Digital Commons Network^™

Gamesmanship In Modern Discovery Tech, Neel Guha, Peter Henderson, Diego A. Zambrano

Faculty Scholarship

This chapter explores the potential for gamesmanship in technology-assisted discovery. Attorneys have long embraced gamesmanship strategies in analog discovery, producing reams of irrelevant documents, delaying depositions, or interpreting requests in a hyper-technical manner. The new question, however, is whether machine learning technologies can transform gaming strategies. By now it is well known that technologies have reinvented the practice of civil litigation and, specifically, the extensive search for relevant documents in complex cases. Many sophisticated litigants use machine learning algorithms – under the umbrella of “Technology Assisted Review” (TAR) – to simplify the identification and production of relevant documents in discovery. …

The Application Of Graph Technology For Improving Entity Resolution Results In The Context Of Group Membership, Md Abdus Salam Siddique

Theses and Dissertations

The main objective of Entity resolution (ER) is to find duplicate records within the same data table from the same source or different data tables from various sources. A traditional pair-wise supervised entity resolution matching depends on pre-built rules for finding matched records. On the other hand, unsupervised or semisupervised also relies on pair-wise matching. In the maximum case, group membership is left behind for consideration. In this dissertation, I have discussed the design, implementation and evaluation of a graph-based entity resolution for group membership to enhance the pair-wise matching ER system. I have designed and implemented a pipeline for …

Artificial Intelligence, Basic Skills, And Quantitative Literacy, Gizem Karaali

Numeracy

The introduction in November 2022 of ChatGPT, a freely available language-based artificial intelligence, has led to concerns among some educators about the feasibility and benefits of teaching basic writing and critical thinking skills to students in the context of easily accessed, AI-based cheating mechanisms. As of now, ChatGPT can write pretty convincing student-level prose, but it is still not very good at answering quantitatively rich questions. Therefore, for the time being, the preceding concerns may not be shared by a large portion of the numeracy education community. However, as Google and WolframAlpha are definitely capable of answering standard and some …

Semantic Orientation Of Crosslingual Sentiments: Employment Of Lexicon And Dictionaries, Arslan Ali Raza, Asad Habib, Jawad Ashraf, Babar Shah, Fernando Moreira

All Works

Sentiment Analysis is a modern discipline at the crossroads of data mining and natural language processing. It is concerned with the computational treatment of public moods shared in the form of text over social networking websites. Social media users express their feelings in conversations through cross-lingual terms, intensifiers, enhancers, reducers, symbols, and Net Lingo. However, the generic Sentiment Analysis (SA) research lacks comprehensive coverage about such abstruseness. In particular, they are inapt in the semantic orientation of Crosslingual based code switching, capitalization and accentuation of opinionative text due to the lack of annotated corpora, computational resources, linguistic processing and inefficient …

Safe Space: To Help Minimize Cyberbullying And Support Social Well-Being, Eiman Rana

CISLA Senior Integrative Projects

The perverseness of cyberbullying as a growing and serious form of abuse with the potential for harm among children and youth needs to be recognized. In a resource-limited setting such as South Asia where youth have very little access to counseling within schools, the implications for mental health should be recognized. This research study explores whether our youth is capable of using technology in the right way to minimize cyberbullying and support social well-being.

Index Terms - Cyberbullying, Social Well-being, User Experience Design, and Usability Study.

Self-Omics: A Self-Supervised Learning Framework For Multi-Omics Cancer Data, Sayed Hashim, Karthik Nandakumar, Mohammad Yaqub

Computer Vision Faculty Publications

We have gained access to vast amounts of multi-omics data thanks to Next Generation Sequencing. However, it is challenging to analyse this data due to its high dimensionality and much of it not being annotated. Lack of annotated data is a significant problem in machine learning, and Self-Supervised Learning (SSL) methods are typically used to deal with limited labelled data. However, there is a lack of studies that use SSL methods to exploit inter-omics relationships on unlabelled multi-omics data. In this work, we develop a novel and efficient pre-training paradigm that consists of various SSL components, including but not limited …

Encryption And Compression Classification Of Internet Of Things Traffic, Mariam Najdat M Saleh

