Digital Commons Network^™

A Comparative Study For Classical Machine Learning Models For Swahili Social Media Sentiment Analysis, Mahadia Tunga, Davis David

Tanzania Journal of Science

Despite sentiment analysis being one of the most popular applications in Natural Language Processing (NLP), most studies are skewed towards languages with a rich corpus (language database). Less emphasis has been placed on low-resource languages like Swahili. Swahili is the official language of the African Union and of 4 countries in East Africa, and is spoken by many people on the African continent. This study performed sentiment analysis using 3,000 tweets hosted on the Zindi Africa platform. Data was processed using a term frequency-inverse document frequency vectorization method, and five classical machine learning algorithms (RandomForest, XgBoost, and CatBoost, HistogramGradientBoost, LightGradientBoos) …

Towards Mitigation Of Hallucination For Llm-Empowered Agents: Progressive Generalization Bound Exploration And Watchdog Monitor, Siyuan Liu, Wenjing Liu, Zhiwei Xu, Xin Wang, Bo Chen, Tao Li

Michigan Tech Publications

Empowered by large language models (LLMs), intelligent agents have become a popular paradigm for interacting with open environments to facilitate AI deployment. However, hallucinations generated by LLMs - where outputs are inconsistent with facts - pose a significant challenge, undermining the credibility of intelligent agents. Only if hallucinations can be mitigated, the intelligent agents can be used in real-world without any catastrophic risk. Therefore, effective detection and mitigation of hallucinations are crucial to ensure the dependability of agents. Unfortunately, the related approaches either depend on white-box access to LLMs or fail to accurately identify hallucinations. To address the challenge posed …

Large Language Models As Information Providers For Appropriate Antimicrobial Use: Computational Text Analysis And Expert-Rated Comparison Of Chatgpt, Claude And Gemini, Marcello Di Pumpo, Maria Rosaria Gualano, Danilo Buonsenso, Francesca Raffaelli, Daniele Donà, Vittorio Maio, Patrizia Laurenti, Walter Ricciardi, Leonardo Villani

College of Population Health Faculty Papers

OBJECTIVES: Antimicrobial resistance is a critical public health threat. Large language models (LLMs) show great capability for providing health information. This study evaluates the effectiveness of LLMs in providing information on antibiotic use and infection management.

METHODS: Using a mixed-method approach, responses to healthcare expert-designed scenarios from ChatGPT 3.5, ChatGPT 4.0, Claude 2.0 and Gemini 1.0, in both Italian and English, were analysed. Computational text analysis assessed readability, lexical diversity and sentiment, while content quality was assessed by three experts via DISCERN tool.

RESULTS: 16 scenarios were developed. A total of 101 outputs and 5454 Likert-scale (1-5) scores were obtained …

Graphrag-Enabled Local Large Language Model For Gestational Diabetes Mellitus: Development Of A Proof-Of-Concept, Edmund Evangelista, Fathima Ruba, Salman Bukhari, Amril Nazir, Ravishankar Sharma

All Works

Background: Gestational diabetes mellitus (GDM) is a prevalent chronic condition that affects maternal and fetal health outcomes worldwide, increasingly in underserved populations. While generative artificial intelligence (AI) and large language models (LLMs) have shown promise in health care, their application in GDM management remains underexplored. Objective: This study aimed to investigate whether retrieval-augmented generation techniques, when combined with knowledge graphs (KGs), could improve the contextual relevance and accuracy of AI-driven clinical decision support. For this, we developed and validated a graph-based retrieval-augmented generation (GraphRAG)–enabled local LLM as a clinical support tool for GDM management, assessing its performance against open-source LLM …

Cv: Teresa Bixby (Chemistry), Teresa Bixby

Chemistry Department Faculty Curricula Vitae

No abstract provided.

