arianna Bush

Master's Projects

The ultimate goal of government is to serve the community for the greater good. Creating an inclusive and representative environment for those working in government and for the population they serve will improve many aspects of public service. In recent decades, Diversity, Equity, and Inclusion (DEI) have been increasingly prioritized as America has become increasingly diverse. However, this effort intensified in 2020 after the murder of George Floyd and the subsequent Black Lives Matter (BLM) protests. “Three years after Floyd's death and the movement hit the streets, 74% of Black executives said they saw positive change in hiring, retention, and …

How Are Mcps Doing On Achieving Assessed Calaim Requirements? A Comparative Analysis Of Selected Not-For-Profit, Publicly Governed Health Plans In California, Junell Chen

Master's Projects

At the heart of a larger societal movement, the imperative to foster diversity, equity, and inclusion (DEI) is a resounding call to action across all sectors. This pressing concern underscores the need for proactive and equity-centric solutions, including within the American healthcare system. The U.S. Department of Health and Human Services has been instrumental in shaping policies and initiatives, such as Healthy People, aimed at promoting health equity and reducing health disparities. Similarly, the Centers for Medicare and Medicaid Services (CMS) has instituted supplementary compliance requirements to hold healthcare stakeholders accountable for implementing equitable programs designed to eliminate health disparities …

Enhancing Environmental Health And Safety: Fine-Tuning Large Language Models For Domain-Specific Applications, Mohammad Adil Ansari

Master's Projects

This study aims to simplify Environmental Health and Safety (EHS) by leveraging the power of Large Language Models (LLMs). In this research, we focus on fine-tuning three LLMs — LLaMA, Mistral, and Falcon — using PEFT techniques such as QLoRA and SFT, to address domain-specific needs such as safety compliance, incident reporting, and knowledge dissemination. Our research methodology involves fine-tuning each LLM model on a custom dataset compiled from various regulatory agencies, supplemented by targeted web scraping and manual collection of questionnaires to capture and enrich the models with the latest regulations and guidelines. This study aims to compare the …

Instagram Data Analysis Using Machine Learning, Lakshmi Prasanna Gorrepati

Master's Projects

With enormous amount of social media content, we can draw valuable insights. In this paper, we apply different Machine Learning and Deep Learning techniques on Instagram data to determine the techniques that work well to discover the engagement class of a social media post. Out of all the social media platforms, Instagram is growing rapidly not just in the number of users but also in terms of Advertisement and marketing surpassing YouTube’s advertisement revenue. The end goal of this paper is to propose a technique to predict the engagement class. We applied Random Forest (RF), Stacking Classifier, Extreme Gradient Boost …

Ranking-Based Hashtag Recommendation With Collaborative And Content-Based Filtering, Fei Pan

Master's Projects

The purpose of this project is recommending relevant hashtags for users using both Collaborative Filtering (CF) and Content-based filtering with Twitter dataset. The Twitter dataset was collected by leveraging Twitter API v2. After data preprocessing, 40,806 tweets posted by 278 users with 3,107 hashtags from 01/01/2022 to 04/30/2022 are used for model training and testing. For CF models, we will mainly focus on generating embeddings to learn about user and hashtag latent factors and finally predict a probability for unseen hashtags with most possibility will be ranked as topK items for corresponding users. In this project, Matrix Factorization (MF), Neural …

In Their Words: Voices Of High School Graduates Who Were Labeled English Learners, Yolanda K. Jimenez

Dissertations

This research captures the experiences of high school graduates who were labeled English Learners while they were enrolled in a public high school in the greater Sacramento area of California. The study examined what these bilingual high school graduates report as beneficial and detrimental experiences faced while completing the course requirements for high school graduation. This study builds on research that includes secondary classroom teachers and their perceptions of English Learners, classroom teaching and learning, and experiences of emergent bilingual students. The study expands the body of research and informs praxis pertaining to supporting emergent bilingual students as they attempt …

Addressing Equity Gaps In Stem: A Self-Study, Prabhjeet Kaur Brar

Dissertations

The Hispanic/Latinx population is increasing nationwide and in the state of California; however, the Hispanic/Latinx population remains underrepresented in STEM professions contributing to a lack of diversity in STEM. To increase the academic success of the Hispanic/Latinx student population in STEM majors, high leverage research-based teaching strategies through the lens of historically responsive literacy were applied and examined throughout this research. The purpose of this mixed-methods self-study was to examine the impact of research-based effective strategies/high leverage practices on Latinx students’ success rates in my introductory biology classrooms. The study focused on two biology course sections with a laboratory. Each …

How Can We Do Better? Understanding Student Experiences And Support Needs During And After The Covid-19 Pandemic, Kevina M. Brown

Dissertations

This dissertation study aimed to provide opportunities for students at San José State University (SJSU), to share about their experiences during the Covid-19 pandemic and to provide feedback and recommendations regarding resources and culturally engaging supports on campus. The research inquiry involved survey and interview methodology to gain insights into student experiences pertaining to financial and mental health challenges and academic disruption and social isolation during the beginning, middle and end of the pandemic, as well as their engagement with resources and supports provided on campus. Recruitment was done by flyer distribution throughout campus and via email distribution to students …

