Digital Commons Network^™

Ml-Based User Identification Through Mouse Dynamics, Rakshit Gupta

Master's Projects

User authentication and identification plays a crucial role in ensuring the security and integrity of digital systems. Traditional authentication methods, such as passwords and biometrics, have inherent limitations that can compromise system security. This research proposes a novel approach to user authentication by leveraging machine learning techniques and behavioral biometrics, specifically mouse dynamics. The primary objective is to develop a sophisticated framework that can accurately identify individuals based on their unique mouse behavior patterns. The study explores and compares multiple deep learning architectures, including Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and Transformer models, to generate embeddings from …

Distinguishing Chatbot From Human, Gauri Anil Godghase

Master's Projects

There have been many recent advances in the field of Generative Artificial Intelligence and Large Language Models, with GPT 3 or ChatGPT model being one of the frontrunners in this field. These large language models have become so powerful that it has become difficult to differentiate between text written by humans and machine-generated text. This paper proposes a solution to the problem of classification of the origin of data (human or chatbot) by using Machine Learning. In addition, the proposed solution also helps us analyze the text generated by such Language Models and understand the underlying patterns present in the …

Sample Sizes For 10 Types Of Qualitative Data Analysis: An Integrative Review, Empirical Guidance, And Next Steps, Amber Wutich, Melissa Beresford, H. Russell Bernard

Faculty Research, Scholarly, and Creative Activity

There has been a recent explosion of articles on minimum sample sizes needed for analyzing qualitative data. The purpose of this integrated review is to examine this literature for 10 types of qualitative data analysis (5 types of saturation and 5 common methods). Building on established reviews and expanding to new methods, our findings extract the following sample size guidelines: theme saturation (9 interviews; 4 focus groups), meaning saturation (24 interviews; 8 focus groups), theoretical saturation (20–30+ interviews), metatheme saturation (20–40 interviews per site), and saturation in salience (10 exhaustive free lists); two methods where power analysis determines sample size: …

Research On Teachers Of Color And Indigenous Teachers: Developing And Fortifying Policies That Diversify The Educator Workforce, Conra Gist, Travis J. Bristol, Saili Kulkarni

Faculty Research, Scholarly, and Creative Activity

This special issue expands upon the Handbook of Research on Teachers of Color and Indigenous Teachers (Gist & Bristol, 2022a) and the practitioner-focused Phi Delta Kappan special issue, “Learning from the Voices of Black, Indigenous and People of Color Educators: Charting New Directions for Research, Policy, and Practice” (Gist & Bristol, 2021). The co-created articles in this special issue highlight the combined expertise of policy makers and education researchers. While the Handbook featured empirical research, and the Phi Delta Kappan special issue featured research briefs and teacher testimonies, the policy-driven articles in this special issue explore how research can be …

Resume Content Generation Using Llama 2 With Adapters, Navaneeth Sai Nidadavolu, William B. Andreopoulos

Faculty Research, Scholarly, and Creative Activity

This paper presents a novel approach to enhancing the Llama language model for generating customized resumes tailored to domain-specific job descriptions. Unlike traditional methods that rely heavily on extensive fine-tuning, we implement scalable adapter modules to minimize parameter adjustments. This approach preserves the model's inherent ability to generate coherent and contextually appropriate language across diverse tasks, ensuring that its general linguistic capabilities remain intact. Additionally, we employ a prompting strategy to dynamically create a diverse and comprehensive dataset, ensuring high relevance to various job roles. Using a dataset of 10,000 job descriptions and resumes, our approach resulted in a 20% …

The Applicability Of Llms In Generating Textual Samples For Analysis Of Imbalanced Datasets, Saroj Gopali, Faranak Abri, Akbar Siami Namin, Keith S. Jones

Faculty Research, Scholarly, and Creative Activity

In machine learning class imbalance is a pressing issue, where the model is biased towards the majority classes and underperforms in the minority classes. In textual data, the natural language processing (NLP) model bias significantly reduces overall accuracy, along with poor performance in minority classes. This paper investigates and compares the performance of transformer-based models, such as Multi-head Attention with the data levels and algorithmic levels approaches and BERT (Bidirectional Encoder Representations from Transformers) with LLM-based data augmentation. The research utilized the approaches, such as Random Over Sampler, Synthetic Minority Over-sampling Technique (SMOTE), SMOTEENN, data augmentation at word level, class …