Zero Trust - The Future Of Cybersecurity, Danial Haider, Shougfta Mushtaq, Hasnat Ali, Mazliham Mohd Su’Ud

Journal of Informatics and Web Engineering

The recent Zero-Trust Architecture (ZTA) is progressively adopted to the develop network security by assuming no implicit trust within or outside an organization’s boundary. Though, ZTA faces substantial challenges in detecting sophisticated and developing cyber threats, particularly due to its trust on traditional security mechanisms that struggle to manage internal threats and sophisticated attack techniques. To report these shortcomings, the proposed study discovers the combination of advanced machine learning (ML) and deep learning (DL) performances to improve the anomaly detection proficiencies within ZTA environments. The study develops the CICIDS2017 dataset, which contains diverse and realistic network traffic patterns, to assess …

The Role Of Generative Ai In E-Commerce Recommender Systems: Methods, Trends And Insights, Kai-Ze Liau, Heru Agus Santoso

Journal of Informatics and Web Engineering

Recommender systems have existed for decades, shaping how people consume digital content, receive information, and engage in day-to-day activities, among others. Undoubtably, recommender systems also play a crucial role in e-commerce applications as well, with industry players like Amazon, AliBaba, eBay using recommender systems within their ecosystems to give suitable and value-driven insights. However, recommender systems face some main concerns such as data sparsity, cold-start problems and so on. As a result, research is currently ongoing to solve these issues and provide high-quality recommendations to consumers. This review aims to identify prevailing gaps surrounding these issues by analysing existing research …

Research Article Recommender Systems: A Comprehensive Review Of Models, Approaches And Evaluation Metrics, Sir-Yuean Lim, Noramiza Hashim, Lanh Le Thanh

Journal of Informatics and Web Engineering

With the advent of the current digital era, individuals across the developed world are commonly equipped with devices that can access vast amounts of information at their fingertips. What was considered an impossible feat was realized through remarkable technological advancements. This positive transformation has had a profound impact on education, where traditional knowledge management, such as libraries, are no longer a primary determinant of a student’s academic success. Instead, it has been replaced by the internet as a medium for learning, practicing, and topic exploration. However, the sheer volume of the ever-increasing information available online can easily overwhelm a user, …

Lightweight String Similarity Approaches For Duplicate Detection In Academic Titles, Fahrudin Mukti Wibowo, Muhammad Zidny Nafan, Muhamad Azrino Gustalika, Harinda Fernando, Muhammad Hussain, Nur Afiqah Sahadun

Journal of Informatics and Web Engineering

This study addresses the critical challenge of detecting duplicate final year project (FYP) titles in academic institutions, where minor variations like reordering, synonyms, and paraphrasing often obscure plagiarism. We systematically evaluate four string similarity algorithms - Jaro-Winkler, Levenshtein Edit Distance, TF-IDF with Cosine Similarity, and Jaccard Similarity - using a synthetic dataset of 250 title pairs representing common duplication patterns. Our experiments reveal that character-based methods (Jaro-Winkler and Edit Distance) achieve perfect detection (F1-score=1.0) for literal matches, including typographical variations and phrase reordering. At the same time, TF-IDF demonstrates strong semantic capability (F1-score=0.95), albeit with some false positives. Jaccard Similarity …

Needs Analysis Of Interactive Learning Media For Teachingheat Transfer In Physics: Students’ And Teachers’Perspectives, Rizki Eka Shintya, Ika Mustika Sari, Ida Kaniawati

Jurnal Pendidikan Sains

Heat transfer material in physics is known to be abstract. This study specifically analyzes the conceptual difficulties, and visualization needs specific to this material, which is different from the analysis of physics needs in general. This analysis does not only look for the need for traditional media but explicitly looks for the need for interactive media (simulation, animation, virtual laboratory). Therefore, this study aims to identify the need for interactive learning media in physics education, specifically in the teaching of heat transfer, from the perspective of students and teachers in West Java, Indonesia. Using a quantitative descriptive survey, data were …

