Digital Commons Network^™

On Explaining The Sentiments In Prediction Of Stock Movement: An Xai-Based Analysis, D. J. Ranade, Sarthak Bhaya, Siddhanth Bhimakari, Moe Aye Chan, Keith Quille, Rajesh Jaiswal

Research Outputs: 2025-Present

Empirical evidence shows that short-horizon equity returns are not fully random; there is a degree of predictability, especially when traditional financial data is combined with public sentiment measures. Sentiment-based features have been used to improve prediction tasks, but there is limited explanation of their contribution. In addition, the impact of news on investor sentiment, and how that impact decays over time, has rarely been investigated. To bridge this gap, we integrate sentiment scores extracted from financial news headlines using HKUST FinBERT with daily market-based indicators to predict the next-day price direction. We evaluated two aggregation strategies: the most confident news …

Environmental And Social Strategies, And Sustainable Performance: The Mediating Role Of Management Control Systems, Zheng Siqi

Student Works (2020-2029)

This study investigates how environmental and social (E&S) strategies influence enterprise sustainability performance (SP), with a focus on the mediating roles of Environmental Management Control Systems (EMCS) and Social Management Control Systems (SMCS). Anchored in the Resource-Based View (RBV), the study conceptualizes E&S strategies, EMCS, and SMCS as internal organizational resources that support the implementation of sustainability-related strategic intent. Although Chinese manufacturing enterprises face increasing regulatory and societal expectations regarding environmental and social responsibilities, prior research has primarily examined the direct association between sustainability strategies and performance outcomes or has treated sustainability control systems as aggregated constructs, providing comparatively less …

Weather As A Weapon Of War: The Legality Of Cloud Seeding Under International Humanitarian Law, Fatemah Albader

Seattle Journal of Technology, Environmental, & Innovation Law

No abstract provided.

The Double-Edged Sword Of Ai In Elections: Navigating Risks And Opportunities In Washington State, Payvand Khastkhodaei

Seattle Journal of Technology, Environmental, & Innovation Law

No abstract provided.

Deepfake Danger: The Urgent Need For Federal Protections Against Ai-Generated Pornography, Benjamin Comfort

Seattle Journal of Technology, Environmental, & Innovation Law

No abstract provided.

Qualitative Methods For Health Research, 5th Edition: A Review, Rikki Mangrum

The Qualitative Report

Qualitative Methods for Health Research (5^th ed.; Green et al., 2025) is an introductory textbook that provides an overview of qualitative methodology as it is used in health-related fields, including public health, healthcare delivery, and medical science. It provides instruction on theoretical principles, core methods and their implementation, and related topics such as developing research proposals and publishing study results. This new addition includes updated content and new content pertinent to recent developments that have affected health research practices, such as the COVID-19 pandemic and broader awareness of the impact of colonialism and racial discrimination.

On The Automatic Image Captioning Task In Italian: A Human-Centric Approach, Valentina De Amicis, Rajesh Jaiswal, Fernando Perez-Tellez

Research Outputs: 2025-Present

Automatic Image Captioning (AIC) combines two distinct machine learning disciplines, Computer Vision (CV) and Natural Language Processing (NLP), forming a challenging research landscape. Much research has been carried out for AIC in the English language facilitated by the availability of English language datasets. However, this is not true for other languages. The aim of this work is to investigate existing AIC models' compatibility for the Italian language. The scope of this research will be aimed to reduced complexity, improved efficiency, and readily trainable models on smaller datasets while maintaining an acceptable level of caption quality. The popular Show and Tell …

Right-To-Be-Forgotten By Design In Adapter-Tuned Transformers, D. J. Ranade, Rajesh Jaiswal

Research Outputs: 2025-Present

Enforcing the Right-to-be-Forgotten (RtBF) in transformer models remains challenging: full retraining is costly, while post-hoc unlearning often leaves residual signal without guarantees. We propose an RtBF-by-design protocol for adapter-tuned models that combines differential privacy (DP) applied to Low-Rank Adaptation (LoRA) adapters with a matched-control Deletion Sufficiency Certificate (DSC). A DP-trained model on the full dataset is evaluated against an identically configured and trained redacted-control model using three complementary criteria - prediction agreement, membership-inference separability, and calibrated confidence exposure - to assess deletion sufficiency. The DSC offers an operational go/no-go decision for RtBF without requiring full retraining. Experiments on a text …