The Role Of Intersectionality In Research On Teachers Of Color And Indigenous Teachers, Saili S. Kulkarni, Tanja Burkhard, David J. Johns

Faculty Research, Scholarly, and Creative Activity

This paper emphasizes the complexity and criticality of intersectionality in understanding the research on Teachers of Color and Indigenous Teachers (TOCIT). Cho and colleagues (2013) identified three dimensions of intersectional dialogues: how intersectionality has been used in research and teaching, how it has been used as a theory and methodology, and how it has been used in community organizations. As Cho and colleagues noted, what intersectionality does in theory is equally as important as what it does in practice. Therefore, we drew from the recently published Handbook of Research on Teachers of Color and Indigenous Teachers to highlight how intersectionality …

The Role Of Paradata In Algorithmic Accountability, Ciaran B. Trace, James A. Hodges

Faculty Research, Scholarly, and Creative Activity

This chapter examines how the doings of the algorithm (instantiated through its operations, actions, and steps) and its accompanying algorithmic system are revealed and explored through an engagement with the paradata created as a part of this data-making effort. In doing so, the chapter explores how the concept of paradata helps us understand how information professionals and domain stakeholders conceptualize accountable algorithmic entities and how this influences how they emerge as documented and describable entities. Two complementary frameworks for capturing and preserving paradata for accountability purposes are examined in the process. The first is associated with diplomatic theory and archival …

Cross-Cultural Adaptation Of The Voice-Related Experiences Of Nonbinary Individuals - Veni To Brazilian Portuguese, Isabela Dos Santos, Mara Behlau, Grace Shefcik, Pei Tzu Tsai, Vanessa Veis Ribeiro

Faculty Research, Scholarly, and Creative Activity

Purpose: This study aimed to translate and cross-culturally adapt the “Voice-related Experiences of Nonbinary Individuals” (VENI) to Brazilian Portuguese (BP). Methods: Cross-cultural adaptation was performed based on the combined guidelines of the World Health Organization’s (WHO) Translation Recommendations and the COnsensus-based Standards for the selection of health Measurement INstruments (COSMIN). The process included five stages: a) Translation of the instrument into BP by a translator specialized in the construct and a non-specialist, both native BP speakers and fluent in English; b) Synthesis of the two translations by consensus; c) Back-translation by a translator specialized in the construct and a non-specialist, …

Fpdclustering: A Comprehensive R Package For Probabilistic Distance Clustering Based Methods, Cristina Tortora, Francesco Palumbo

Faculty Research, Scholarly, and Creative Activity

Data clustering has a long history and refers to a vast range of models and methods that exploit the ever-more-performing numerical optimization algorithms and are designed to find homogeneous groups of observations in data. In this framework, the probability distance clustering (PDC) family methods offer a numerically effective alternative to model-based clustering methods and a more flexible opportunity in the framework of geometric data clustering. Given nJ-dimensional data vectors arranged in a data matrix and the number K of clusters, PDC maximizes the joint density function that is defined as the sum of the products between the distance and the …

Computer Vision Intelligence Test Modeling And Generation: A Case Study On Smart Ocr, Jing Shu, Bing Jiun Miu, Eugene Chang, Jerry Gao, Jun Liu

Faculty Research, Scholarly, and Creative Activity

AI-based systems possess distinctive characteristics and introduce challenges in quality evaluation at the same time. Consequently, ensuring and validating AI software quality is of critical importance. In this paper, we present an effective AI software functional testing model to address this challenge. Specifically, we first present a comprehensive literature review of previous work, covering key facets of AI software testing processes. We then introduce a 3D classification model to systematically evaluate the image-based text extraction AI function, as well as test coverage criteria and complexity. To evaluate the performance of our proposed AI software quality test, we propose four evaluation …

Emergency And Disaster Preparedness For Individuals Who Use Augmentative And Alternative Communication: A Pilot Study On Supported Planning Using A Toolkit, Andrea Barton-Hulsey, Miriam C. Boesch, Yoosun Chung, Tina Caswell, Amy Miller Sonntag, Wendy Quach

