Learning Community Research Articles

The impact of generative AI on the scholarly communications of early career researchers: An international, multi‐disciplinary study

AbstractThe Harbingers study of early career researchers (ECRs), their work life and scholarly communications, began by studying generational—Millennial—change (c.2016), then moved to pandemic change (c.2020) and is now investigating another potential agent of change: artificial intelligence (2024–). We report here on a substantial scoping pilot study that looks at the impact of AI on the scholarly communications of international ECRs and, extends this to the arts and humanities. It aims to fill the knowledge gap concerning ECRs whose millennial mindset may render them especially open to change and, as the research workhorses they are, very much in the frontline. The data was collected via in‐depth interviews in China, Malaysia, Poland, Portugal, Spain and (selectively) the United Kingdom/United States. The data show ECRs to be thinking, probing and, in some cases, experimenting with AI. There was a general acceptance that AI will be responsible for the growth of low‐quality scientific papers, which could lead to a decline in the quality of research. Scholarly integrity and ethics were a big concern with issues of authenticity, plagiarism, copyright and poor citation practices raised. The most widespread belief was AI would prove to be a transformative force and would exacerbate existing scholarly disparities and inequalities.

Field‐specific gold open access dynamics in the Chinese mainland: Overviews, disparities, and strategic insights

AbstractGold Open Access (OA) journals are crucial for scholarly communication, highlighting the need for a thorough evaluation of their academic influence on different research fields. This study leverages the InCites platform to examine article‐level characteristics relating to 22 Essential Science Indicators (ESI) research fields, with a focus on the dynamics of gold OA articles, including gold OA uptake in the Chinese mainland and gold OA adoption in the domestic English‐language academic journal publishing of the Chinese mainland. The findings reveal that disparities in gold OA adoption across 22 ESI fields are more pronounced in the Chinese mainland compared with the world scenario. In the Chinese mainland, there is a significant polarization in gold OA publishing volumes across different ESI fields, particularly in Chemistry, Clinical Medicine, and Engineering. This study builds on the understanding of OA citation advantage (OACA) by incorporating gold OA publishing volume into a two‐dimensional framework, resulting in the development of a “distance” metric. It further categorizes gold OA citation effects into four quadrants: positive citation effects (quadrants A and B) and negative citation effects (quadrants C and D), based on category normalized citation impact (CNCI) and journal normalized citation impact (JNCI) indicators from the InCites database. The findings underscore the importance of developing tailored strategies to address field‐specific challenges and promote gold OA dynamics in the Chinese mainland; while prioritizing high‐quality gold OA journals is essential for fostering gold OA development in the rest of the world.

Professional experience of Chinese international pre-service teachers in Australia’s early childhood education: professional learning and belonging

ABSTRACT International pre-service teachers (PSTs) can struggle to engage with Professional Experience (PE) communities in an Australian Early Childhood Education context. This qualitative case study examines three first-year Chinese international PSTs’ PE in different early childhood settings in Australia. Framed by Bourdieu’s analytical concepts, this paper explores Chinese PSTs’ culturally shaped understanding of PE and mentoring expectations, showing how this dimension of their habitus is differentiated and differentiating. We argue that with a supportive learning community, the rich cultural and linguistic repertoire of international PSTs can add to capital and funds of knowledge of Australian Early Childhood Education.

Use of Social Media and Artificial Intelligence Tools by Online Doctoral Students

Our paper aims to explore how doctoral EdD students in their thesis stage made use of digital technologies, social media (SM), and artificial intelligence (AI) tools. In this study, AI does not involve data on the use of the new generation of AI, which has been introduced in more recent years after this study took place. This paper refers to a 2nd stage qualitative analysis of semi-structured interviews collected from research undertaken in 2018 into student use of digital technologies in an online professional doctorate programme. The original study utilised an exploratory case study approach, an online survey (n = 28), and a series of semi-structured interviews (n = 9). This study will add further qualitative findings and perspectives to those that emerged in the previous study. This study will help to provide new insights into the interview data that was used to inform the initial paper resulting from the research in 2018. We argue that the unique characteristics of online doctoral students as both individuals and learners determine the popularity of some digital tools and that, in order to make the best use of the full range available they need to develop new skills and a better understanding of the pedagogy associated with those digital tools and the value they can add to an educational context. This can be achieved through the provision of more systematic coaching and support systems. This in turn will contribute to enhancing students’ feelings of belonging to a real academic learning community and their self-confidence and autonomy as online learners in general and in their performance in a Viva in particular.

Enhancing English abstract quality for non-English speaking authors using ChatGPT: A comparative study of Taiwan, Japan, China, and South Korea with slope graphs.

