Open Access. Powered by Scholars. Published by Universities.®
- Discipline
- Keyword
- Publication Year
- Publication
- File Type
Articles 31 - 60 of 213
Full-Text Articles in Digital Humanities
Changing Narratives Of Self-Improvement: Self-Help Literature Across Two Eras, Ayesha Aslam
Changing Narratives Of Self-Improvement: Self-Help Literature Across Two Eras, Ayesha Aslam
IPHS 300: AI for Humanity
This project explores how the narratives of personal growth in self-help literature have evolved between the 1970s and the 2010s. The goal was to identify which themes persisted across eras and how others shifted in response to broader cultural and technological changes. I hypothesized that 1970s texts would emphasize self-control and traditional success, while 2010s texts would highlight flexibility, mental well-being, and authenticity, with some shared focus on motivation and habit-building. To test this, I selected five bestselling books from each decade and applied Latent Dirichlet Allocation (LDA) topic modeling using a Colab-based notebook. The top 30 most salient terms …
Leveraging Ai Agents And Multi-Agent Debate To Automate Mlb Front Office Decisions And Roster Construction, Parker Gibbons
Leveraging Ai Agents And Multi-Agent Debate To Automate Mlb Front Office Decisions And Roster Construction, Parker Gibbons
IPHS 484: Senior Seminar
This project leverages artificial intelligence Agents and Multi-Agent Debate (MAD) to evaluate Major League Baseball players and construct a twenty-six player MLB roster. The AI Agents evaluate each player based on statistics and grades them according to a five-tool scale, eventually resulting in a single numerical rating. MAD is then employed alongside optimization techniques to select thirteen hitters and thirteen pitchers, maximizing team performance according to agent consensus, while staying within a specified salary cap. The operating hypothesis is that AI agents can effectively evaluate Major League Baseball players based on performance statistics, even with large and complex datasets. By …
Understanding Human-Ai Interactions: What 17,000 Conversations Reveal About Creativity And Chatgpt, Hannah Sussman
Understanding Human-Ai Interactions: What 17,000 Conversations Reveal About Creativity And Chatgpt, Hannah Sussman
IPHS 484: Senior Seminar
This study uses topic modeling to analyze over 17,000 English-language conversations from the WILDCHAT-FULL dataset, a large-scale collection of human-ChatGPT interactions. By applying Latent Dirichlet Allocation (LDA) across 17 time-based segments spanning one year, the research identifies major themes and temporal shifts in user engagement. Creative writing emerged as the dominant topic category, accounting for nearly 40% of all identified topics. Subcategories such as character development, fight scenes, and sexual content offer further insight into how users creatively engage with ChatGPT. By combining large-scale topic modeling with close qualitative review, this study demonstrates a scalable yet nuanced approach to analyzing …
Ai's Creative Boundaries: A Cross-Model Pattern Analysis Of Identity-Based Narratives, Maisie Jane Brigham
Ai's Creative Boundaries: A Cross-Model Pattern Analysis Of Identity-Based Narratives, Maisie Jane Brigham
IPHS 300: AI for Humanity
This research project examines creative writing outputs from five leading large language models (Claude 3.7 Sonnet, ChatGPT 4o, Grok 3, Gemini 2.5 Flash, and Deepseek R1) as they generate and respond to prompts focused on diverse identity experiences. By analyzing stories centered on immigrant, Black, LGBTQ+, transgender, and Indigenous experiences, I identify recurring patterns, tropes, and limitations across different AI systems. This study illuminates how algorithmic storytelling currently relies on a limited repertoire of narrative elements, raising important questions about the representation of diverse human experiences in AI-generated creative content and the potential impacts of these patterns as AI writing …
Peak : An Ai Voice Coach For Emotion-Aware Performance Tracking In High-Stakes Fields, Ayman Wadud
Peak : An Ai Voice Coach For Emotion-Aware Performance Tracking In High-Stakes Fields, Ayman Wadud
IPHS 484: Senior Seminar
High-stakes performers, such as athletes, artists, and professionals, often lack tools that integrate objective performance metrics with subjective mental states. This disconnect can hinder effective training and optimization. PEAK addresses this gap by combining customizable performance analytics with real-time emotional insights via Hume's Empathic Voice Interface (EVI). Through natural voice interaction, PEAK correlates emotional expression with performance data, enabling personalized feedback and data-driven reflection. The platform empowers users to understand their emotion-performance dynamics and develop targeted strategies for sustainable peak performance.
