Digital Commons Network^™

Explainable Multimodal Sentiment Analysis Of Social Media Visual Content For Child Safety, Yee Sen Tan, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

Ensuring the safety and well-being of children is increasingly important, especially in a world where visual content is pervasive. This paper proposes a novel multimodal, multilingual, and multiclass sentiment analysis method for social media content, aimed at improving content moderation for child safety. Our approach integrates textual, visual, and audio data from videos, categorizing sentiment into four levels: positive, slightly negative, negative, and strongly negative, enabling granular detection of harmful content. To enhance explainability and trust, we also leverage interpretable mechanisms to analyze the contributions of each modality. Evaluation of our method demonstrates strong generalization across diverse video types, and …

Eformer: An Effective Edge-Based Transformer For Vehicle Routing Problems, Dian Meng, Zhiguang Cao, Yaoxin Wu, Yaqing Hou, Hongwei Ge, Qiang Zhang

Research Collection School Of Computing and Information Systems

Recent neural heuristics for the Vehicle Routing Problem (VRP) primarily rely on node coordinates as input, which may be less effective in practical scenarios where real cost metrics--such as edge-based distances--are more relevant. To address this limitation, we introduce EFormer, an Edge-based Transformer model that uses edge as the sole input for VRPs. Our approach employs a precoder module with a mixed-score attention mechanism to convert edge information into temporary node embeddings. We also present a parallel encoding strategy characterized by a graph encoder and a node encoder, each responsible for processing graph and node embeddings in distinct feature spaces, …

Fine‑Tuning Multimodal Large Language Models For Product Bundling, Xiaohao Liu, Jie Wu, Zhulin Tao, Yunshan Ma, Yinwei Wei, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Recent advances in product bundling have leveraged multimodal information through sophisticated encoders, but remain constrained by limited semantic understanding and a narrow scope of knowledge. Therefore, some attempts employ In-context Learning (ICL) to explore the potential of large language models (LLMs) for their extensive knowledge and complex reasoning abilities. However, these efforts are inadequate in understanding mulitmodal data and exploiting LLMs' knowledge for product bundling. To bridge the gap, we introduce Bundle-MLLM, a novel framework that fine-tunes LLMs through a hybrid item tokenization approach within a well-designed optimization strategy. Specifically, we integrate textual, media, and relational data into a unified …

Affinitytune: A Prompt-Tuning Framework For Few-Shot Anomaly Detection On Graphs, Jingyan Chen, Guanghui Zhu, Guansong Pang, Chunfeng Yuan, Yihua Huang

Research Collection School Of Computing and Information Systems

Graph anomaly detection (GAD) is a critical task with applications in domains such as networking, finance, and bioinformatics. % However, the scarcity of labeled anomalies and the limitations of unsupervised methods hinder effective detection. % While semi-supervised and few-shot learning approaches offer improvements, they struggle with knowledge transfer and rely heavily on labeled data. % Recent advancements in prompt tuning on graphs provide a promising direction, but their application to heterophilous graphs in anomaly detection remains underexplored. % In this work, we propose AffinityTune, a novel framework for few-shot graph anomaly detection based on prompt tuning. % Our approach introduces …

Role Of Social Media Mindfulness In Combatting Fake News Propagation, Gaurav Bansal, Fiona Fui-Hoon Nah, Jason B. Thatcher

Research Collection School Of Computing and Information Systems

The dissemination of fake news by social media users is a key factor in the escalation of misinformation. Research suggests that social media networks are becoming increasingly homophilic, which leads to an overreliance on social media friends that contributes to the spread of fake news. However, little is known about how social media mindfulness can reduce the sharing of fake news. To investigate this research question, we conceptualized a social media mindfulness construct and developed the social media mindfulness scale. We also hypothesize that social media mindfulness lowers overreliance on friends’ knowledge, which increases skepticism about social media news that …

Aluminum Doped Tin Sulfide Thin Films For Solar Cell Applications, Gabriel Rodriguez Guijarro

Open Access Theses & Dissertations

Tin sulfide (SnS) is theorized to be a suitable material for solar cells, but there are some difficulties that have not been overcome when making thin films that have the properties needed to compete with other materials. This work investigates the structural and optoelectronic properties of aluminum-doped SnS thin films, deposited via magnetron cosputtering physical vapor deposition at different temperatures. To characterize the films a variety of techniques were used: Raman spectroscopy, SEM, TEM, X-Ray Reflectivity, and UV-Vis spectroscopy. The results show that the target stoichiometry is a relevant parameter to take into account when growing SnS thin films, the …