A clear and proficient English abstract is crucial for disseminating research findings to a global audience, significantly impacting the accessibility and visibility of research from non-English speaking countries. Despite the adoption of ChatGPT since November 30, 2022, a comprehensive analysis of improvements in English abstracts in scholarly journals has not been conducted. This study aims to identify which authors from Taiwan, Japan, China, and South Korea (TJCS) have shown the most improvement in English abstracts. Article abstracts published in Medicine (Baltimore) sourced from the Web of Science Core Collection from 2020 to 2023 were downloaded. A mixed-methods approach was employed, combining quantitative analysis of linguistic quality indicators and qualitative assessments of coherence and engagement using the Rasch model. Ten quality indicators were determined by prompting ChatGPT. Two scenarios were analyzed: (1) generative pretrained transformer (GPT) versus non-GPT (each with 30 abstracts from 2021) and (2) TJCS in comparison (each with 100 abstracts from 2021 and 2023, respectively). Standardized mean differences were compared using paired samples t test. Visuals including forest plots, Rasch Wright Map, the slope graph, and scatter plot with 95% control lines were used to examine the 2 scenarios. (1) No significant difference was found between GPT and non-GPT abstracts with Rasch logit scores of 3.31 and 3.17, respectively (P = .42), likely due to small sample size (n = 30); (2) significant difference exists between 2020 and 2023 in each country, and between South Korea and Taiwan in 2020. Among TJCS, Taiwan showed the greatest improvement in English abstract quality post-ChatGPT implementation, followed by Japan, China, and South Korea. The English abstracts in Medicine (Baltimore) have improved, reflecting the tool's positive impact on enhancing technical language. This study demonstrates that ChatGPT can enhance the quality of English abstracts for authors from non-English speaking regions, although the assumption that all authors use ChatGPT is invalid and impractical. The findings underscore the value of artificial intelligence tools in academic writing and recommend further investigation into the long-term implications of artificial intelligence integration in scholarly communication.

In between the neoliberal reality and the humanities imagination: a narrative inquiry of an English major’s identity construction in China

ABSTRACT This study reports an ethnographic case study of a Chinese female English major of a working-class background – Faye (pseudonym) and her English learning and use experience in an elite community in the Chinese context. Drawing on the data collected from a 13-month longitudinal inquiry, the study employs Darvin and Norton’s [2015. ‘Identity and a Model of Investment in Applied Linguistics.’ Annual Review of Applied Linguistics 35:36–56. https://doi.org/10.1017/S0267190514000191] model of investment to explore her identity transformation through English-as-a-foreign-language (EFL) practices. Findings suggest that Faye’s investment in EFL practices appeared to transform with her evolving perceptions of EFL learning and imagined identities, which were shaped largely under the influence of neoliberal and humanities discourses. The study argues for a critical interrogation of the impact of neoliberalism on EFL learning and humanities education, cautioning against its tendency to constrain identity potentials and sustain structural inequalities. Pedagogical implications are suggested at the end of the article.

Building Inclusive Learning Communities in Multicultural Classrooms: The Role of the CTL Model in Learning Interpersonal Skills

This study explores the effectiveness and challenges of implementing the Contextual Teaching and Learning (CTL) model in multicultural classrooms, particularly focusing on its impact on interpersonal skills development. The primary aim is to investigate how the CTL model enhances student engagement by connecting academic content to real-world contexts and to identify the barriers that impede its effective application. This research utilized a qualitative approach with a case study method to examine the application of the CTL (Contextual Teaching and Learning) model in building inclusive learning communities and fostering interpersonal skills in multicultural classrooms. The data collection techniques used in this study included interviews, observations, and document analysis. The findings indicate that while the CTL model significantly enhances student engagement and fosters the development of interpersonal skills, its implementation is fraught with challenges. Key obstacles include insufficient teacher training, misalignment with existing curriculum standards, limited resources, and institutional barriers such as rigid schedules and lack of administrative support. Despite these challenges, the research highlights the importance of sustained professional development and a supportive learning community to overcome these barriers. By addressing these issues, educators can better leverage the CTL model to create inclusive and effective learning environments. Overall, this study underscores the potential of the CTL model to transform teaching practices and improve student outcomes in multicultural settings. It calls for a concerted effort to provide the necessary support and resources for educators to implement the CTL model successfully, thereby enhancing educational experiences and fostering inclusive learning communities.

Diversity and Grit: First-Generation College Students in Online Degree Programs

ABSTRACT First-generation college students (FGCS) show self-determination and resilience as they seek to become the first within their families to earn a higher education degree. Colleges are beginning to recognize these strengths as they recruit and keep a diverse student population, particularly within the expanding online degree programs. For better insight into FGCS experiences online compared to students enrolled in traditional degree programs, researchers examined a secondary dataset from an anonymous undergraduate survey conducted at a 4-year public university. Among 412 survey respondents who identified as first-generation, 71 were enrolled in online degree programs. This study examines scores on the Grit-S and Social Support scales and student use of campus resources. Results highlight online students’ pattern of self-reliance over seeking outside support. They also had less connection to campus resources. Increased social support can enhance their sense of belonging to the learning community as online FGCS. Improving support for online students starts with collaboration between educators and administrators. Focusing on increasing academic confidence we can develop opportunities for online students to connect virtually with tutors, mentors, peer study groups, and faculty.

What Does It Mean to “Misuse” Research Data?