Development Of Digital Comic Learning Media Based On Mobile Learning On Media: Making Media Materials In Plant Tissue Culture, Sufina Intan Pertiwi, Fauziyah Harahap, Aline Gusti Yolanda Harahap, Marsya Amira Indrawati, Aline Jelita Christiani Simanullang, Yanda Febry Gracea Br Tarigan, Maureen Efriyanti Sitinjak

Jurnal Pendidikan Sains

his research was conducted based on student needs analysis, analysis of learner characteristics, and curriculum analysis, namely the lack of visualization and presentation of concepts and the lack of utilization of interactive technology in the learning process on media material and media making in tissue culture for college students. This study intends to develop digital comic media based on mobile learning and making media materials in tissue culture. This research method used research and development (R&D) with the ADDIE model: analyze, design, develop, implement, and evaluate. The subjects of this study were students of the Department of Biology, Universitas Negeri …

The Challenge Of Achieving Attributability In Multilingual Table-To-Text Generation With Question-Answer Blueprints, Aden Haussmann

International Journal of Undergraduate Research and Creative Activities

Generating faithful text descriptions from data tables is a significant challenge in Natural Language Processing (NLP), especially for the world’s many low-resource languages. This paper investigates whether Question-Answer (QA) blueprints—an intermediate planning step where a model first asks and answers questions about the data—can improve the factual accuracy of multilingual table-to-text generation. This novel approach is tested on the TaTA dataset, which includes several African languages, by finetuning models with and without these blueprints.

The results show a key distinction: while the QA blueprint method improves performance for English-only models, these gains disappear in the multilingual setting. This paper’s analysis …

Analyzing Adversarial Strategies And Countermeasures For Cyberbullying Detection, Maddie Juarez, Eldor Abdukhamidov, Manuel Sandoval, Deborah Hall, Mujtaba Nazari, George Thiruvathukal, Tamer Abuhmed, Yasin Silva, Mohammed Abuhamad

Computer Science: Faculty Publications and Other Works

Cyberbullying on social networking sites has become more prevalent. Most cyberbullying detection models often lack consideration of adversarial threads, leaving them vulnerable. This study evaluates the resilience of text-based cyberbullying detection models, constrained by limited available datasets, against word-level substitutions and character-level perturbations. We consider well-established ML techniques with real-world data and more recent LLM-based approaches to uncover model weaknesses. The results reveal that adversarial attacks can significantly reduce detection accuracy, e.g., most models are vulnerable to word- and character-level attacks with success rates up to 88% and 44%, respectively. We also find that LLM-based models such as CyberBERT are …

Follow Me Into Math: Near-Peer Influencers Take The Stage, Aaron T. Wilson, Sergey Grigorian, Mayra Ortiz Galarza, Xiaohui Wang

School of Mathematical & Statistical Sciences Faculty Publications

Young people like to be entertained, and to entertain others. What if students were to invest enough of their time and effort into learning topics from our mathematics courses to become experts in the eyes of their peers? In this study we positioned college students and high school students as mathematical performers on the stage in front of their nearpeers, for whom they became math influencers, developing and presenting MathShows. The paper shows readers how we positioned students on the stage, using a 7-step MathShow Design Process informed by a Neer-peer Mathematical Mentoring framework. Of import for educators, researchers and …

Investigating Factors Influencing Organic Chemistry Learners' Explanation Sophistication And Representational Competence, Caroline J. Crowder

USF Tampa Graduate Theses and Dissertations

The research presented in this dissertation has two themes: organic chemistry learners’ written explanations and representational competence. Chapters 3 and 4 explore how organic chemistry learners construct explanations of reaction mechanisms, specifically focusing on electrophile and nucleophile components. Chapter 5 investigates organic chemistry learners’ representational competence skills and the relationship between these skills and their performance in the course.