Let’S Teach More Accurate And Inclusive History! The Case Of Islamic Contributions To Mathematics And Science, Nuh Aydin

Journal of Humanistic Mathematics

Schools commonly teach a history of mathematics and science that is Eurocentric. This selective version of the history of science, called Classical Narrative by some, is rooted in colonial times and mindset, and has reinforced certain negative opinions about other cultures. It ignores or downplays contributions to mathematics and sciences from non-western civilizations, and falsely attributes many scientific discoveries to European scholars. Medieval Islamic Civilization, which had strong connections to Renaissance Europe, serves as a clear example of how this narrative is distorted. Based on research on primary sources since the middle of the 20th century, we now know that …

Math Anxiety And Shame Exemplified On The Reality Show Survivor, James Drimalla, Dru Horne

Journal of Humanistic Mathematics

In an episode of season 45 of the reality show Survivor, three contestants competed in a challenge involving mathematics. In their reflections and responses to the challenge, the contestants discussed feelings of anxiety, fear, and shame. In this article, we describe (a) the challenge, (b) the three contestants’ attempts to complete the challenge and their responses to the challenge, (c) responses to the challenge in the media, and (d) relevant details of our personal experiences and related backgrounds. We then discuss themes of math anxiety, shame, and virtues, and encourage leaders in mathematical spaces to place a higher value on …

Memes As An Effective Approach To Increase Public Engagement With Mathematical Concepts, Juan M. Romero, Carlos Trenado

Journal of Humanistic Mathematics

A meme is a graphical concept or cultural item that is disseminated via the Internet, often through social media platforms. Memes serve as a mechanism for replicating cultural traits by incorporating aspects of cultural mutation and evolution. The potential of memes in learning and education has been emphasized in several recent studies. The present article examines the impact of memes in increasing public engagement with mathematics and mathematical concepts. By focusing on memes that exhibit specific attributes—such as emotional facial expressions of recognizable human characters and dialogues emphasizing the usefulness or beauty of a mathematical concept—we observe a significant increase …

Re: Comment Letter For Clark Tailings Consolidated Waste Management Area (Ctcwma) Site Investigation Quality Assurance Project Plan Revision 01 (Dated June 6, 2025), Emma Rott

Silver Bow Creek/Butte Area Superfund Site

No abstract provided.

Green Innovation: Optimizing The Potential Of Plastic Waste As An Alternative To Fossil Fuels, Hani Alfiyani, Evi Gusmayanti, Nelly Wahyuni

Journal of Environmental Science and Sustainable Development

Plastic bag waste has the potential to be converted into alternative fuel oil through the pyrolysis method. This study applies the principle of thermal pyrolysis, conducted without oxygen, at the Edelweis Integrated Waste Management Site. The purpose is to analyze the characteristics of fuel oil derived from plastic bag waste based on parameters such as density, viscosity, calorific value, and acid number, as well as to estimate the potential fuel oil yield from plastic bag waste in Pontianak City. The results show that the density, viscosity, and calorific value of the produced fuel oil meet or closely approach standard requirements. …

Improved Efficiency Of Plant Regeneration From Smooth Bromegrass (Bromus Inermis) Suspension Culture, T H. Chen, J Marowitch

IGC Proceedings (1977-2023)

Smooth bromegrass, Bromus inermis Leyss, is the most important forage grass in Canada. Breeding for improvements such as higher yield and faster regrowth has made little progress, mainly due to the polyploidy and cross-pollination which are characteristic of this grass. The application of tissue culture methods to bromegrass improvement holds promise only if an efficient procedure for plant regeneration is found. Various basal culture media and auxins were tested for their effects on callus induction, growth of suspension cultures and plant regeneration. None of the tested auxins gave better in vitro growth than 2,4-D. Eriksson's medium with 2,4-D as the …

Analysis Of The Impact And Adaptation Of Tidal Floods From Coastal Landscape Area Communities In Poasia District, Kendari City, Indonesia, La Ode Hadini, La Aba, Noor Husna Khairisa, Nikita Jasmine Almira

Jurnal Pendidikan Geografi: Kajian, Teori, dan Praktek dalam Bidang Pendidikan dan Ilmu Geografi