Browse all Theses and Dissertations

The Internet of Things (IoT) is used in many fields that generate sensitive data, such as healthcare and surveillance. Increased reliance on IoT raised serious information security concerns. This dissertation presents three systems for analyzing and classifying IoT traffic using Deep Learning (DL) models, and a large dataset is built for systems training and evaluation. The first system studies the effect of combining raw data and engineered features to optimize the classification of encrypted and compressed IoT traffic using Engineered Features Classification (EFC), Raw Data Classification (RDC), and combined Raw Data and Engineered Features Classification (RDEFC) approaches. Our results demonstrate …

Maple: Multi-Modal Prompt Learning, Muhammad Uzair Khattak, Hanoona Rasheed, Muhammad Maaz, Salman Khan, Fahad Shahbaz Khan

Computer Vision Faculty Publications

Pre-trained vision-language (V-L) models such as CLIP have shown excellent generalization ability to downstream tasks. However, they are sensitive to the choice of input text prompts and require careful selection of prompt templates to perform well. Inspired by the Natural Language Processing (NLP) literature, recent CLIP adaptation approaches learn prompts as the textual inputs to fine-tune CLIP for downstream tasks. We note that using prompting to adapt representations in a single branch of CLIP (language or vision) is sub-optimal since it does not allow the flexibility to dynamically adjust both representation spaces on a downstream task. In this work, we …

Genealogical Relationship Extraction From Unstructured Text Using Fine-Tuned Transformer Models, Lubomir Stanchev, Carloangello Parrolivelli

Computer Science and Software Engineering

The paper tackles the task of extracting genealogical relationships, such as “sibling-of”, “parent-of”, “child-of”, and “spouse-of”, from unstructured, free-form text. In order to solve the problem, we propose a three-stage pipeline consisting of Named Entity Recognition (NER), Coreference Resolution (CR), and Relationship Classification (RC). NER identifies tokens in the text that refer to people, such as proper nouns or nicknames, using the SpaCy software. CR maps multiple tokens representing pronouns to their antecedents. For example, CR could map “She”, “His sister”, and “Maria” to the antecedent “Maria Johnson”. CR allows us to transform a genealogical relationship between two tokens, such …

Simulating The Machine Translation Of Low-Resource Languages By Designing A Translator Between English And An Artificially Constructed Language, Michaela Snyder

Mahurin Honors College Capstone Experience/Thesis Projects

Natural language processing (NLP), or the use of computers to analyze natural language, is a field that relies heavily on syntax. It would seem intuitive that computers would thrive in this area due to their strict syntax requirements, but the syntax of natural languages leaves them unable to properly parse and generate sentences that seem normal to the average speaker. A subfield of NLP, machine translation, works mainly to computerize translation between different languages. Unfortunately, such translation is not without its weaknesses; language documentation is not created equal, and many low-resource languages—languages with relatively few kinds of documentation, most often …

Understanding Human-Centred Artificial Intelligence In The Banking Sector, Krishnaraj Arul Obuchettiar, Alan @ Ali Madjelisi Megargel

Research Collection Lee Kong Chian School Of Business

The advent of smart digital devices and social media has shaped how consumers interact and transact with their financial institutions. Consumers increasingly want hyperpersonalised interactions that are more frequent and proactive, while financial institutions have a growing need to cater to consumers’ new demands. Financial institutions, such as banks, continuously adapt to the latest technologies to keep pace with evolving customer behaviours, needs, and experiences. One such emerging technology is artificial intelligence (AI). Many organisations realise the potential of AI; however, a human-centred AI system must be capable of understanding human characteristics and making decisions like humans. This paper presents …

Seqadver: Automatic Payload Construction And Injection In Sequence-Based Android Adversarial Attack, Fei Zhang, Ruitao Feng, Xiaofei Xie, Xiaohong Li, Lianshuan Shi

Research Collection School Of Computing and Information Systems

Machine learning has achieved a great success in the field of Android malware detection. In order to avoid being caught by these ML-based Android malware detection, malware authors are inclined to initiate adversarial sample attacks by tampering with mobile applications. Although machine learning has high capability, it lacks robustness against adversarial attacks. Currently, many of the adversarial attacking tools not only inject dead code into target applications, which can never be executed, but also require the injection of many benign features into a malicious APK. This can be easily noticeable by program analysis techniques. In this paper, we propose SeqAdver, …

