Digital Humanities Commons^™

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

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

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

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

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.

Dh In The Classroom Case Study: Alternative Fashion Trends And Omeka.Net, Bonnie Finn, Amelia Cheever

Libraries Staff Publications

As technology embeds into higher education classroom instruction, digital humanities assignments may be looked to as an alternative for writing papers or curating exhibits, and an area of interest for faculty members looking for multiple ways to build student critical thinking skills. This case-study focuses on an 8-week Omeka.net project assignment created collaboratively by a costume/design professor and the fine arts librarian. This article includes the assignment instructions for students, a rubric to use for Omeka metadata, and lead-in assignments that include image citation, visual literacy, and ethically finding image sources.

[This article is an expansion of a paper presented …

Transatlantic Literary Networks, 1949-1972, Cristina Iuli, Stefano Morello

Publications and Research

Il racconto di Donald Barthelme “Critique de la Vie Quotidienne”, pubblicato sul New Yorker il 9 luglio 1971, si apre su una famiglia newyorkese di classe media sull’orlo di una crisi matrimoniale. Wanda, la moglie, sfoglia Elle, costringendo il marito a prestare attenzione alle foto dell’elegante ristrutturazione di un vecchio mulino in Bretagna da cui spiccano arredi di Arne Jacobsen e “cose di plastica arancione e rosso brillante che arrivano da Milano” (Barthelme 1971, p. 26). Barthelme, che aveva trascorso tutta l’infanzia e buona parte della gioventù a Houston, in Texas, dove il padre era direttore del museo di …

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

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

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

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

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 …

The Exploration Of Ancient Poetry: A Decision-Level Fusion Of Large Model Corrections For Allusion Citation Recognition Methods, Wenru Bu, Hao Wang, Xiaomin Li, Shu Zhou, Sanhong Deng

Journal of Scientific Information Research

[Purpose/significance]Allusions, as an important and widely used rhetorical device in literary creation, hold immeasurable value for the study of ancient Chinese literature. Despite this, the automatic identification technology for allusions is not yet mature and currently relies mainly on manual identification, which requires further in-depth research. [Method/process]The article proposes an allusion citation recognition method that incorporates the function of making corrections using large language models at the decision-making level. This method combines traditional sequence labeling techniques with general large language models, introduces prompt templates, and performs output fu‐ sion at the decision layer to improve accuracy. In addition, this study …

Devices And Dining: A Cross-Cultural Analysis Of Mobile Device Use In Italian And American Restaurants, O'Malley Jenkins

Senior Theses

The field of technology ethics has seen increasing growth and interest over the years. Many have begun to consider the impacts of technology’s use and whether it is being employed in a healthy manner by users. However, there has been limited investigation into whether the ways in which technology use varies across cultures. This study begins to address this gap by researching Italian and American device usage in fast food settings. Non-participant naturalistic observations were used to record data for 89 Italian and 88 American customers of fast food restaurants. Analysis of the collected data indicates that Americans use their …

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

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

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

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

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

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 …