Poasia District is located in the coastal area of the southern part of Kendari City, which is highly susceptible to tidal flooding. However, the extent of the community's exposure to these events and their subsequent adaptation measures remain to be fully delineated. This study examines the impacts of tidal flooding and the adaptation patterns of the Poasia Coastal Community to the tidal flood disaster. This research employed a descriptive qualitative method, which was carried out through document review, interviews involving 34 respondents, and field observations. The results of this study indicate that tidal flooding exerts a negative impact on the …

Learning From Conditional Data Distributions, Jizhou Huang

McKelvey School of Engineering Graduate Student Theses & Dissertations

Traditional machine learning paradigms often rely on a single global model trained on an entire dataset, aiming for broad generalization across all instances. However, in many real-world applications, the underlying data distribution is heterogeneous, and meaningful predictions often require models that focus on specific subpopulations rather than treating the data as a whole. This motivates the study of learning from conditional distributions, a framework where predictive models are designed to capture the structure and properties of restricted subsets of the data, leading to improved accuracy, fairness, and interpretability. This dissertation explores three key subproblems that exemplify different aspects of learning …

Multiclass Cyberbullying Detection Using Advanced Neural Network Architectures: A Comparative Study Amidst The Covid-19 Pandemic, Mahyar Alinejad

Data Science and Data Mining

Amidst the COVID-19 pandemic, the digital communication landscape has seen an unprecedented rise in cyberbullying incidents. Addressing this critical issue, our study develops and evaluates a novel multiclass cyberbullying detection framework employing several advanced neural network architectures—namely Neural Networks (NN), Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and Gated Recurrent Units (GRU). Utilizing a balanced dataset created through Dynamic Query Expansion, this research benchmarks the performance of these models in accurately classifying cyberbullying according to specific victim attributes such as age, ethnicity, gender, and religion. Our results demonstrate that LSTM and GRU models, in particular, exhibit superior performance …

Multiclass Cyberbullying Detection Using Advanced Neural Network Architectures: A Comparative Study Amidst The Covid-19 Pandemic, Mahyar Alinejad

Data Science and Data Mining

Amidst the COVID-19 pandemic, the digital communication landscape has seen an unprecedented rise in cyberbullying incidents. Addressing this critical issue, our study develops and evaluates a novel multiclass cyberbullying detection framework employing several advanced neural network architectures—namely Neural Networks (NN), Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and Gated Recurrent Units (GRU). Utilizing a balanced dataset created through Dynamic Query Expansion, this research benchmarks the performance of these models in accurately classifying cyberbullying according to specific victim attributes such as age, ethnicity, gender, and religion. Our results demonstrate that LSTM and GRU models, in particular, exhibit superior performance …

Comparative Study Of Machine Learning Models For Predicting The Market Value Of Professional Football Players, Álvaro Salvador López

Master's Theses or Doctor of Nursing Practice

The market value of professional football players is a critical factor in decision-making for clubs, agents, and analysts. Accurate player valuation impacts transfers, contract negotiations, and financial planning. In recent years, data-driven approaches have emerged to support traditional scouting with predictive analytics. This thesis presents a comparative study of machine learning models to estimate the market value of football players based on historical performance and personal attributes.

This thesis presents a comparative study of two independently developed machine learning systems designed to predict the market value of football players for the 2020–2021 season. Both systems were trained using real data …

Exploring Adversarial Threats To Neuralhash: A Perceptual Hashing Algorithm, Gurleen Kaur

Student Theses

Perceptual hashing algorithms are algorithms that generate content-based image hashes by extracting perceptual features from the images. Unlike cryptographic hashes, which exhibit significant changes with even slight input alterations, perceptual hashes do not change when modifications like compression, color correction and brightness are applied to the images. These hashes are designed to remain similar for inputs that are visually or perceptually alike, which has led to their widespread application in detecting duplicate images, finding similar images for reverse image search and to detecting inappropriate content of Child sexual abuse (CSAM) images by comparing image hashes with dataset of known perceptual …

Reviving The Lost Art: Historical Foundations And Future Pathways For Bespoke Service In Luxury Retail, Andrew Burnstine