Multimodal Emotion Analysis With Focused Attention, Siddhi Kiran Bajracharya

Dissertations and Theses

Emotion analysis, a subset of sentiment analysis, involves the study of a wide array of emotional indicators. In contrast to sentiment analysis, which restricts its focus to positive and negative sentiments, emotion analysis extends beyond these limitations to a diverse spectrum of emotional cues. Contemporary trends in emotion analysis lean toward multimodal approaches that leverage audiovisual and text modalities. However, implementing multimodal strategies introduces its own set of challenges, marked by a rise in model complexity and an expansion of parameters, thereby creating a need for a larger volume of data. This thesis responds to this challenge by proposing a …

Exploring Transformers As Compact, Data-Efficient Language Models, Clayton Fields, Casey Kennington

Computer Science Faculty Publications and Presentations

Large scale transformer models, trained with massive datasets have become the standard in natural language processing. The huge size of most transformers make research with these models impossible for those with limited computational resources. Additionally, the enormous pretraining data requirements of transformers exclude pretraining them with many smaller datasets that might provide enlightening results. In this study, we show that transformers can be significantly reduced in size, with as few as 5.7 million parameters, and still retain most of their downstream capability. Further we show that transformer models can retain comparable results when trained on human-scale datasets, as few as …

Data-Driven Strategies For Pain Management In Patients With Sickle Cell Disease, Swati Padhee

Browse all Theses and Dissertations

This research explores data-driven AI techniques to extract insights from relevant medical data for pain management in patients with Sickle Cell Disease (SCD). SCD is an inherited red blood cell disorder that can cause a multitude of complications throughout an individual’s life. Most patients with SCD experience repeated, unpredictable episodes of severe pain. Arguably, the most challenging aspect of treating pain episodes in SCD is assessing and interpreting the patient’s pain intensity level due to the subjective nature of pain. In this study, we leverage multiple data-driven AI techniques to improve pain management in patients with SCD. The proposed approaches …

“Any Means Necessary To Refuse Erasure By Algorithm:” Lillian-Yvonne Bertram’S Travesty Generator, Zach Whalen

Communication & Digital Studies Articles

Lillian-Yvonne Bertram's 2019 book of poetry is titled Travesty Generator in reference to Hugh Kenner and Joseph O'Rourke's Pascal program to “fabricate pseudo-text” by producing text such that each n-length string of characters in the output occurs at the same frequency as in the source text. Whereas for Kenner and O'Rourke, labeling their work a “travesty” is a hyperbolic tease or a literary burlesque, for Bertram, the travesty is the political reality of racism in America. For each of the works Travesty Generator, Bertram uses the generators of computer poetry to critique, resist, and replace narratives of oppression and to …

Code Execution Capability As A Metric For Machine Learning–Assisted Software Vulnerability Detection Models, Daniel Grahn, Lingwei Chen, Junjie Zhang

Computer Science and Engineering Faculty Publications

In this paper, we consider how the ability to learn Code Execution Tasks affects a model’s accuracy on software vulnerability detection (SVD) benchmark datasets. We initially find that models can achieve near state-of-the-art accuracy on SVD benchmarks regardless of their ability to learn Code Execution Tasks. However, these models fail to generalize well across SVD benchmarks. The results indicate a bias in the datasets that allows models to predict non- SVD signals. Under the theory that different collection methods will reduce biases, we investigate combining the SVD datasets. When trained on combined datasets, SVD accuracy is reduced but correlation with …

Disciplines Different Of Fine-Grained Acknowledged Entity：A Case Of Doctoral Dissertations In Chinese Humanities And Social Sciences, Jiaxin He, Shijin Zhang, Jiayu Zheng, Xinlong Chu, Chengzhi Zhang

Journal of Scientific Information Research

[Purpose/significance]Thesis acknowledgment is a public text in which the authors express their gratitude to individuals and institutions those support their research. It is helpful to understand the individuals and institutions that play a role in the cultivation of doctoral candidate in different disciplines by extracting the entities of acknowledgment and comparing the distribution of the objects of acknowledgment in the dissertations of different disciplines.[Method/process]In this paper, we gained more than 60 000 Chinese doctoral dissertations acknowledgment of 21 humanities and social sciences disciplines, extracted acknowledged entities from acknowledgment, and constructed a fine-grained classification system of acknowledgment entities. The classification system …