Faculty Research, Scholarly, and Creative Activity

Purpose: When emergencies or disasters arise, individuals who use augmenta-tive and alternative communication (AAC) are particularly vulnerable. It is critical that individuals who use AAC are supported to make decisions that impact their own lives and are able to communicate during such a crisis. Preparedness efforts that include a plan around communication needs and supports are necessary for ensuring that individuals who use AAC are able to understand options that ensure personal safety and express their needs during a time of crisis. Method: Qualitative methods were used to identify and describe the experi-ences of two young adults who use AAC …

Challenges Encountered In The Implementation Of The National Literacy Acceleration Program (Nalap) In The Abura Asebu Kwamankese District, Ghana, Julius Arhin-Asamoah

Library Philosophy and Practice (e-journal)

The National Literacy Acceleration Program (NALAP) aims to enhance early grade primary school pupils' literacy rates, yet national evaluations reveal widespread deficiencies in reading proficiency in both the local language and English. This study examines challenges in implementing NALAP in the Abura Asebu Kwamankese district, Ghana, focusing on the teacher and resource-related issues. A mixed-methods sequential explanatory design was employed. The study covered 12 basic schools in the Abura Asebu Kwamankese district. In all, 61 respondents comprising 50 teachers and 11 circuit supervisors were involved in the study. The findings highlight teacher-related issues such as inadequate pedagogical practices, low motivation, …

Harnessing Artificial Intelligence-Powered Search Engines For The Literature Review Process, Omobolanle Seri Fasola

Library Philosophy and Practice (e-journal)

Literature reviews are an essential part of research, and they require a significant amount of time and effort to be able to search through the millions of academic papers both online and physically. However, with the advent of AI-powered search engines, the process of conducting literature reviews has become more efficient and effective. AI-powered search engines use machine learning algorithms to analyze large volumes of data and provide researchers with relevant and accurate information in a matter of seconds. The importance of AI-powered search engines in literature reviews cannot be overstated. They help researchers save time, improve the accuracy and …

Using Graph Neural Networks For Social Recommendations, Dharahas Tallapally, John Wang, Katerina Potika, Magdalini Eirinaki

Faculty Research, Scholarly, and Creative Activity

Recommender systems have revolutionized the way users discover and engage with content. Moving beyond the collaborative filtering approach, most modern recommender systems leverage additional sources of information, such as context and social network data. Such data can be modeled using graphs, and the recent advances in Graph Neural Networks have led to the prominence of a new family of graph-based recommender system algorithms. In this work, we propose the RelationalNet algorithm, which not only models user–item, and user–user relationships but also item–item relationships with graphs and uses them as input to the recommendation process. The rationale for utilizing item–item interactions …

Students’ Perception Of Plagiarism As A Form Of Academic Dishonesty (Case Study On Students Of Uin Syarif Hidayatullah Jakarta), Al Muhdil Karim, Evi Zakiyah

Library Philosophy and Practice (e-journal)

The rapid advancement of information technology has an impact on easier access to information, which could encourage academic plagiarism. If plagiarism is not overcome, it can have a number of consequences, including copyright infringement and the emergence of the assumption that plagiarism is a simple way to create a scientific work. Thus, actions are required to overcome plagiarism, one of which is understanding the perception of students as academicians who frequently commit plagiarism, so strategies to overcome it may be provided. This is a quantitative study based on a survey of 106 students of UIN Syarif Hidayatullah Jakarta. The data …

Is A Psychotic Anthropology Possible? Or How To Have Inclusive Anthropologies Of Subjectivity And Personhood, John Marlovits, Matthew J. Wolf-Meyer

Faculty Research, Scholarly, and Creative Activity

Dominant anthropological theories of mind, cognition, and consciousness reify particular ways of being in the world as "normal," which marginalizes the experiences of people who do not meet normative expectations of personhood or exhibit nonnormative subjectivities. By focusing on atypical forms of communication and self-representation in the ethnographic record, which draws from work in the anthropology of disability and psychological anthropology, we argue for the need to attend to interactions and behavior as the necessary basis for anthropological studies of personhood and subjectivity. These foci, which build on a foundation provided by affect theory and disability studies, stand to open …

Humor And Surveillance - “That’S Not Funny” (Or Is It?): For Professor Serge Gutwirth On His Retirement, Gary T. Marx

Secrecy and Society

No abstract provided.