Biolinkbert-Pr: A Large Language Model For Diagnosing Pediatric Rheumatological Disorders, Juliette Lowe
Biolinkbert-Pr: A Large Language Model For Diagnosing Pediatric Rheumatological Disorders, Juliette Lowe
IPHS 300: AI for Humanity
Pediatric rheumatology is an understudied and underprovided field in medicine. Currently, there are only 850 pediatric rheumatologists in the United States (1). This can make it incredibly difficult to get a diagnosis, since pediatric rheumatologic disorders are rare and thus easily missed. For example, eight states have no pediatric rheumatologists at all, and only 25% of children with arthritis are able to see a rheumatologist (2). AI applications in pediatric rheumatology are lacking, likely due to the combination of a lack of interest and a lack of data. This project utilizes a large language model (LLM) to create an AI …
Yunique: Adaptive Intelligence For Convertible Bond Investing, Yunhan Zhao
Yunique: Adaptive Intelligence For Convertible Bond Investing, Yunhan Zhao
IPHS 484: Senior Seminar
No abstract provided.
Nlp Analysis Of The Septuagint: Topic Modeling And Sentiment Analysis Of Biblical Domestic Terms, Anne-Duncan Enright
Nlp Analysis Of The Septuagint: Topic Modeling And Sentiment Analysis Of Biblical Domestic Terms, Anne-Duncan Enright
IPHS 484: Senior Seminar
This study conducts an exploratory data analysis (EDA) of topic modeling and sentiment analysis applied to the Septuagint (LXX – the Greek translations of the Old Testament and the New Testament in the original Koine Greek) as well as four English translations of the Bible (LSV, Darby, DR, and KJV). Utilizing Latent Dirichlet Allocation (LDA) for topic modeling, I compare the Vulgate-based translations to Septuagint-based translations, discovering marked differences between the two categories of translations. The Vulgate is the Latin translation of the Bible done by Jerome in 900 A. D. which is already one step away from the original …
Scraping Sermonsusing Natural Language Processing To Compare Protestant Churches, Annalia Fiore
Scraping Sermonsusing Natural Language Processing To Compare Protestant Churches, Annalia Fiore
IPHS 484: Senior Seminar
This project compares sermons from three Christian traditions: Evangelical, Charismatic, and Reformed. Using data scraped from church youtube channels based in the Columbus, Ohio area, I ran thousands of sermons through Topic Modeling to evaluate the differing emphases of each tradition. Many of the topics corresponded with what we might expect from their respective tradition. But others were surprising. Most significantly, there was a strong emphasis within the Charismatic tradition on tithing and finances, concerns with resisting sexual temptation among the Evangelicals, and a focus on ecclesiology within the Reformed tradition. This project also indicates that further topic modeling on …
Can Advanced Chatbots Help Us Navigate Educational Advocacy? Understanding The Potential Of Large Language Models As Assistants And Guides Within An Iep (Individualized Education Program) Meeting Context, Nava Bahrampour
IPHS 300: AI for Humanity
Hundreds of thousands of parents and students in New York City’s school district alone (Fancsali and Farley 2018) go through the Individualized Education Program (IEP) process every year, attending meetings and evaluations in order to determine adequate services and students with disabilities’ educational trajectories. However, most parents, especially those new to public education policy, report difficulty navigating the system or acquiring the resources necessary to successfully advocate for their children at IEP meetings (Advocates for Children 2025, Kurth et al. 2020). The rise of generative artificial intelligence and increased linguistic capabilities of interactional chatbots provokes questions about such technologies’ ability …
Following The Crowd? A Topic Modeling Analysis Of Twitter Discourse And Supreme Court Decisions, Jessica Daughterty
Following The Crowd? A Topic Modeling Analysis Of Twitter Discourse And Supreme Court Decisions, Jessica Daughterty
IPHS 300: AI for Humanity
This project uses topic modeling to compare the top topics from Twitter posts with the text of the Supreme Court’s Dobbs v. Jackson ruling, which overturned Roe v. Wade in 2022. I analyzed whether the Court’s reasoning reflected public concerns or was disconnected. While some analysis of the Twitter data exists on the Kaggle dataset I used, I conducted this research independently of those results. By putting the Court’s language and public sentiment side by side, this project explores whether institutions are responding to what people care about.
