Data Science Commons^™

Assessing Frustration Towards Venezuelan Migrants In Columbia: Path Analysis On Newspaper Coded Data, Brian Llinás, Guljannat Huseynli, Erika Frydenlund, Katherine Palacia, Jose Padilla

Modeling, Simulation and Visualization Student Capstone Conference

This study analyzes the impact of Venezuelan migrants on local frustration levels in Colombia. The study found a relationship between the influx of Venezuelan migrants and the level of frustration among locals towards migrants, infrastructure, government, and geopolitics. Additionally, we identified that frustration types have an impact on other frustrations. The study used articles from a national newspaper in Colombia from 2015 to 2020. News articles were coded during a previous study qualitatively and categorized into frustration types. The code frequencies were then used as variables in this study. We used path modeling to statistically study the relationship between dependent …

Learning In A Virtual Environment To Improve Type 2 Diabetes Outcomes: Randomized Controlled Trial, Constance M Johnson, Gail D'Eramo Melkus, Louise Reagan, Wei Pan, Sathya Amarasekara, Katherine Pereira, Nancy Hassell, Sarah Nowlin, Allison Vorderstrasse

Faculty, Staff and Student Publications

Background: Given the importance of self-management in type 2 diabetes mellitus (T2DM), a major aspect of health is providing diabetes self-management education and support. Known barriers include access, availability, and the lack of follow through on referral to education programs. Virtual education and support have increased in use over the last few years.

Objective: The purpose of the Diabetes Learning in a Virtual Environment (LIVE) study was to compare the effects of the LIVE intervention (educational 3D world) to a diabetes self-management education and support control website on diet and physical activity behaviors and behavioral and metabolic outcomes in adults …

Identifying Features And Predicting Consumer Helpfulness Of Product Reviews, Triston Hudgins, Shijo Joseph, Douglas Yip, Gaston Besanson

SMU Data Science Review

Major corporations utilize data from online platforms to make user product or service recommendations. Companies like Netflix, Amazon, Yelp, and Spotify rely on purchasing trends, user reviews, and helpfulness votes to make content recommendations. This strategy can increase user engagement on a company's platform. However, misleading and/or spam reviews significantly hinder the success of these recommendation strategies. The rise of social media has made it increasingly difficult to distinguish between authentic content and advertising, leading to a burst of deceptive reviews across the marketplace. The helpfulness of the review is subjective to a voting system. As such, this study aims …

Bridging The Chasm Between Fundamental, Momentum, And Quantitative Investing, Allen Hoskins, Jeff Reed, Robert Slater

SMU Data Science Review

A chasm exists between the active public equity investment management industry's fundamental, momentum, and quantitative styles. In this study, the researchers explore ways to bridge this gap by leveraging domain knowledge, fundamental analysis, momentum, crowdsourcing, and data science methods. This research also seeks to test the developed tools and strategies during the volatile time period of 2020 and 2021.

Question Answering With Distilled Bert Models: A Case Study For Biomedical Data, Brittany Lewandowski, Rayon Morris, Pearly Merin Paul, Robert Slater

SMU Data Science Review

In the healthcare industry today, 80% of data is unstructured (Razzak et al., 2019). The challenge this imposes on healthcare providers is that they rely on unstructured data to inform their decision-making. Although Electronic Health Records (EHRs) exist to integrate patient data, healthcare providers are still challenged with searching for information and answers contained within unstructured data. Prior NLP and Deep Learning research has shown that these methods can improve information extraction on unstructured medical documents. This research expands upon those studies by developing a Question Answering system using distilled BERT models. Healthcare providers can use this system on their …

Comparison Of Sampling Methods For Predicting Wine Quality Based On Physicochemical Properties, Robert Burigo, Scott Frazier, Eli Kravez, Nibhrat Lohia

SMU Data Science Review

Using the physicochemical properties of wine to predict quality has been done in numerous studies. Given the nature of these properties, the data is inherently skewed. Previous works have focused on handful of sampling techniques to balance the data. This research compares multiple sampling techniques in predicting the target with limited data. For this purpose, an ensemble model is used to evaluate the different techniques. There was no evidence found in this research to conclude that there are specific oversampling methods that improve random forest classifier for a multi-class problem.