Queer A.F.: Queer Educators In Affinity Family Personal-Professional Development, James Egisto Aguirre

Dissertations

Scholarship shows that affinity groups are spaces of support, learning, and healthy career development that are responsive to the needs of a particular marginalized community. The concept of heteroprofessionalism– the implicit or explicit pressure/s queer educators feel to fit within the proverbial cisgender/heterosexual (cishet) box–is but one of a myriad issues and pressures affect queer educators across the nation. This study brings queer educators from one school district together to unpack their experiences through the lens of heteroprofessionalism. Via queer theory, qualitative, written response data was collected and subsequently analyzed in three, half-day sessions offered in spring 2024. Thirty participants …

Examining The Impact Of Registered Nurse Engagement In Medical Assistant Clinical Competency Development And Team Effectiveness In Ambulatory Care, Colleen Burckin

Doctoral Projects

Background

As ambulatory care grows in complexity, there is a growing need to ensure that staff possess a high level of competence and team effectiveness to provide safe, efficient, and cost-effective care. Leveraging the expertise and leadership skills of Registered Nurses (RN) to support the team of unlicensed, Medical Assistants (MA) will be incentivized. With limited knowledge of MA preparation to meet the rapidly changing demands, managers will struggle to build effective teams and look to the impact of RN- supported MA onboarding to bridge skill gaps.

Purpose

To examine this issue, a quasi-experimental, quality improvement study was done to …

(Miss)Educated Latino Males: Academic Preparedness, Navigation, And Retention At 2-Year Colleges, Nannette Stephanie Regua

Dissertations

This study centers Latino males, first generation, first year students at four 2-year colleges in the Silicon Valley by understanding their experiences in transferable English 1A Writing Composition course and looking at the acts of instilling a sense of belonging and mattering by institutional agents and support services that are invaluable to student retention and success. The purpose of this study is to determine Latino male students’ perceptions of academic preparation, navigation, and success in higher education after the implementation of California Assembly Bill 705. My findings revealed important themes that map onto conceptual frameworks, most notably the Community Cultural …

The Anticipation Is Killing Me! - Examining The Mediating And Moderating Relationships Between Mistreatment Anticipation And Work Engagement, Mia N. Fagan

Master's Theses

The mistreatment of workers by customers in the service industry is widespread and well-known. Although customer mistreatment is associated with negative consequences for employees, there is little knowledge about the potential consequences of the expectation of future mistreatment. The present study examined the relationship between mistreatment anticipation and work engagement and hypothesized that mistreatment anxiety would mediate the relationship between the two and that perceived organizational support (POS) would moderate the relationship between mistreatment anticipation and mistreatment anxiety. Data were collected from a sample of 183 individuals via an online survey. Results showed a significant and negative relationship between mistreatment …

In And Ex Spheres Of A Tetrahedron, Hidefumi Katsuura

Faculty Research, Scholarly, and Creative Activity

We prove that (1) a tetrahedron is isosceles if and only if the vertices of its twin tetrahedron are the excenters of the tetrahedron, (2) if a tetrahedron is orthocentric, and if the orthocenter is either the incenter, the centroid, or the circumcenter, then the tetrahedron is regular, (3) a tetrahedron is regular if and only if the four ex-spheres are tangent to the in-sphere, and (4) we prove an inequality relating the in-radius, circumradius, and the distances between the in-center and the vertices of a tetrahedron.

Sample Sizes For 10 Types Of Qualitative Data Analysis: An Integrative Review, Empirical Guidance, And Next Steps, Amber Wutich, Melissa Beresford, H. Russell Bernard

Faculty Research, Scholarly, and Creative Activity

There has been a recent explosion of articles on minimum sample sizes needed for analyzing qualitative data. The purpose of this integrated review is to examine this literature for 10 types of qualitative data analysis (5 types of saturation and 5 common methods). Building on established reviews and expanding to new methods, our findings extract the following sample size guidelines: theme saturation (9 interviews; 4 focus groups), meaning saturation (24 interviews; 8 focus groups), theoretical saturation (20–30+ interviews), metatheme saturation (20–40 interviews per site), and saturation in salience (10 exhaustive free lists); two methods where power analysis determines sample size: …

Sibelius’S Scaramouche: A Comparative Production History Of A Tragic Pantomime, 1913–1977, Karl E. Toepfer, Eija Kurki

Open Educational Resources

The book describes the historical context for the Scaramouche tragic pantomime created by Poul Knudsen and Jean Sibelius in 1913. The pantomime had numerous productions in various European countries between 1922 and 1977, and the book examines all of them according to all available evidence. The text explains the historical and cultural significance of the pantomime and how it uniquely explores a dark and complex intersection of female sexuality, marriage, and class control of erotic desire. The authors examine all productions of Scaramouche from the premiere production in Copenhagen in 1922 to the last major production in Karl-Marx-Stadt, East Germany …