Modeling Spasticity: A Systematic Review, Gaby Gonzalez Chan, Jonathan Marsden, Alexander Besinis, Pablo Borja, Hilary Gunn

School of Health Professions

Spasticity, a type of hypertonia characterized by a velocity-dependent increase in muscle tone, is associated with damage to the brain and/or spinal cord in different neurological conditions. However, secondary non-neurological factors, such as soft tissue changes, can complicate the assessment and differentiation of the underlying causes. Accurate assessment is crucial for effective treatment planning, with clinicians relying on passive movement to grade the ‘feel’ of the spastic limb. This review aims to identify and evaluate the feasibility of spasticity models or simulations for clinical teaching. Models based on human spastic limbs were examined, with no restrictions on specific conditions or …

Sting-Induced Blood-Brain Barrier Opening Combined With Radiotherapy Potentiates Antitumor Response In A High-Grade Glioma Model, Shashwat Tripathi, Hinda Najem, Lisa Hurley, Ruochen Du, Crismita Dmello, Heba Ali, Kathleen Mccortney, Karl J Habashy, Peng Zhang, Craig M Horbinski, Lara Leoni, Ryan J Avery, Rimas V Lukas, Timothy L Sita, David R Raleigh, Sean Sachdev, Roger Stupp, Maciej S Lesniak, David M Ashley, Daniele Procissi, Michael A Curran, Irina Balyasnikova, Amy B Heimberger

Faculty, Staff and Student Publications

Radiation therapy (RT) is the standard of care for glioblastoma but is not curative. Triggering the cGAS/stimulator of interferon genes (STING) pathway with potent agonists, such as 8803, exerts activity across high-grade glioma preclinical models. To determine if the combination of 8803 with RT warrants consideration in the up-front treatment setting and to clarify the underlying mechanisms of therapeutic activity, C57BL/6J mice harboring intracerebral CT-2A or QPP8v gliomas were treated with RT, intratumoral 8803, or both. The treatment with the combination resulted in 80% long-term survival in the CT-2A model but not in the radiation-resistant QPP8v model. This therapeutic effect …

Meta-Analytic And Economic Evaluation Of Fungicide Programs Applied For Managing Sclerotinia Stem Rot In Soybean Across The North Central United States, Hope Renfroe-Becton, Maria Oros, Adam M. Byrne, Martin I. Chilvers, Nathan Kleczewski, Horacio D. Lopez-Nicora, Brian D. Mueller, Daren S. Mueller, Damon L. Smith, Darcy E P Telenko, Richard Wade Webster

APC Fund Awardees

Farmers in the North Central United States are at risk of having soybean yield robbed due to infection by Sclerotinia sclerotiorum, the causal agent of Sclerotinia stem rot (SSR). While certain management strategies, such as wide row spacings, lower plant populations, and resistant varieties, can reduce SSR development, there is often a negative yield impact associated with these strategies. Conversely, chemical management strategies do not have an associated yield drag, and therefore, they have been the primary tool for suppressing SSR development. Independent chemical programs were evaluated across eight states from 2017 to 2024, resulting in 32 site-years (n = …

Discourses On Homosexuality And The Paradox Of The Closet In The New Life (2023) By Tom Crewe, Paramita Ayuningtyas, Shuri Mariasih Gietty Tambunan, Asri Saraswati

Bahasa dan Seni: Jurnal Bahasa, Sastra, Seni, dan Pengajarannya

This article offers a critical examination of Tom Crewe's biographical novel The New Life (2023), focusing on its representation of homosexual subjectivity in Victorian England—a historical context defined by restrictive moral norms and punitive legal regimes that criminalised same-sex relationships. Drawing on Michel Foucault's theory of discursive power, Eve Kosofsky Sedgwick's concept of the closet, and Michael Boucai's topology of the closet, the study demonstrates that the novel portrays the closet not merely as a private site of concealment but as a complex social mechanism shaped by legal regulation, gender norms, and class-based power relations. Building on this theoretical framework, …

Roles And Strengths Of Therapeutic Recreation Professionals In Service Provision: A Strengths-Based Approach, M. Rebecca Genoe, Linda Ostryzniuk, Kathy Park, Sherri Nelson, Douglas G. Cripps, Donna Boser