Semiotic Analysis Of Library Homepages: A Case Study Of The University Of Management And Technology (Umt), Lahore, Pakistan., Mariym Muhammad Muhammad Ismail Miss, Muhammad Waseem Zia Mr, Kamaluddeen Isa El-Kalash

Library Philosophy and Practice (e-journal)

Abstract

Purpose- Signs and symbols play important roles in our lives because they help us to convey messages even without written words. With the invention of the internet and the evolution of web technologies, the universe became a global village because the internet facilitated a better and faster avenue for human communication. In libraries and allied information science terrains, the internet fostered the use of Websites, to portray the intellectual contents that are domiciled in them. On the library websites, users can ascertain the timings, collections, policies etc. of a particular library because the icons that are visible on a …

Artificial Intelligence Adoption And Utilization By Librarians In University Libraries In Kwara State, Nigeria, Abdrahman Atanda Moustapha, Ibrahim .O. Yusuf Mr.

Library Philosophy and Practice (e-journal)

The study investigated how librarians working in various university libraries in Kwara State, Nigeria, adopt and use artificial intelligence. The study raised four research goals as well as four research questions. A descriptive survey method and random sampling techniques with 450 randomly selected librarians from Kwara State Universities, Nigeria, were used for the research. Five research assistants were trained on how to contact respondents and secure their consent before distributing the structured questionnaire designed by the researcher, who assisted in the tool distribution process. The researcher was able to retrieve 410 copies of the 450 questionnaires that were given to …

Application And Use Of Artificial Intelligence (Ai) For Library Services Delivery In Academic Libraries In Kwara State, Nigeria, Abdullahi Olayinka Isiaka

Library Philosophy and Practice (e-journal)

The application and use Artificial Intelligence (AI) in library services delivery and operations has modernized traditional practices, enabling libraries to adapt to the evolving information needs of patrons in the digital era. The main purpose of this study is to investigate the application and use of Artificial Intelligence (AI) Technologies for Library Services Delivery in Academic Libraries in Kwara State, Nigeria. The study used a descriptive survey approach. The population was the 108 librarians in academic libraries in Kwara State, Nigeria. A total enumeration technique was employed, and a questionnaire was used to collect data from the library staff. The …

Comparative Analysis Of Covid-19 Non-Pharmaceutical Intervention Videos On Facebook: Insights From Nigeria And Benin Republic, Jimme Matyek, Sheba Umbule Tayo-Garbson, Philomena Effiong Umoren Phd, Benmun Paul, Emeka Williams Etumnu

Library Philosophy and Practice (e-journal)

Facebook has been adopted by public health organisations for health promotion, psychoeducation and behaviour change campaigns. Studies have underscored the potential advantages of non-pharmaceutical interventions (NPIs) in decelerating the transmission of COVID-19 and mitigating its severe health consequences. However, these studies did not content analyse these NPI messages especially on Facebook. This study sought to investigate the phenomenon of NPI COVID-19 videos on Facebook that were viewed by Nigerians and Beninese. This study used quantitative content analysis as the research design and analysed 56 Nigerian videos and 36 Beninese videos totalling 92 on Facebook with an inter-rater reliability of 96%. …

A Case Study: Relationship Between Students' Reading Habits And Their Academic Performance In Government Post Graduate College Nowshera At Bachelor Of Sciences (Bs) Level, Muhammad Yaqoob

Library Philosophy and Practice (e-journal)

Those who read more books, have more chances of mental development and better opportunities of success. Hence, this paper is an attempt to find out relationship between students’ reading habits and their academic performance in Government Post Graduate College Nowshera, Pakistan at Bachelor of Sciences (BS) level. To collect the relevant data, a questionnaire was designed and distributed among 420 (270 males and 150 females) students studying at BS level. The questionnaire investigated students’ reading habit and their attitudes towards reading. Students’ academic performances were recorded through the transcripts of their examination in the previous semester. The collected data were …

A Scientometric Analysis Of The Global Research Output On Information Literacy Using Web Of Science, Ganesh Kumar K, Senthilkumar, V

Library Philosophy and Practice (e-journal)

This study is aimed to examine the productivity and literature output in Information Literacy. This study analyses the growth of the literature output and information literacy, types of documents. The relevant data were collected using the Web of Science database from the period 2011-2023 and data were tabulated. The total record retrieved is 2582. Major subject categories are authors whose contribution is at the maximum level, country-wise productivity, Affiliations of the institutions, and the source titles of the literature. The highest number of documents were published in the year 2022 i.e., 295 records (11.416 %), and lowest number of documents …