Binary Text Classification Using Genetic Programming With Crossover-Based Oversampling For Imbalanced Datasets, Mona Aljero, Nazi̇fe Di̇mi̇li̇ler

Turkish Journal of Electrical Engineering and Computer Sciences

It is well known that classifiers trained using imbalanced datasets usually have a bias toward the majority class. In this context, classification models can present a high classification performance overall and for the majority class, even when the performance for the minority class is significantly lower. This paper presents a genetic programming (GP) model with a crossover-based oversampling technique for oversampling the imbalanced dataset for binary text classification. The aim of this study is to apply an oversampling technique to solve the imbalanced issue and improve the performance of the GP model that employed the proposed technique. The proposed technique …

Lvq Treatment For Zero-Shot Learning, Firat İsmai̇loğlu

Turkish Journal of Electrical Engineering and Computer Sciences

In image classification, there are no labeled training instances for some classes, which are therefore called unseen classes or test classes. To classify these classes, zero-shot learning (ZSL) was developed, which typically attempts to learn a mapping from the (visual) feature space to the semantic space in which the classes are represented by a list of semantically meaningful attributes. However, the fact that this mapping is learned without using instances of the test classes affects the performance of ZSL, which is known as the domain shift problem. In this study, we propose to apply the learning vector quantization (LVQ) algorithm …

Automated Short-Answer Grading And Misconception Detection Using Large Language Models, Nazmul H. Kazi

UNF Graduate Theses and Dissertations

As education technology continues to evolve, the domains of Automatic Short-Answer Grading (ASAG) and Automated Misconception Detection (AMD) stand at the forefront of innovative approaches to educational assessment. We explore the transformative potential of Large Language Models (LLMs) in revolutionizing these critical areas. Leveraging the remarkable capabilities of LLMs in semantic inference, contextual understanding, and transfer learning, we embark on a comprehensive journey to enhance both ASAG and AMD. On ASAG, we illuminate the efficacy of transfer learning by fine-tuning RoBERTa Large, a state-of-the-art LLM, on task-related corpora, e.g. the Multi-Genre Natural Language Inference (MNLI) corpus. The model's adaptability across …

Practical Ai Value Alignment Using Stories, Md Sultan Al Nahian

Theses and Dissertations--Computer Science

As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally - using only a measure of task performance as feedback--can violate societal norms for acceptable behavior or cause harm. Consequently, it becomes necessary to prioritize task performance and ensure that AI actions do not have detrimental effects. Value alignment is a property of intelligent agents, wherein they solely pursue goals and activities that are non-harmful and beneficial to humans. Current approaches to value alignment largely depend on imitation learning or learning from demonstration methods. However, the dynamic nature …

Murder On The Vr Express: Studying The Impact Of Thought Experiments At A Distance In Virtual Reality, Andrew Kissel, Krzysztof J. Rechowicz, John B. Shull

Philosophy Faculty Publications

Hypothetical thought experiments allow researchers to gain insights into widespread moral intuitions and provide opportunities for individuals to explore their moral commitments. Previous thought experiment studies in virtual reality (VR) required participants to come to an on-site laboratory, which possibly restricted the study population, introduced an observer effect, and made internal reflection on the participants’ part more difficult. These shortcomings are particularly crucial today, as results from such studies are increasingly impacting the development of artificial intelligence systems, self-driving cars, and other technologies. This paper explores the viability of deploying thought experiments in commercially available in-home VR headsets. We conducted …

Combating Fake News: A Gravity Well Simulation To Model Echo Chamber Formation In Social Media, Jeremy E. Thompson

Dartmouth College Ph.D Dissertations

Fake news has become a serious concern as distributing misinformation has become easier and more impactful. A solution is critically required. One solution is to ban fake news, but that approach could create more problems than it solves, and would also be problematic from the beginning, as it must first be identified to be banned. We initially propose a method to automatically recognize suspected fake news, and to provide news consumers with more information as to its veracity. We suggest that fake news is comprised of two components: premises and misleading content. Fake news can be condensed down to a …