Understanding reaction mechanisms is critical for success in organic chemistry, yet learners often struggle to reason beyond explicit, surface-level features. Constructed-response prompts that ask learners to explain what is happening in a reaction mechanism and why it occurs can provide insight …

Creativity In Large Language Models, Robert Kenneth Morain

Theses and Dissertations

As artificial intelligence systems approach human-level performance across a wide variety of domains, creative domains remain a critical yet underexplored area of research. Unlike traditional AI tasks with well-defined objectives, creative tasks rely on inherently subjective measures, making them particularly challenging for machines that lack human experiential context. This dissertation establishes the fundamental importance of creativity in AI systems and presents methods for improving and evaluating the creative capabilities of LLMs on the pathway toward AGI. This work addresses and examines key limitations in current LLM creativity through model innovations, development frameworks, and comparative studies. The dissertation develops novel architectural …

Research On Identification And Evaluation Method Of Medical Experts' Expertise Domains In Online Health Community Based On Knowledge Graph, Yunjiang Xi, Qian Zhang, Man Li, Juan Yu

Journal of Scientific Information Research

[Purpose/significance] This study aims to identify the expertise domains of medical experts, and evaluates their domain levels to provide a basis for community expert recommendation.

[Method/process] This study utilized the improved OneRel model to structure community historical Q&A into entity relation triples. Then used the knowledge graph triples to test the consistency between the medical knowledge in the community Q&A and the domain knowledge, and finally obtained the doctor's domain levels by aggregating in each expertise domain.

[Result/conclusion] Using the data example from xywy.com website, 214 doctors in the community were ranked in terms of their average level of expertise …

Smarter Disease Detection From Electronic Health Record Data: An End-To-End Ai-Augmented Pipeline For Computable Phenotyping, Dylan Owens

Statistical Science Theses and Dissertations

Electronic Health Records (EHR) contain a wealth of structured and unstructured patient data that can be leveraged for computable phenotyping, the process of algorithmically identifying patient cohorts with specific diseases or conditions. Traditional rule-based phenotyping approaches, while interpretable, often struggle with scalability, portability across institutions, and effective use of unstructured clinical narratives. Recent advances in large language models (LLMs) present new opportunities for synthesizing complex free-text information into concise, clinically meaningful representations. However, integrating LLMs into phenotyping workflows requires careful design to maintain transparency, interpretability, and measurable uncertainty—features essential for clinical adoption and downstream applications such as decision support.

We …

Parameter-Efficient Variational Autoencoder For Multimodal Multi-Interest Recommendation, Nhu Thuat Tran, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Learning user preferences in recommendation systems is enriched by multimodal features, such as textual and visual content, and amplified by multi-interest modeling with Variational AutoEncoders (VAEs). However, prior efforts are limited by single modality focus and cumbersome, parameter-heavy architecture designs. To address these limitations, we introduce an innovative solution that blends the semantic richness of multimodal data with the representational power of multi-representation VAEs. Drawing inspiration from Mixture of Experts (MoE), we cast each VAE as an expert tailored to a specific modality, then fuse them via a novel parameter-merging function into a lean, unified model. This approach efficiently captures …

Memad: Structured Memory Of Debates For Enhanced Multi-Agent Reasoning, Shuai Ling, Lizi Liao, Dongmei Jiang, Weili Guan

Research Collection School Of Computing and Information Systems

Large Language Models (LLMs) demonstrate remarkable in-context learning capabilities but often struggle with complex, multi-step reasoning. Multi-Agent Debate (MAD) frameworks partially address these limitations by enabling iterative agent interactions. However, they neglect valuable historical insights by treating each new debate independently. In this paper, we propose Memory-Augmented MAD (MeMAD), a parameter-free memory-augmented MAD framework that systematically organizes and reuses past debate transcripts. MeMAD stores structured representations of successful and unsuccessful reasoning attempts enriched with self-reflections and peer feedback. It systematically retrieves them via semantic similarity at inference time to inform new reasoning tasks. Our experiments on challenging mathematical reasoning, scientific …

The Complexity Of Long-Distance Dependencies And Their Impact On Language Models, Abhijit Shrikant Mahalunkar