Exploring The Potential Of Ai For Swim Technique Evaluation And Athlete-Centered Coaching, Gwen Eisenbeis
Exploring The Potential Of Ai For Swim Technique Evaluation And Athlete-Centered Coaching, Gwen Eisenbeis
IPHS 300: AI for Humanity
This project explores the use of AI-powered video analysis to simulate elite-level coaching in butterfly stroke technique. Using Google’s Gemini 2.5, the goal of the project is to determinewhether a large multimodel, trained on technique videos of elite swimmers, can generate detailed and personalized feedback that mirrors the insight of a well-informed human swim coach. Training videos featuring Olympic-level butterfly swimmers were used to establish an internal reference model of an ideal butterfly technique. The model was then presented with videos of collegiate swimmers and prompted to deliver coaching-style feedback. Overall, this project demonstrates the potential for AI systems to …
Ai Proof Benchmarking: Evaluating Mathematical Reasoning In Open-Source Llms Via Taylor Series Analysis, Godwin Idowu
Ai Proof Benchmarking: Evaluating Mathematical Reasoning In Open-Source Llms Via Taylor Series Analysis, Godwin Idowu
IPHS 300: AI for Humanity
This research project investigates large language models’ (LLMs) abilities to develop conceptually and mathematically correct proofs by using a benchmark based on the Taylor Series representation. The task examines LLM models for their capacity to adhere to definitions, theorems, and calculus. A range of models of varying sizes was tested, including Qwen, Gemma and LLaMA. Models under 2B parameters demonstrate poor understanding of Taylor and geometric series and apply wrong theorems while lacking logical reasoning about convergence. Models with at least 27B parameters typically generate proofs that are both coherent and almost complete. The research identifies existing constraints in symbolic …
Authenticity Under Review: How Well Does Genai Write College Admissions Essays?, Adrian Mangine
Authenticity Under Review: How Well Does Genai Write College Admissions Essays?, Adrian Mangine
IPHS 300: AI for Humanity
With nearly 30% of people ages 14-22 reporting frequent AI use, increasing AI assistance in college admissions essays poses a new consideration with ethical AI use (Rubin et al., 2024). This study investigates how well three generative AI models write college admissions essays: ChatGPT o3, Gemini 2.5 Pro, and Grok. Each model responded to a Common App 2025-2026 application prompt as three distinct applicants: Elijah, Grace, and Malik (Common App, 2025). Each student represented a common college applicant archetype: Elijah, an academically successful dual sports recruit; Grace, a near-perfect award-winning scholar; and Malik, a gifted student from an underrepresented background. …
Ai Agentic Framework For Data-Driven Cricket Player Scouting, Muhammad Ibraheem Nadeem
Ai Agentic Framework For Data-Driven Cricket Player Scouting, Muhammad Ibraheem Nadeem
IPHS 391: Interdisciplinary AI Frontiers
This project focuses on developing a data-driven Agentic Framework for player scouting, tailored to optimize cricket team selection. By integrating performance metrics with insights into evolving T20 cricket rules, the framework evaluates players based on their fitness, popularity, and on-field impact. These tools will empower leagues with limited resources to make informed scouting decisions, democratizing player evaluation and fostering equitable opportunities in cricket.