The Qualitative Report

Therapeutic Recreation professionals work in healthcare and community-based settings where they utilize recreation and leisure to improve quality of life. Despite their contributions, Therapeutic Recreation often goes unrecognized as an important component of the healthcare team. The purpose of this study was to explore the strengths and successes of Therapeutic Recreation professionals. We aimed to explore how Therapeutic Recreation professionals identify and perceive their roles, and what strengths they use within their roles. Data was collected through 19 individual interviews and eight focus groups with Therapeutic Recreation professionals and analyzed thematically. The theme of “nurturing well-being through leisure” was generated …

The Prospector, Februrary 16, 2026, Utep Student Publications

The Prospector

No abstract provided.

Mmu: 02/16/26-02/22/26, Student Bar Association

Monday Morning Update

This Week @ NDLS

Mass Times

Commons Daily Menu

Saint of the Week

General Announcements

Transformative Technology And Shortening The Statute Of Limitations Applicable To Taxpayers, Jay A. Soled, Leslie Book

Faculty Publications

When it comes to submitting tax returns and paying taxes, most taxpayers understand the nature of their civic duties and do so dutifully, if not willingly. However, many taxpayers fail to grasp why the IRS has such an elongated time period—namely, three years— to audit their tax returns and propose an assessment. Indeed, when the IRS exercises its oversight authority, records may no longer be available, and memories may be dulled.

Since the original institution of the three-year tax assessment limitations period nearly a century ago, tremendous technological strides have been made. Indeed, over ninety percent of income tax returns …

Automated Quantification Of Movement Qualities In The Human Upper Extremity After Stroke Using A Wearable Robot., Yoon No Gregory Hong, Kyoungsoon Kim, Sheng Li, Marcia K O'Malley, Ashish D Deshpande, Jinsook Roh

Faculty, Staff and Student Publications

Background: Stroke is a leading cause of long-term adult disability, with approximately 80% of survivors experiencing upper extremity (UE) motor impairments. Conventional tools like the Fugl-Meyer Assessment (FMA) are widely used but limited by ordinal scales and subjective visual observation. While wearable robotics offer high-resolution data, their clinical translation is hindered by a lack of standardized protocols and limited interpretability for clinical decision-making.

Objective: This study aimed to develop an objective, standardized, and clinically interpretable method to quantify UE motor qualities by integrating wearable robotic technology with traditional clinical assessment tasks.

Methods: Ten healthy individuals and ten stroke survivors performed …

Myelodysplastic Syndrome Secondary To Chimeric Antigen Receptor T-Cell (Car-T) Therapy For The Treatment Of Relapsed/Refractory Multiple Myeloma, Waqqas Tai, Daniel Kim, Joe Dib, Jessica Thomas, Swathi Gopishetty, Precious Idogun, Afoma Anyadibe, Anuoluwa Ayetoran, Syed Zaidi, Savitha Balaraman, Ishmael Jaiyesimi

Student Publications

We present the case of a 65-year-old man with relapsed/refractory multiple myeloma (RRMM) who developed therapy-related myelodysplastic syndrome (MDS) following chimeric antigen receptor T-cell (CAR-T) therapy with idecabtagene vicleucel (ide-cel). The patient, initially diagnosed in 2019, underwent multiple lines of therapy, including high-dose melphalan with autologous stem cell transplantation, before receiving ide-cel for progressive disease. Despite initial remission, a day 100 bone marrow biopsy revealed MDS with a 7q deletion, a cytogenetic abnormality not present on prior marrow evaluations. While CAR-T therapy has revolutionized RRMM treatment, long-term complications such as therapy-related hematologic malignancy remain under-recognized.