Following The Crowd: Beginners Investors Guide To The Options Market, Jeremy Dawkins, Alexy Morris, Jacob Gipson, Masoud Valizadeh

SMU Data Science Review

While the options market may be intimidating for a beginner, having the right tools can help improve the outcome of their investments. This project aims to develop a tool that uses time-series analysis and forecasting to model the future demand of S&P 500 and AAPL options contracts. The open interest of these contracts will be analyzed using various models such as AR, ARIMA, Neural Networks, and VAR, along with the put-call ratio. The goal is not to make buy or sell recommendations, but alert the user when money is flowing into a security or index. Of all the models, the …

The Role Of Machine Learning In Improved Functionality Of Lower Limb Prostheses, Joaquin Dominguez, Richard Kim, Robert Slater

SMU Data Science Review

Lower-limb amputations can cause a plethora of obstacles that lead to a lower quality of life. Implementing machine learning techniques means advanced prosthetics can contribute to facilitating the lives of those that live with lower-limb amputations. Using the publicly available HuGaDB data set, the current study investigates several classification models (random forest, neural network, and Vowpal Wabbit) to predict the locomotive intentions of individuals using lower-limb prostheses. The results of this study show that the neural network model yielded the highest accuracy, comparable precision, and recall scores to the other models. However, the Vowpal Wabbit model's advantage in speed may …

Using Nlp To Model U.S. Supreme Court Cases, Katherine Lockard, Robert Slater, Brandon Sucrese

SMU Data Science Review

The advantages of employing text analysis to uncover policy positions, generate legal predictions, and inform or evaluate reform practices are multifold. Given the far-reaching effects of legislation at all levels of society these insights and their continued improvement are impactful. This research explores the use of natural language processing (NLP) and machine learning to predictively model U.S. Supreme Court case outcomes based on textual case facts. The final model achieved an F1-score of .324 and an AUC of .68. This suggests that the model can distinguish between the two target classes; however, further research is needed before machine learning models …

Content-Based Unsupervised Fake News Detection On Ukraine-Russia War, Yucheol Shin, Yvan Sojdehei, Limin Zheng, Brad Blanchard

SMU Data Science Review

The Ukrainian-Russian war has garnered significant attention worldwide, with fake news obstructing the formation of public opinion and disseminating false information. This scholarly paper explores the use of unsupervised learning methods and the Bidirectional Encoder Representations from Transformers (BERT) to detect fake news in news articles from various sources. BERT topic modeling is applied to cluster news articles by their respective topics, followed by summarization to measure the similarity scores. The hypothesis posits that topics with larger variances are more likely to contain fake news. The proposed method was evaluated using a dataset of approximately 1000 labeled news articles related …

Professor Text: University Fundraising Optimization, Braden Anderson, Connor Dobbs, Hien Lam, John Santerre

SMU Data Science Review

University fundraising campaigns are a unique type of cause-related marketing with its own challenges and opportunities. Campaigns like this typically last an extended period, such as five or more years, and goals exist beyond the dollar amount raised. These supplemental goals, such as awareness among potential future donators or brand reputation within the local community, are important to consider and strategize. There can also be unique limitations, such as requiring advertising specifically on recent large gifts or endowment programs. This research explores how machine learning techniques such as natural language processing can be used to optimize a fundraising campaign strategy, …

Nviz: Unraveling Neural Networks Through Visualization, Kevin Hoffman

Mathematics, Computer Science & Statistics Presentations

The growing utility of artificial intelligence (AI) is attributed to the development of neural networks. These networks are a class of models that make predictions based on previously observed data. While the inferential power of neural networks is great, the ability to explain their results is difficult because the underlying model is automatically generated. The AI community commonly refers to neural networks as black boxes because the patterns they learn from the data are not easily understood. This project aims to improve the visibility of patterns that neural networks identify in data. Through an interactive web application, NVIZ affords the …

R Text Analysis For Adam Smith Cie Selected Works, Charlotte Grahame

Mathematics, Computer Science & Statistics Presentations

Text mining and text analysis is a way of understanding text documents using r coding that is more frequently used for numbered data. It helps with understanding portions of the text and drawing conclusions from there. This research looks specifically at the Adam Smith required documents that are used in the CIE course designated for freshmen. It looks at sentiments of the documents, including word sentiment, sentence sentiment, page and overall document sentiment as well. It provides visuals of word clouds to portray word frequency, tf-idf (which is explained in the presentation) and bigram analysis.