Doctoral

Sequential data modeling is an important challenge in various fields and in particular in natural language processing. Building effective sequential models faces a notable challenge in the form of Long-Distance Dependencies (LDDs) within the sequence data. Hence, successfully overcoming this challenge is imperative for developing robust and accurate sequential models across various domains and applications. To tackle this challenge, the first step is to conduct a detailed analysis of the complexity of LDDs observed in various sequence datasets. This thesis offers a thorough exploration and documentation of this analysis. An important finding from this thesis is the consistent patterns of …

Analysis Of The Status And Thematic Trends Of Ai For Science Research Abroad From 2015 To 2024, Fangyuan Wang, Huiting Xu, Jinghua Xue

Journal of Scientific Information Research

[Purpose/significance] This paper analyzes the relevant literature in the field of AI for Science（AI4S）in the WoS core database from 2015 to 2024, and sorts out the research status and development trends in this field, aiming to provide forward-looking insights for the application of AI technology in scientific research.

[Method/process] This paper combines bibliometric analysis with the BERTopic model to analyze the publication trends, publishing countries, core authors, and topic identification and development trends in the field of AI4S.

[Result/conclusion] Through bibliometric analysis, this paper reveals the exponential growth trend of AI4S-related literature, and finds that China ranks first in the …

(Si15-017) Modeling Construction Project Uncertainty Using Fuzzy Inference And Nature-Inspired Metaheuristic Knowledge-Based Algorithms, M. Kapoor, B. K. Pathak, R. Kumar

Applications and Applied Mathematics: An International Journal (AAM)

Construction projects are influenced by various uncertain factors, including supervisory knowledge, labor expertise, and weather conditions. These uncertain factors have linguistic properties that are challenging to quantify with the help of traditional set theory. To address this, the study applies fuzzy inference systems, specifically the Mamdani fuzzy inference system, to model and evaluate the impact of these uncertainties on construction projects. This fuzzy inference system provides a more nuanced understanding of these factors compared to traditional set theory methods. Experimental results indicate that uncertainties significantly impact construction projects. These findings establish a valuable framework for developing adaptive strategies, enhancing project …

Look Before You Decide: Prompting Active Deduction Of Mllms For Assumptive Reasoning, Yian Li, Wentao Tian, Yang Jiao, Jingjing Chen, Tianwen Qian, Bin Zhu, Na Zhao, Yu‑Gang Jiang

Research Collection School Of Computing and Information Systems

Recently, Multimodal Large Language Models (MLLMs) have achieved significant success across multiple disciplines due to their exceptional instruction-following capabilities and extensive world knowledge. However, whether these MLLMs possess human-like compositional reasoning abilities remains an open problem. To unveil their reasoning behaviors, we first curate a Multimodal Assumptive Reasoning Benchmark (MARS-Bench) in this paper. Interestingly, we find that most prevalent MLLMs can be easily fooled by the introduction of a presupposition into the question, whereas such presuppositions appear naive to human reasoning. Besides, we also propose a simple yet effective method, Active Deduction (AD), a novel reinforcement learning paradigm to encourage …

Viewsrd: 3d Visual Grounding Via Structured Multi-View Decomposition, Ronggang Huang, Haoxin Yang, Yan Cai, Xuemiao Xu, Huaidong Zhang, Shengfeng He

Research Collection School Of Computing and Information Systems

3Dvisual grounding aims to identify and localize objects in a 3Dspacebasedontextualdescriptions. However, existing methods struggle with disentangling targets from anchors in complex multi-anchor queries and resolving inconsisten cies in spatial descriptions caused by perspective variations. To tackle these challenges, we propose ViewSRD, a frame work that formulates 3D visual grounding as a structured multi-view decomposition process. First, the Simple Rela tion Decoupling (SRD) module restructures complex multi anchor queries into a set of targeted single-anchor state ments, generating a structured set of perspective-aware de scriptions that clarify positional relationships. These de composed representations serve as the foundation for the Multi-view …

Visual-Enhanced Multimodal Framework For Flexible Job Shop Scheduling Problem, Peng Zhao, Zhiguang Cao, Di Wang, Wen Song, Wei Pang, You Zhou, Yuan Jiang