The temporal relationship between CAR-T …

Riding The Rush: A Deep Learning Approach To Bus Overcrowding Prediction, Nikhitha Guttula, Akshay Vellanki, J. S.N. Sudhamayi Putchakayalapalli, Akhil Ratnam, Rajesh Jaiswal, Keith Quille

Research Outputs: 2025-Present

Overcrowding in public transport is often explained by common-sense factors such as peak hours and busy routes. While these patterns are well known, what remains unclear is whether machine learning can uncover less obvious interactions that go beyond human intuition. This study investigates whether predictive models can not only forecast bus overcrowding but also reveal overlooked dynamics within operational data that traditional analysis might miss. Using timestamped stop-level records containing temporal and route-based features (hour of day, day of week, stop ID, line ID, and vehicle capacity), we develop machine learning and deep learning models to identify high-load events. Explainable …

Data Preprocessing Methods For Automating Mlops Pipelines: A Comparative Study, Surya Teja Gowd Ayinavilli, Keith Quille, Tarry Singh

Research Outputs: 2025-Present

Preprocessing tools for data are increasingly being utilized in MLOps pipelines to develop models automatically. However, the fairness and reliability of automated processes are inadequately researched, risking causing performance degradation or bias. This discrepancy is addressed in this thesis with an evaluation of automated data preprocessing methods compared to a baseline approach, designed for integration into a TensorFlow Extended (TFX) pipeline. The performance of each method was compared in terms of classification measures and subgroup fairness to determine potential bias. Significance tests were employed to compare the performance of each automated method against the baseline. The results indicate that around …

Educators' Evaluation Of Explanation Types In Xai For Higher Education Dropout, Henry Maathuis, Jan Glazenborg, Meike Grol, Keith Quille

Research Outputs: 2025-Present

First-year student dropout rates represent a global challenge, particularly in Computer Science programs. In response, the Predict Student Success (PreSS) tool was developed over two decades using Naïve Bayes, a black box machine learning model, to identify students at risk of early withdrawal or academic failure. Given growing concerns about the use of black box models in high-stakes domains such as education, this study builds on former research by comparing the Naïve Bayes model to three glass box AI models: Decision Tree, Explainable Boosting Machine, and Automatic Piecewise Linear Regression. These models were used to generate four types of explainable …

Leveraging Graph Neural Networks For Explainable And Adaptive Seismic Risk Modelling (Work In Progress)), Shivam Tyagi, Musfira Jilani

Research Outputs: 2025-Present

Seismic risk modeling predicts the likelihood of earthquake occurrences in different regions over time. This presents a distinctive challenge as both the spatial structure of underlying geological features and the temporal evolution of seismic events must be accounted for accurately. In addition, for planners and decision-makers, it is essential that such models are not only accurate but also explainable. However, most existing models lack explainability, which limits their usefulness. This research proposes a novel graph neural network based seismic risk modeling methodology that is both explainable as well as adaptable, as it allows decision-makers the flexibility to choose the risk …

Social Prescribing For Refugee Populations: A Protocol For A Rapid Realist Review Of International Evidence, Victoria Touzel, Anna-Lena Esser, Kerryn Husk, Doreen Reifegerste

Peninsula Medical School

BackgroundSocial prescribing addresses complex individual health and social needs through person-centered referral from healthcare into community settings, supporting wellbeing and integrated care. While evidence for majority populations continues to expand, no review has yet synthesized evidence specifically for refugee populations, despite this group facing profound social and systemic barriers. As such, this protocol defines the research objectives for a rapid realist review that will identify what approaches to social interventions work for refugee populations, for whom they are effective, and under which circumstances.MethodsA rapid realist review will be conducted to identify relevant evidence from both social prescribing interventions and social …

Ontology-Based E-Commerce Recommender System: A Hybrid Semantic Filtering Approach, Shaymaa Al-Juboori, Jocelyn Pua, Su-Cheng Haw, Lucia Dwi Krisnawati, Gee-Kok Tong

School of Engineering, Computing and Mathematics

The rapid growth of e-commerce has led to product overload, which has resulted in personalized product discovery becoming a crucial problem for consumers. Classic recommender systems (RS), which rely heavily on content-based filtering or collaborative filtering, tend to face well-known problems such as cold start, data sparsity, and ignorance of semantics. Such constraints frequently result in irrelevant or redundant suggestions, thereby lowering the user satisfaction and conversions. This study presents a hybrid ontology-based e-commerce recommender system that combines symbolic reasoning with deep semantic matching. The system is based on a Neo4j graph database to capture structured product relationships and is …

Chimes: February 16, 2026, Calvin University

Chimes

Faculty Senate approves a reduction in graduation credit-hour requirement by Maya Oeverman

Fluoridation documentary examines how we talk about politics by Alec DeYoung

Track and field gains momentum as indoor championships are underway by Zach Kern & Hendrick Beelen