Multi-Agent Framework For Digital Marketing Optimization, Samyak Shrestha, Jon Chun
Multi-Agent Framework For Digital Marketing Optimization, Samyak Shrestha, Jon Chun
IPHS 391: Interdisciplinary AI Frontiers
This project presents a multi-agent framework designed to help marketers quickly create, test, and understand digital marketing campaigns. By combining state-of-the-art language models, automated content generation, simulated audience feedback through personas, and organized data analysis, this framework aims to save time, reduce guesswork, and offer clear insights. The result is a more efficient way for marketers to improve their campaigns and reach the right audience.
Ai Virtual Assistant For Student Disability Services: Implementing Rag-Enhanced Chatbots In Higher Education Support, Hannah Sussman, Jon Chun
Ai Virtual Assistant For Student Disability Services: Implementing Rag-Enhanced Chatbots In Higher Education Support, Hannah Sussman, Jon Chun
IPHS 391: Interdisciplinary AI Frontiers
When students with disabilities enter the college arena they lose many of the resources that supported them throughout high school, and suddenly are responsible for advocating for their needs and rights themselves. For some, this is an easy transition, but for most the sudden shift in setting, expectations, and responsibilities leaves them unprepared to transition smoothly into college life. A chatbot with sufficient institutional data and information about disabilities and accommodations could help college students with disabilities by providing immediate and personalized guidance throughout their college experience. The proposed accessibility support system implements a hybrid architecture combining a Retrieval-Augmented Generation …
Ai-Powered Appointment Prioritization System For Resource-Poor Settings, Ayman Wadud
Ai-Powered Appointment Prioritization System For Resource-Poor Settings, Ayman Wadud
IPHS 391: Interdisciplinary AI Frontiers
This project presents an AI-driven multi-agent system for managing and prioritizing patient appointments in a physician's chamber in a resource-poor setting. By employing a multi-agent architecture and a vector database, the system dynamically adapts to real-time events like patient check-ins, and supports the manual reordering of appointments. Built using Python, LangChain, and the ChromaDB vector database, the system can be accessed via a simple UI on Streamlit. The objective is to enhance patient flow, reduce wait times, and provide an adaptive and efficient appointment system in a Bangladeshi clinical setting.
Ancient Greek Parsing With Ai: Unpacking Complex Word Composition With Agentic Systems, Braeden Singleton, Jon Chun, Katherine Elkins
Ancient Greek Parsing With Ai: Unpacking Complex Word Composition With Agentic Systems, Braeden Singleton, Jon Chun, Katherine Elkins
IPHS 391: Interdisciplinary AI Frontiers
This proof of concept shows that an agentic AI system, with the aid of grammatical rules and dictionaries, can effectively identify the form and definition of an Ancient Greek word, a task which current unassisted systems like ChatGPT tend to struggle with.
The Evolution Of The Translations Of Virgil’S “The Aeneid”: An Analytical Comparison Of Robert Faglesand John Dryden's Translations Using Sentiment Analysis And Topic Modeling, Eric Zhang, Katherine Elkins
The Evolution Of The Translations Of Virgil’S “The Aeneid”: An Analytical Comparison Of Robert Faglesand John Dryden's Translations Using Sentiment Analysis And Topic Modeling, Eric Zhang, Katherine Elkins
IPHS 200: Programming Humanity
This research poster aims to explore two English translations of the ancient Roman epic “The Aeneid” written by the poet Virgil. The two versions that were chosen for analysis are John Dryden’s translation from 1697 compared with Robert Fagles’ translation from 2006. This poster seeks to use sentiment analysis and word frequency analysis tools to analytically compare the two versions of the epic. From the results, the older translation appeared to use more formal wording and “dramatic” storytelling structures compared to a more “accurate” rendition of the epic translated using modern language. The sentiment analysis result also demonstrates greater sentiment …
Ai On The Air: Analyzing Ai Sentiment In Us News Reporting, Gwen Eisenbeis, Katherine Elkins
Ai On The Air: Analyzing Ai Sentiment In Us News Reporting, Gwen Eisenbeis, Katherine Elkins
IPHS 200: Programming Humanity