Cie Text Analysis: Narrative Of The Life Of Frederick Douglass, The Declaration Of Independence, And The Declaration Of Sentiments, Arianna Knipe

Mathematics, Computer Science & Statistics Presentations

Our STAT-451 class has worked with analyzing the words from CIE texts and assigning them to a sentiment or feeling and comparing them with one another using RStudio. This project analyzes texts from three sources: The Narrative of the Life of Frederick Douglass, The Declaration of Independence and the Declaration of Sentiments.

Rethinking" Risk" In Algorithmic Systems Through A Computational Narrative Analysis Of Casenotes In Child-Welfare, Devansh Saxena, Erina Seh-Young Moon, Aryan Chaurasia, Yixin Guan, Shion Guha

Health Services and Informatics Research

No abstract provided.

A Multi-Site Randomized Trial Of A Clinical Decision Support Intervention To Improve Problem List Completeness, Adam Wright, Richard Schreiber, David W Bates, Skye Aaron, Angela Ai, Raja Arul Cholan, Akshay Desai, Miguel Divo, David A Dorr, Thu-Trang Hickman, Salman Hussain, Shari Just, Brian Koh, Stuart Lipsitz, Dustin Mcevoy, Trent Rosenbloom, Elise Russo, David Yut-Chee Ting, Asli Weitkamp, Dean F Sittig

Faculty, Staff and Student Publications

OBJECTIVE: To improve problem list documentation and care quality.

MATERIALS AND METHODS: We developed algorithms to infer clinical problems a patient has that are not recorded on the coded problem list using structured data in the electronic health record (EHR) for 12 clinically significant heart, lung, and blood diseases. We also developed a clinical decision support (CDS) intervention which suggests adding missing problems to the problem list. We evaluated the intervention at 4 diverse healthcare systems using 3 different EHRs in a randomized trial using 3 predetermined outcome measures: alert acceptance, problem addition, and National Committee for Quality Assurance Healthcare …

The Potential Regulation Of A-To-I Rna Editing On Genes In Parkinson's Disease, Sijia Wu, Qiuping Xue, Xinyu Qin, Xiaoming Wu, Pora Kim, Jacqueline Chyr, Xiaobo Zhou, Liyu Huang

Faculty, Staff and Student Publications

Parkinson's disease (PD) is characterized by dopaminergic neurodegeneration and an abnormal accumulation of α-synuclein aggregates. A number of genetic factors have been shown to increase the risk of PD. Exploring the underlying molecular mechanisms that mediate PD's transcriptomic diversity can help us understand neurodegenerative pathogenesis. In this study, we identified 9897 A-to-I RNA editing events associated with 6286 genes across 372 PD patients. Of them, 72 RNA editing events altered miRNA binding sites and this may directly affect miRNA regulations of their host genes. However, RNA editing effects on the miRNA regulation of genes are more complex. They can (1) …

Topological Data Analysis Of Weight Spaces In Convolutional Neural Networks, Adam Wagenknecht

Dissertations

Convolutional Neural Networks (CNNs) have become one of the most commonly used tools for performing image classification. Unfortunately, as with most machine learning algorithms, CNNs suffer from a lack of interpretability. CNNs are trained by using a training data set and a loss function to tune a set of parameters known as the layer weights. This tuning process is based on the classical method of gradient descent, but it relies on a strong stochastic component, which makes the weight behavior during training difficult to understand. However, since CNNs are governed largely by the weights that make up each of the …

Comparative Analysis Of Feature Selection And Machine Learning Models For Breast Cancer Risk Prediction, Tonmoy Roy

Student Research Symposium

The comparative analysis of feature selection and machine learning models for breast cancer risk prediction aims to develop accurate and efficient models for diagnosing breast cancer. In this analysis, we explore different feature selection techniques and machine learning models to identify the most effective feature combination for breast cancer risk prediction. Our study provides valuable insights into the importance of feature selection and model selection in developing accurate breast cancer risk prediction models. Using the three features provide high accuracy to detect breast cancer. Overall, this study highlights the importance of combining feature selection techniques with machine learning algorithms to …