Faculty and Staff Publications & Presentations

The mid-20th century witnessed a zenith of deeply personalized, bespoke service within iconic luxury specialty retailers. This paper critically analyzes the foundational principles of this historical bespoke service model, extending Service-Dominant (S-D) Logic and retail evolution theory, to propose a robust framework for its modern revival. Employing a rigorous qualitative, multiple-case study approach, grounded in extensive historical and media analysis of four archetypal American and British luxury boutiques, and uniquely informed by an insider-ethnographic perspective on the central case exemplar ("Martha's"), the study distills six core principles: Profound Client Knowledge, Visionary Curation & Styling, Anticipatory & Proactive Service, The Exclusive …

A Mutational Analysis Of Thatisin: How Single Point Mutations Impact The Biosynthetic Process Of A Group 16 Graspetide, John F. Boynton Jr

Chemistry and Chemical Biology ETDs

Abstract:

Graspetides are a family of Ribosomally synthesized and Post-translationally modified Peptide (RiPP) natural products named for their ATP Grasp Macrocyclases. We identified several Graspetide Biosynthetic Gene Clusters containing common double glycine cleavage motifs and attempted characterization of the mature Graspetides. One of the resulting peptides, Thatisin, has a topology with two interlocking macrolactones installed by a single ATP Grasp Ligase named ThtC. Here we use single and double point mutations to observe the impact or variation on the installation of these macrocycles. Alanine scan mutagenesis is used to assess leader peptide residues in the precursor peptide ThtA to determine …

Research Progress On Thermal Management Of Lithium-Ion Batteries, Hong-Da Li, Qiu-Wan Shen, Zhao-Yang Zhang, Xin-Yue Zhao, Yuan Wei, Shi-An Li

Journal of Electrochemistry

Nowadays, new energy technologies are developing rapidly, energy storage systems are widely used, and lithium-ion batteries occupy a dominant position among them. Therefore, it is also very important to ensure their performance, safety and service life through thermal management technology. In this paper, the causes of thermal runaway of lithium batteries are reviewed firstly, and three commonly used thermal management technologies, namely, air cooling, liquid cooling and phase change material cooling, are compared according to relevant literature in recent years. Air cooling technology has been widely studied because of its simple structure and low cost, but its temperature control effect …

“Silent Is Not Actually Silent”: An Investigation Of Toxicity On Bug Report Discussion, Mia Mohammad Imran, Jaydeb Sarker

Computer Science Faculty Research & Creative Works

Toxicity in bug report discussions poses significant challenges to the collaborative dynamics of open-source software development. Bug reports are crucial for identifying and resolving defects, yet their inherently problem-focused nature and emotionally charged context make them susceptible to toxic interactions. This study explores toxicity in GitHub bug reports through a qualitative analysis of 203 bug threads, including 81 toxic ones. Our findings reveal that toxicity frequently arises from misaligned perceptions of bug severity and priority, unresolved frustrations with tools, and lapses in professional communication. These toxic interactions not only derail productive discussions but also reduce the likelihood of actionable outcomes, …

Llput: Investigating Large Language Models For Bug Report-Based Input Generation, Alif Al Hasan, Subarna Saha, Mia Mohammad Imran, Tarannum Shaila Zaman

Computer Science Faculty Research & Creative Works

Failure-inducing inputs play a crucial role in diagnosing and analyzing software bugs. Bug reports typically contain these inputs, which developers extract to facilitate debugging. Since bug reports are written in natural language, prior research has leveraged various Natural Language Processing (NLP) techniques for automated input extraction. With the advent of Large Language Models (LLMs), an important research question arises: how effectively can generative LLMs extract failure-inducing inputs from bug reports? In this paper, we propose LLPut, a technique to empirically evaluate the performance of three open-source generative LLMs-LLaMA, Qwen, and Qwen-Coder-in extracting relevant inputs from bug reports. We conduct an …

Ionic Liquid Enhanced Proton Transfer For Neutral Oxygen Evolution Reaction, Ming-Xing Chen, Nian Liu, Zi-He Dua, Jing Qi, Rui Cao

Journal of Electrochemistry

The development of highly active catalyst in pH-neutral media for oxygen evolution reaction (OER) is critical in the field of renewable energy storage and conversion. Nevertheless, the slow kinetics of proton-coupled electron transfer (PCET) hinders the overall OER efficiency. Herein, we report an ionic liquid (IL) modified CoSn(OH)₆ nanocubes (denoted as CoSn(OH)₆-IL), which could be prepared through a facile strategy. The modified IL would not change the structural characteristics of CoSn(OH)₆, but could effectively regulate the local proton activity near the active sites. The CoSn(OH)₆-IL exhibited higher intrinsic OER performances than the pristine …