Lent: Going back to basics by Ella Vanden Berg

What it means to be American by Maya Oeverman

Relationship Between Navigation Success, Diagnostic Accuracy, And Ventilation Strategy: Retrospective Chart Review Of 224 Consecutive Navigational Bronchoscopic Procedures Performed Under General Anesthesia, Basavana Goudra, Prarthna Chandar, Divakara Gouda, Harrison Yang, Ganan Muhunthan, Suvan Sundaresh, Michael Stuart Green

Department of Medicine Faculty Papers

Background: Navigational bronchoscopy (NB) enables precise sampling of peripheral and central pulmonary nodules using shape-sensing or electromagnetic guidance. A major challenge is anesthesia-induced atelectasis, which alters lung anatomy, reduces registration accuracy, and is known to lower diagnostic accuracy. To counteract this, ventilatory protocols such as the Ventilatory Strategy to Prevent Atelectasis (VESPA) and the Lung Navigation Ventilation Protocol (LNVP) have been recommended. Their adoption and clinical impact, however, remain uncertain. Methods: We conducted a retrospective review of 224 consecutive NB procedures performed under general anesthesia at a single academic medical center (January 2020–August 2024). Demographic, anesthetic, and ventilatory data were …

Communicative Legitimacy: The Supreme Court's Hidden Cultural Binaries In The U.S. Civil Sphere, Steven Arrigg Koh

Faculty Scholarship

How does the U.S. Supreme Court establish its legitimacy? Over the last two hundred years in U.S. society, the Court has interpreted the U.S. Constitution on watershed issues such as slavery, segregation, and marriage equality. And yet the Constitution is just 7,591 words. A puzzle thus emerges: how does the Court intelligibly interpret this short text for U.S. society? This article develops a new theoretical and empirical cultural sociological account of such Supreme Court decision-making, which it calls “communicative legitimacy.” According to this theory, which draws on Jeffrey Alexander’s civil sphere theory, the Court consistently and inevitably draws on a …

Strspy2.0: Unlocking The Potential Of Long Reads For Forensic Dna Profiling, Courtney L Hall, Rupesh K Kesharwani, Katherine E Mcbroom Henson, Bupe Kapema, Nicole R Phillips, Fritz J Sedlazeck, Roxanne R Zascavage

Faculty, Staff and Students Publications

Forensic human identification relies on length-based differences in short tandem repeats (STRs) across autosomal and Y chromosomes, which require separate reactions and provide limited resolution. While next-generation sequencing offers greater discriminatory power, most platforms are expensive and restricted to traditional lab settings. Nanopore sequencing has the potential to change this with the real-time, portable MinION sequencer. However, forensic-specific tools that generate STR profiles compatible with established length-based databases are lacking. To address this, we developed STRspy2.0, which simultaneously profiles autosomal and Y-STRs using nanopore reads. STRspy2.0 produced accurate profiles for 54 multiplexed control libraries and 41 mock casework samples (blood, …

Intouch Week Of February 16, 2026, New York Medical College

InTouch

• HeLa Conference Explores Ethics, Equity, and Innovation in a Changing Health Care Landscape
• Kupersmith Lecture Explores Federal Tax Incentives for Living Kidney Donation: Ethical, Economic, and Halachic Considerations
• Medical Students Celebrate in Style at Annual NYMC Formal
• Faculty Spotlight: From Pupil to Professor: Randy Goldberg, M.D. '97, M.P.H. '13, FACP, FHM

Non-Canonical Role Of Dna Mismatch Repair On Sensory Processing In Mice, Sadia N Rahman, Demetrios Neophytou, Siboney Oviedo-Gray, Bao Q Vuong, Hysell V Oviedo

2020-Current year OA Pubs

DNA repair mechanisms are essential for cellular development and function. In post-mitotic neurons, deficiencies in DNA damage response proteins can lead to severe neurodegenerative and neurodevelopmental disorders. One highly conserved factor involved in DNA repair is MutS Homolog 2 (Msh2), which is responsible for correcting base-base mismatches and insertion/deletion loops during cell proliferation. However, its role in mature neurons remains poorly understood. This study investigates the impact of Msh2 loss on sensory processing in mice. Using electrophysiological and molecular assays, we identifiedsignificant deficits in cortical and thalamic sound processing in Msh2