Physio-Psycho-Social Interaction Mechanism In Dyadic Health Of Young And Middle-Aged Stroke Survivors And Their Spousal Caregivers: A Longitudinal Observational Study Protocol, Dandan Xiang, Zhen-Xiang Zhang, Song Ge, Wen Na Wang, Bei-Lei Lin, Su-Yan Chen, Er-Feng Guo, Peng-Bo Zhang, Zhi-Wei Liu, Hui Li, Yong-Xia Mei

Faculty, Staff and Student Publications

Introduction: In recent years, stroke has become more common among young people. Stroke not only has a profound impact on patients' health but also incurs stress and health threats to their caregivers, especially spousal caregivers. Moreover, the health of stroke survivors and their caregivers is interdependent. To our knowledge, no study has explored dyadic health of young and middle-aged stroke survivors and their spousal caregivers from physiological, psychological and social perspectives. Therefore, this proposed study aims to explore the mechanism of how physiological, psychological and social factors affect dyadic health of young and middle-aged stroke survivors and their spousal caregivers. …

Quantitative Proteomic Screening Uncovers Candidate Diagnostic And Monitoring Serum Biomarkers Of Ankylosing Spondylitis, Mark Hwang, Shervin Assassi, Jim Zheng, Jessica Castillo, Reyna Chavez, Kamala Vanarsa, Chandra Mohan, John Reveille

Faculty, Staff and Student Publications

BACKGROUND: We sought to discover serum biomarkers of ankylosing spondylitis (AS) for diagnosis and monitoring disease activity.

METHODS: We studied biologic-treatment-naïve AS and healthy control (HC) patients' sera. Eighty samples matched by age, gender, and race (1:1:1 ratio) for AS patients with active disease, inactive disease, and HC were analyzed with SOMAscan™, an aptamer-based discovery platform. T-tests tests were performed for high/low-disease activity AS patients versus HCs (diagnosis) and high versus low disease activity (Monitoring) in a 2:1 and 1:1 ratio, respectively, to identify differentially expressed proteins (DEPs). We used the Cytoscape Molecular Complex Detection (MCODE) plugin to find clusters …

Distribution Of Serum Uric Acid Concentration And Its Association With Lipid Profiles: A Single-Center Retrospective Study In Children Aged 3 To 12 Years With Adenoid And Tonsillar Hypertrophy, Jiating Yu, Xin Liu, Honglei Ji, Yawei Zhang, Hanqiang Zhan, Ziyin Zhang, Jianguo Wen, Zhimin Wang

Faculty, Staff and Student Publications

BACKGROUND: Presently, there is no consensus regarding the optimal serum uric acid (SUA) concentration for pediatric patients. Adenoid and tonsillar hypertrophy is considered to be closely associated with pediatric metabolic syndrome and cardiovascular risk and is a common condition in children admitted to the hospital. Therefore, we aimed to evaluate the relationship between SUA and dyslipidemia and propose a reference range for SUA concentration that is associated with a healthy lipid profile in hospitalized children with adenoid and tonsillar hypertrophy.

METHODS: Preoperative data from 4922 children admitted for elective adenoidectomy and/or tonsillectomy surgery due to adenoid and tonsillar hypertrophy were …

Domain Specific Analysis Of Privacy Practices And Concerns In The Mobile Application Market, Fahimeh Ebrahimi Meymand

LSU Doctoral Dissertations

Mobile applications (apps) constantly demand access to sensitive user information in exchange for more personalized services. These-mostly unjustified-data collection tactics have raised major privacy concerns among mobile app users. Existing research on mobile app privacy aims to identify these concerns, expose apps with malicious data collection practices, assess the quality of apps' privacy policies, and propose automated solutions for privacy leak detection and prevention. However, existing solutions are generic, frequently missing the contextual characteristics of different application domains. To address these limitations, in this dissertation, we study privacy in the app store at a domain level. Our objective is to …

Twitter Database Health Visualization, Tor Qureshi

2023 IDIR Data Visualization Challenges-Archive

By utilizing the Twitter IDs and their corresponding posts in the database, we were able to create a UI that generates a graph that demonstrates a word or phrases' usage over time based on the number of times mentioned within the time span of the database (2011-2023). In the future, this could be improved by combining it with the Twitter API to monitor live trends and associations.