Newtonian Fractional-Dimension Gravity And The Mass-Dimension Field Equation, Gabriele U. Varieschi

Physics Faculty Works

We resume our analysis of Newtonian Fractional-Dimension Gravity (NFDG), an alternative gravitational model which does not require the Dark Matter (DM) paradigm. We add three more galaxies (NGC 6946, NGC 3198, NGC 2841) to the catalog of those studied with NFDG methods. Once again, NFDG can successfully reproduce the observed rotation curves by using a variable fractional dimension D (R), as was done for nine other galaxies previously studied with these methods. In addition, we introduce a mass-dimension field equation for our model, which is capable of deriving the fractional mass-dimension Dm (R) from first principles, as opposed to the …

Transformation With Genes To Improve Lipid Production And Barcoding To Identify Unknown Algal Species, Michelle T. Rada

Theses and Dissertations

With the rising demand for alternative fuels, algal-based biofuels are a promising, sustainable source that meets commercial interest while producing lower greenhouse gas emissions compared to fossil fuels. This thesis explored two studies, evaluating microalgae for their future potential in lipid yield for biofuel production.

The first study involved developing a cost-efficient electroporation protocol that allowed for the genetic transformation of Chlamydomonas reinhardtii using the pChlamy_4 vector, which supports future cloning of genes to enhance lipid production. Parameters affecting DNA uptake and integration into algal genomes were studied: the effect of cell density, the settings of the electroporation device, and …

Multilingual Cyber Threat Intelligence Feeds Preprocessing For Threat Intelligence Event Extraction: A Systematic Literature Review, Jamal H. Al-Yasiri, Mohamad Fadli Bin Zolkipli, Nik Fatinah N. Mohd Farid

Karbala International Journal of Modern Science

In cyber threat intelligence (CTI), information security specialists face overwhelming data flows from multiple sources, including hacker forums, dark web markets, and social media. These diverse and multilingual information streams require extensive analysis and processing. However, the current state of CTI faces several challenges, such as reliance on manual annotation and evaluation, as well as limited support for non-English languages, which hinders advanced threat detection and comprehensive analysis. This systematic literature review proposes a conceptual framework designed to overcome existing state-of-the-art limitations. It evaluates recent advancements in CTI methodologies by following PRISMA guidelines and analyzing selected studies from reputable sources, …

Key Technologies And Approaches For Water Resource Conservation And Utilization In Arid To Semi-Arid Open-Pit Coal Mining Areas In The Northern Sand Prevention Belt Of China, Fang Jie, Xu Zhimin, Cheng Wei, Lu Zihan, Zhao Yongqiang, Zhu Yuhao, Chen Tianci

Coal Geology & Exploration

Background The northern sand prevention belt (NSPB) of China is primarily distributed in arid and semi-arid regions such as Xinjiang, Inner Mongolia, Ningxia, and Gansu. This belt exhibits scarce rainfall and intense evaporation, which lead to a shortage of water resources and vulnerable ecosystems. In recent years, the large-scale development of open-pit coal mines has caused increasingly violent mining disturbance in this belt, as well as increasingly prominent issues such as a decline in regional groundwater levels and ecological contradictions. To address technical challenges in balancing coal exploitation and water resource conservation in this belt, there is an urgent need …

(Arise) Achievements In Research, Inquiry And Scholarship Exhibition 2025, Office Of Undergraduate Research

(ARISE) Achievements in Research, Inquiry and Scholarship Exhibition

Conference held at John A. Delaney Student Union on July 25, 2025

Impacts Of Boundary Conditions And Parameter Heterogeneity On The Simulation And Prediction Of Water Inflow In Coal Mines, Ji Qiang, Wu Zhenjiang, Yao Yingying

Coal Geology & Exploration

Background Accurate prediction of water inflow in coal mines is essential for ensuring safe mining operations. Three-dimensional (3D) groundwater numerical models can be used to characterize hydrogeological conditions in mining areas and simulate the dynamic processes of water inflow, providing a theoretical basis for scientifically predicting mining-induced water inflow. However, there is a lack of a clear understanding of the impacts of the boundary conditions with surface water-groundwater interactions and the heterogeneity of aquifer permeability coefficients (K) on the simulation and prediction of water inflow during coal mining. Methods This study developed a 3D transient groundwater numerical model …