This project examines sentiment surrounding mentions of artificial intelligence within news broadcasts of the three most prominent American news channels: FOX, CNN, and CNBC. Sentiment analysis was conducted on closed captioning data from news clips that mentioned “artificial intelligence” for each of the news channels from 2012 to 2024. This project seeks to evaluate sentiment as mentions of artificial intelligence increase and compare the respective sentiment for each news channel. While clear sentiment differences from the beginning of the time period to the end could not be determined, there was a difference in the overall sentiment trends for each news …
What Makes An Emotionally Compelling Novel? A Sentiment Analysis Of Science Fiction Novels 1984 And We, Annalia Fiore, Katherine Elkins
What Makes An Emotionally Compelling Novel? A Sentiment Analysis Of Science Fiction Novels 1984 And We, Annalia Fiore, Katherine Elkins
IPHS 200: Programming Humanity
The purpose of this project is to compare the Soviet novel We by Yevgeny Zamyatin (1924) to the English novel 1984 by George Orwell (1949). Many have previously drawn comparisons between the two works, but the focus of this research is to find dissimilarities in their respective emotional arcs using sentiment analysis, a computational tool used for processing large bodies of text. The findings of this research were twofold. Firstly, the novel We suffers from an undeveloped emotional arc due to a weak narrative voice and a lack of emotionally varied events. This is especially notable when compared to 1984, …
Optimizing Mlb Roster Selection With Moneyball Ai Scouting Agents: Using High Fidelity Synthetic Data To Optimize Team Performance, Parker Gibbons, Jon Chun
Optimizing Mlb Roster Selection With Moneyball Ai Scouting Agents: Using High Fidelity Synthetic Data To Optimize Team Performance, Parker Gibbons, Jon Chun
IPHS 391: Interdisciplinary AI Frontiers
This project utilizes artificial intelligence Agents to generate high-fidelity synthetic data for Major League Baseball hitters and their statistics over a single 162 game season. The AI evaluates each player based on a five-tool scale, comparing their abilities to one another. Finally, optimization techniques are applied to select an optimal set of thirteen hitters (half of a full MLB roster of twenty-six players), maximizing overall performance while adhering to a specified salary cap. The operating hypothesis is that artificial intelligence can effectively generate high-fidelity synthetic data for baseball hitters and evaluate player performance based on a five-tool scale, given a …
Pitchai: Streamlining Investment Banking Pitches Using Llms, Dillon Cleary
Pitchai: Streamlining Investment Banking Pitches Using Llms, Dillon Cleary
IPHS 391: Interdisciplinary AI Frontiers
Investment banking professionals spend significant time and effort creating client-facing pitch materials, synthesizing large volumes of financial data, and crafting compelling narratives. This project proposes a novel pipeline that leverages large language models (LLMs) and synthetic data generation to streamline and automate the creation of investment banking pitch documents. By drawing on publicly available filings and investor materials of comparable companies, the system generates high-quality, anonymized financial datasets and seamlessly transforms them into investor-ready deliverables—such as valuation ranges and pitch deck materials The result is a more efficient, consistent, and secure approach to preparing client presentations, freeing bankers to focus …
Can Ai Bridge The Aisle? Decoding The 118th Congress Through Artificial Intelligence Legislation, Fiona Hendryx, Katherine Elkins
Can Ai Bridge The Aisle? Decoding The 118th Congress Through Artificial Intelligence Legislation, Fiona Hendryx, Katherine Elkins
IPHS 200: Programming Humanity
The rise of AI’s influence in American life has concerned both the public and the United States Congress. Focusing on the 118th Congress, I identified 365 proposed AI-related bills, only four of which (1.09%) were ultimately passed. Using a combination of natural language processing, topic modeling, and data analysis tools, I investigated why, despite broad bipartisan public and Congressional support, Congress did not pass more AI-related legislation. Amidst shrinking party majority margins and rising polarization among the electorate and elites, the success of AI-related legislative action relies less on popularity and more on party affiliation and control.