Social Inequalities And The Adoption Of Health Misinformation In Cameroon: Implications On Health Behaviour, Eugene Nche Che

Library Philosophy and Practice (e-journal)

Public health restrictions in response to the COVID-19 pandemic resulted in an increase in the reliance on social media for peer interactions. This resulted in the proliferation of medical misinformation and conspiracy theories that undermined public support for disease control measures, and influenced negative health attitudes such as vaccine denial. The aim of this study was to determine how social inequalities influence the adoption of health related misinformation, and the extent to which the adoption of health misinformation results in poor health behaviours. The study employed an exploratory survey design, and relied on both quantitative and qualitative methods to collect …

The Role Of The Library In National Development, Jerry Eyerinmene Friday Mr, Ekeruche Augustina Chinwe Mrs

Library Philosophy and Practice (e-journal)

Every nation in the world aspires for its development because it guarantees the wellbeing of its people. This development, which is referred to as national development, involves various facets of development such as economic development, political development, educational development, manpower development, rural development and so on. Economic development and political development are like two sides of a coin. They seem to be inseparable as one influences the other. These two components of national development are essential to any country across the globe. Hence, nearly all nations in the world make earnest effort at achieving these aspects of national development. A …

The Role Of The Library In National Development, Jerry Eyerinmene Friday Mr, Augustina Chinwe Ekeruche Mrs

Library Philosophy and Practice (e-journal)

Every nation in the world aspires for its development because it guarantees the wellbeing of its people. This development, which is referred to as national development, involves various facets of development such as economic development, political development, educational development, manpower development, rural development and so on. Economic development and political development are like two sides of a coin. They seem to be inseparable as one influences the other. These two components of national development are essential to any country across the globe. Hence, nearly all nations in the world make earnest effort at achieving these aspects of national development. A …

Effects Of Lexical Frequency On The Post-Exposure Magnitude Of Recalibration In Lexically Guided Perceptual Learning: An Explorative Analysis, Hahn Koo, Reiko Kataoka, Julia Thomas Swan, Christina Y. Tzeng

Faculty Research, Scholarly, and Creative Activity

Listeners use lexical information to guide the mapping between acoustic signals and representations of speech sound. This process is known as perceptual learning and results in recalibration of phonetic categories. The current work examines the effect of lexical frequency of exposure words on the magnitude of recalibration. Results showed comparable levels of perceptual learning for listeners exposed to high-frequency vs low-frequency critical words, in line with empirical findings that suggest that if frequency affects recalibration, such effects may be difficult to detect. These findings warrant further empirical probing and theoretical characterization of the role of lexical frequency in perceptual learning.

Use Of Social Media Platforms In Disseminating Information Amid Covid-19 Pandemic In Technical University Libraries In Ghana, Jennifer Kyerewaa Antwi Ms., Akwasi Duffour Frimpong Mr.

Library Philosophy and Practice (e-journal)

Abstract

Educational institutions have undergone tremendous changes through the usage of technology-based applications. Academic libraries however have not been left out of this transition since the libraries are instituted in the university and the heart of the institution. The study aimed to examine social media use to disseminate information amid the Covid-19 pandemic in Technical University libraries. A qualitative research approach was used with semi-structured interviews used to collect data from ten participants. The findings revealed that most of the participants made use of social media like Facebook, YouTube, Instagram, and WhatsApp to disseminate information during the pandemic in both …

Enhancing Plagiarism Detection: The Role Of Artificial Intelligence In Upholding Academic Integrity, Sudhakar Mishra

Library Philosophy and Practice (e-journal)

Plagiarism poses a significant threat to academic integrity, requiring effective measures for its detection and prevention. This paper explores the efficacy of plagiarism detection tools in upholding academic integrity, with a specific focus on the use of artificial intelligence (AI) technologies. The abstract introduces the concept of plagiarism and its impact on scholarly work. It highlights the importance of reliable and accurate plagiarism detection methods and emphasizes the role of AI in enhancing the effectiveness of such tools. The abstract briefly outlines the main points covered in the paper, including the use of AI techniques such as text matching algorithms …