Context Aware Neural Machine Translation Using Graph Encoders, Saurabh Kale

Master's Projects

Machine translation presents its root in the domain of textual processing that focuses on the usage of computer software for the purpose of translation of sentences. Neural machine translation follows the same idea and integrates machine learning with the help of neural networks.Various techniques are being explored by researchers and are famously used by Google Translate, Bing Microsoft Translator, Deep Translator, etc. However, these neural machine translation techniques do not incorporate the context of the sentences and are only determined by the phrasesor sentence structure. This report explores the neural machine translation technique dedicated to context-aware translations. It also provides …

Ml-Based User Authentication Through Mouse Dynamics, Sai Kiran Davuluri

Master's Projects

Increasing reliance on digital services and the limitations of traditional authentication methods have necessitated the development of more advanced and secure user authentication methods. For user authentication and intrusion detection, mouse dynamics, a form of behavioral biometrics, offers a promising and non-invasive method. This paper presents a comprehensive study on ML-Based User Authentication Through Mouse Dynamics.

This project proposes a novel framework integrating sophisticated techniques such as embeddings extraction using Transformer models with cutting-edge machine learning algorithms such as Recurrent Neural Networks (RNN). The project aims to accurately identify users based on their distinct mouse behavior and detect unauthorized access …

Spam Comments Detection In Youtube Videos, Priyusha Kotta

Master's Projects

This paper suggests an innovative way for finding spam or ham comments on the video- sharing website YouTube. Comments that are contextually irrelevant for a particular video or have a commercial motive constitute as spam. In the past few years, with the advent of advertisements spreading to new arenas such as the social media has created a lucrative platform for many. Today, it is being widely used by everyone. But this innovation comes with its own impediments. We can see how malicious users have taken over these platforms with the aid of automated bots that can deploy a well-coordinated spam …

Tiny Language Models Enriched With Multimodal Knowledge From Multiplex Networks, Clayton Fields, Osama Natouf, Andrew Mcmains, Catherine Henry, Casey Kennington

Computer Science Faculty Publications and Presentations

Large transformer language models trained exclusively on massive quantities of text are now the standard in NLP. In addition to the impractical amounts of data used to train them, they require enormous computational resources for training. Furthermore, they lack the rich array of sensory information available to humans, who can learn language with much less exposure to language. In this study, performed for submission in the BabyLM challenge, we show that we can improve a small transformer model’s data efficiency by enriching its embeddings by swapping the learned word embeddings from a tiny transformer model with vectors extracted from a …

More Human Than Human: Llm-Generated Narratives Outperform Human-Llm Interleaved Narratives, Zoie Zhao, Sophie Song, Bridget Duah, Jamie C. Macbeth, Scott Carter, Monica Van, Nayeli Bravo, Matthew Klenk, Katherine Sieck, Alexandre Filipowicz

Computer Science: Faculty Publications

Narrative story generation has gained emerging interest in the field of large language models. The present paper aims to compare stories generated by an LLM only (non-interleaved) with those generated by interleaving human-generated and LLM-generated text (interleaved). The study’s hypothesis is that interleaved stories would perform better than non-interleaved stories. To verify this hypothesis, we conducted two tests with roughly 500 participants each. Participants were asked to rate stories of each type, including an overall score or preference and four facets—logical soundness, plausibility, understandability, and novelty. Our findings indicate that interleaved stories were in fact less preferred than non-interleaved stories. …

A Structured Narrative Prompt For Prompting Narratives From Large Language Models: Sentiment Assessment Of Chatgpt-Generated Narratives And Real Tweets, Christopher J. Lynch, Erik J. Jensen, Virginia Zamponi, Kevin O'Brien, Erika Frydenlund, Ross Gore

VMASC Publications

Large language models (LLMs) excel in providing natural language responses that sound authoritative, reflect knowledge of the context area, and can present from a range of varied perspectives. Agent-based models and simulations consist of simulated agents that interact within a simulated environment to explore societal, social, and ethical, among other, problems. Simulated agents generate large volumes of data and discerning useful and relevant content is an onerous task. LLMs can help in communicating agents' perspectives on key life events by providing natural language narratives. However, these narratives should be factual, transparent, and reproducible. Therefore, we present a structured narrative prompt …