Do Autism Diagnostic Narratives Have A Shape? Using Sentiment Analysis To Evaluate Autism Late Diagnosis Narratives And Ai’S Attitude Towards Disability-Related Keywords, Nava Bahrampour, Katherine Elkins, Jon Chun
Do Autism Diagnostic Narratives Have A Shape? Using Sentiment Analysis To Evaluate Autism Late Diagnosis Narratives And Ai’S Attitude Towards Disability-Related Keywords, Nava Bahrampour, Katherine Elkins, Jon Chun
IPHS 200: Programming Humanity
Do autism diagnostic self-narratives have something in common? The meaning of diagnostic labels is a culturally relevant topic in 2024, and I am curious to know if there are similarities in self-narratives about autism diagnosis. We are at an interesting moment in regards to our attitudes about autism and disability, where diagnostic labels like autism are usually viewed as either a tragedy or a relief. I wanted to look at three recent autism diagnostic self-narratives from late-diagnosed women to confirm or refute the existence of a specific type of “narrative” around diagnosis. I was additionally interested in how artificial intelligence …
Sentiment Analysis Of Harry Potter: Exploring Ai Versus Human Interpretation, Xander Newman, Katherine Elkins
Sentiment Analysis Of Harry Potter: Exploring Ai Versus Human Interpretation, Xander Newman, Katherine Elkins
IPHS 200: Programming Humanity
The project starts by examining whether a smaller window size of 5% allows the algorithm to determine cruxes and their sentiment more accurately than the standard 10% window size, using the passages identified by the crux report to assist me. I find that the smaller window size seems to be more accurate for the most part, but this is not always the case. Moreover, regardless of window size, the algorithm struggled with definitively assessing ambivalent sentiment, much like how a reader has their own interpretation of emotionally charged moments. Moreover, using the results of the 5% and 10% window size …
Journey To The West: A Sentiment Analysis Exploration, Ava Yu, Katherine Elkins
Journey To The West: A Sentiment Analysis Exploration, Ava Yu, Katherine Elkins
IPHS 200: Programming Humanity
Journey to the Westis one of the most influential literary works to come out of the East. Set in Tang-era China, the book is a religious allegory following a Buddhist monk and his supernatural disciples who make a pilgrimage from China to India. The chaptered format of the story lends itself to a very episodic approach to conflict & resolution in the story. The text also has a myriad of different influences; it heavily draws inspiration from Buddhist folklore, Confucianist tradition, and Daoist ideology, which were the reigning schools of thought in 16th-century imperial China(the time period in which this …
Human-Chatbot Interaction Patterns: A Topic Modeling Analysis Of 3,275 Conversations With Chatgpt, Hannah Sussman
Human-Chatbot Interaction Patterns: A Topic Modeling Analysis Of 3,275 Conversations With Chatgpt, Hannah Sussman
IPHS 200: Programming Humanity
This research presents a topic modeling analysis of the WILDCHAT-FULL dataset, examining user interactions with ChatGPT across over one million conversations. The study focused specifically on extended conversations (five or more exchanges) between U.S.-based users and ChatGPT in English. Using Latent Dirichlet Allocation (LDA), I identified 50 distinct conversational topics with coherence scores ranging from -1.5 to -14.92 (mean: -4.47). The analysis revealed diverse interaction patterns spanning creative writing, jailbreaking (attempting to get ChatGPT to do something against its guidelines), technical discussions, business applications, and educational queries. A particularly striking finding was that creative writing and role-play scenarios dominated the …
Park Inequality In Miami: How Income And Population Density Shape Access To Green Spaces, Andre Mccloud, Katherine Elkins
Park Inequality In Miami: How Income And Population Density Shape Access To Green Spaces, Andre Mccloud, Katherine Elkins
IPHS 200: Programming Humanity
This data analytics project explores the relationships between park distribution, income levels, and population in Miami, Florida. Data were collected from multiple sources, including the U.S. Census Bureau, Miami-Dade GIS, and other public databases. The data were then visualized using Tableau to identify trends and patterns related to parks. The visualizations revealed that low-income areas have fewer overall parks, a significant number of “mini parks,” and are underserved relative to their population density. The findings of this project highlight inequalities in park allocation and call for policymakers to leverage this information to create equity-driven investments in low-income, high-density communities, ensuring …