Analysis Of Hawk Mountain Wind Speed To Raptor Count Trends From 1976 Through 2021, Dale E. Parson

Computer Science and Information Technology Faculty

This analysis of summer 2023 is a sequel to the summer 2022 Analysis of Hawk Mountain Sanctuary Observation Data from 1976 through 2021, also available as a web page through end of 2024 here. A presentation of that and subsequent analysis presented at Kutztown University in November 2022 and to Hawk Mountain researchers in January 2023 is available as PDF slides here and also on the web through 2024 here. This work was funded by a Kutztown University Research Grant for spring 2022 through summer 2023. Analytical use of these data proceeded through a subset of projects in three courses …

Investigating The Use Of Recurrent Neural Networks In Modeling Guitar Distortion Effects, Caleb Koch, Scott Hawley, Andrew Fyfe

[Archive] Belmont University Research Symposium (BURS)

Guitar players have been modifying their guitar tone with audio effects ever since the mid-20th century. Traditionally, these effects have been achieved by passing a guitar signal through a series of electronic circuits which modify the signal to produce the desired audio effect. With advances in computer technology, audio “plugins” have been created to produce audio effects digitally through programming algorithms. More recently, machine learning researchers have been exploring the use of neural networks to replicate and produce audio effects initially created by analog and digital effects units. Recurrent Neural Networks have proven to be exceptional at modeling audio effects …

Sports Data Science Job Requirements, Cam E. Morse

Student Publications

Data science is an extremely fast growing field in which job opportunities are opening in every industry related to data science. Within the data science field is the sports data science industry which has it's own requirements and specificities that may not be present in other industries. In this paper, research is done using multiple job posting websites such as LinkedIn, Indeed, Sportstek jobs, and TeamworkOnline to explore the job descriptions of many different sports data science jobs. These job descriptions are then examined using Python coding to find the frequencies of specific data science skills in the various job …

Beyond News Values On Twitter: Predicting Factors That Drive User Engagement In News, Zhiyan Zhong

Dartmouth College Master’s Theses

When deciding on what news stories to cover, traditional journalism determines news values by following several elements of newsworthiness, such as impact, timeliness, and prominence. However, these guidelines do not always seem to correspond with the success of content on social media. As people are increasingly turning to social media for news, our research aims to understand and predict factors that drive user engagement for news on social media. In this study, we analyze news content published on Twitter, and examine a diverse set of characteristics like metrics retrieved from the Twitter API and semantics by natural language processing, including …

Discerning Conversational Context In Online Health Communities For Personalized Digital Behavior Change Solutions Using Pragmatics To Reveal Intent In Social Media (Prism) Framework, Tavleen Singh, Kirk Roberts, Trevor Cohen, Nathan Cobb, Amy Franklin, Sahiti Myneni

Faculty, Staff and Student Publications

BACKGROUND: Online health communities (OHCs) have emerged as prominent platforms for behavior modification, and the digitization of online peer interactions has afforded researchers with unique opportunities to model multilevel mechanisms that drive behavior change. Existing studies, however, have been limited by a lack of methods that allow the capture of conversational context and socio-behavioral dynamics at scale, as manifested in these digital platforms.

OBJECTIVE: We develop, evaluate, and apply a novel methodological framework, Pragmatics to Reveal Intent in Social Media (PRISM), to facilitate granular characterization of peer interactions by combining multidimensional facets of human communication.

METHODS: We developed and applied …

Prediction Of Brain Metastases Development In Patients With Lung Cancer By Explainable Artificial Intelligence From Electronic Health Records, Zhao Li, Rongbin Li, Yujia Zhou, Laila Rasmy, Degui Zhi, Ping Zhu, Antonio Dono, Xiaoqian Jiang, Hua Xu, Yoshua Esquenazi, W Jim Zheng

Faculty, Staff and Student Publications

PURPOSE: Early detection of brain metastases (BMs) is critical for prompt treatment and optimal control of the disease. In this study, we seek to predict the risk of developing BM among patients diagnosed with lung cancer on the basis of electronic health record (EHR) data and to understand what factors are important for the model to predict BM development through explainable artificial intelligence approaches accurately.

MATERIALS AND METHODS: We trained a recurrent neural network model, REverse Time AttentIoN (RETAIN), to predict the risk of developing BM using structured EHR data. To interpret the model's decision process, we analyzed the attention …