Research Collection School Of Computing and Information Systems

Multimodal models leverage complementary information across modalities to enrich feature representations. While visual information shows potential in representing structure for some combinatorial optimization problems (COPs), its application to complex scheduling like the Flexible Job Shop Scheduling Problem (FJSP) remains underexplored. Current learning-based FJSP solvers predominantly rely on handcrafted state features. This dependence can lead to inconsistencies and may not fully capture the problem's intricate dynamics. Crucially, these methods overlook visual modalities. Visual representations offer a distinct advantage by inherently capturing the global topological structure and complex resource interactions within the FJSP state. Unlike localized handcrafted features, this holistic, structural view …

Art4math: Handwritten Mathematical Expression Recognition Via Multimodal Sketch Grounding, Yang Zhou, Jin Wang, Yuxiao Zhang, Kaixiang Huang, Guodong Lu, Jingru Yang, Shengfeng He

Research Collection School Of Computing and Information Systems

Handwritten Mathematical Expression Recognition (HMER) remains a challenging task due to the structural complexity of mathematical notation and the ambiguity of handwritten symbols-e.g., ''ρ'' vs. ''p'' or ''B'' vs. ''β''. While stroke-based models offer disambiguation via temporal cues, most existing methods are constrained by coarse modality fusion and a lack of fine-grained cross-modal alignment, further hindered by limited annotated data. We introduce Art for Math (Art4Math), a novel framework that leverages the structural richness of human sketches to enhance HMER through fine-grained, modality-aware learning. Art4Math follows a two-stage training paradigm: Art Grounding (A-Grd) and Math Decoding (M-Dec). In A-Grd, the …

Language-Driven 3d Human Pose Estimation In Multi-Person Scenarios: A New Dataset And Approach, Tingrui Shen, Bangzhen Liu, Zhirun Fan, Shiting Zhang, Weifeng Pan, Sun Fan, Dan Cao, Shengfeng He

Research Collection School Of Computing and Information Systems

In an NBA game scenario, consider the challenge of locating and analyzing the 3D poses of players performing a user-specified action, such as attempting a shot. Traditional 3D human pose estimation (3DHPE) methods often fall short in such complex, multi-person scenes due to their lack of semantic integration and reliance on isolated pose data. To address these limitations, we introduce Language-Driven 3D Human Pose Estimation (L3DHPE), a novel approach that extends 3DHPE to general multi-person contexts by incorporating detailed language descriptions. We present Panoptic-L3D, the first dataset designed for L3DHPE, featuring 3,838 linguistic annotations for 1,476 individuals across 588 videos, …

Unsupervised Visual Chain-Of-Thought Reasoning Via Preference Optimization, Kesen Zhao, Beier Zhu, Qianru Sun, Hanwang Zhang

Research Collection School Of Computing and Information Systems

Chain-of-thought (CoT) reasoning greatly improves the interpretability and problem-solving abilities of multimodal large language models (MLLMs). However, existing ap proaches focus on text CoT, limiting their ability to lever age visual cues. Visual CoT remains underexplored, and the only work [35] is based on supervised fine-tuning that relies on extensive labeled bounding-box data and is hard to generalize to unseen cases. In this paper, we introduce Unsupervised Visual CoT (UV-CoT), a novel framework for image-level CoT reasoning via preference optimization. UV-CoTperforms preference comparisons between model generated bounding boxes (one is preferred and the other is dis-preferred), eliminating the need for …

Chemistry And Biochemistry Affiliated Publications: Snapshot Of The Research Publications 2019-2024., Jeremy J. Smith, Lutishoor Salisbury

University Libraries Faculty Publications and Presentations

This report highlights the chemistry and biochemistry faculty publications for the period 2019-2024. It includes tables identifying the types of publications, the characteristics of the authors, inter-departmental and external cooperation, summary of the citations of the publications, and the JCR ranking of the journals in which they published.