ABSTRACTIn this panel, we will discuss how “data misuse” is understood across different disciplines, and in particular digital curation, critical data studies, scholarly communication, and algorithmic fairness. The audience will be invited to contribute to the discussion by reporting on their own experience with data misuse, and brainstorming potential interventions to prevent misuse. Controversial reuses of open research data are emerging, including exploitation of marginalized communities, geo privacy violations, and perpetuation of harmful stereotypes. Incidents of data misuse hinder scientific progress and erode public trust, yet defining misuse remains challenging as one community's misuse might be another's best practice. The development of a shared framework to understand when, how, and why misuse of research data occurs can help science stakeholders decide when and how to release crucial research data, evaluate the potential for misuse, and tailor documentation of research data to prevent misuse. Our goal for this panel discussion is to take us a step closer to the development of such a theoretical framework for defining data misuse.

Institutional Mechanisms for Enhancing Production of Doctoral Research Outputs at Makerere University

In the contemporary knowledge society, research production is being re-purposed in terms of not just its academic value, but also its wider societal value. As such, doctoral research ought to be produced in the context of application. Therefore, universities have a responsibility to enhance the uptake and use of doctoral research outputs. This necessitates institutional mechanisms for enhancing the production of doctoral research outputs for uptake and use beyond academia. We examined the institutional mechanisms for enhancing production of doctoral research outputs at Makerere University using the research knowledge infrastructure (RKI) framework as the analytical lens. This was in light of the dismal uptake and use of research produced at Makerere University by students and staff. We used qualitative single case study research design. We collected data through interviewing and review of documents. We interviewed 10 doctoral program coordinators, three managers of research and graduate training and 13 PhD students we selected purposively. We reviewed seven institutional documents pertaining graduate training at Makerere University: two plans, three policies, one framework and one guideline. We used thematic data analysis to make sense of the data. The findings revealed that due to policy-practice gaps and funding constraints, mechanisms to enhance doctoral research production to facilitate uptake and use of doctoral research outputs beyond the academia were not adequately integrated into doctoral research training. This was shown by the lack of mechanisms to enhance doctoral research commissioning and execution, and gaps in priority setting. Opportunities for productive interactions between doctoral researchers and potential users were missed. As such, doctoral research outputs largely remained within the scholarly community. We recommend that the university should establish interface structures and co-creation spaces to leverage doctoral research commissioning, execution and priority setting to facilitate the uptake and use of doctoral research outputs beyond the scientific community.

The translation-to-policy learning cycle to improve public health.

Learning Health Systems (LHSs) have not directly informed evidence-based policymaking. The Translation-to-Policy (T2P) Learning Cycle aligns scientists, end-users, and policymakers to support a repeatable roadmap of innovation and quality improvement to optimize effective policies toward a common public health goal. We describe T2P learning cycle components and provide examples of their application. The T2P Learning Cycle is based on the U.S. Department of Veterans Affairs (VA) Office of Research and Development and Quality Enhancement Research Initiative (QUERI), which supports research and quality improvement addressing national public health priorities to inform policy and ensure programs are evidence-based and work for end-users. Incorporating LHS infrastructure, the T2P Learning Cycle is responsive to the Foundations for Evidence-based Policymaking Act, which requires U.S. government agencies to justify budgets using evidence. The learning community (patients, providers, clinical/policy leaders, and investigators) drives the T2P Learning Cycle, working toward one or more specific, shared priority goals, and supports a repeatable cycle of evidence-building and evaluation. Core T2P Learning Cycle functions observed in the examples from housing/economic security, precision oncology, and aging include governance and standard operating procedures to promote effective priority-setting; complementary research and quality improvement initiatives, which inform ongoing data curation at the learning system level; and sustainment of continuous improvement and evidence-based policymaking. The T2P Learning Cycle integrates research translation with evidence-based policymaking, ensuring that scientific innovations address public health priorities and serve end-users through a repeatable process of research and quality improvement that ensures policies are scientifically based, effective, and sustainable.

Linguistic Strategies, Code Choices, and Teaching Methods Among EFL Learners to Overcome Language Friction

When experiencing language friction, English as Foreign Language (EFL) learners use several linguistic strategies to maintain the continuity of their utterances. This phenomenon has an impact on the code choice taken by those EFL learners. This research aims to reveal: (1) linguistic strategies used among EFL learners when experiencing language friction, (2) EFL learners’ code choices when experiencing language friction, and (3) language teaching methods used to help English learners overcome language friction. Conducted in an English language education study program at a university in Indonesia, this research applied the qualitative descriptive method, and involved 4 students and 2 lecturers as participants. Data was collected using observation and interviews. Data were analyzed using procedures proposed by Creswell (2013), including data management, reading and providing memos, describing, classifying, interpreting data, visualization, and representation. This study found: (1) linguistic strategies that EFL learners used to maintain the continuity of their utterances when experiencing language friction were unlexicalized fillers, lexicalized fillers, excessive repetition of a word, lengthening a word, pauses, and code-switching, (2) code choices among EFL learners were code-alternation dan code-mixing, and (3) language teaching methods used to help EFL learners overcome language friction were implementing holistic learning, practicing relevant communicative contexts, encouraging active involvement in the English language community, using technology and digital media in learning, implementing a multilingual approach, providing social and cultural support, and implementing effective training. Understanding of linguistic strategies and code choice in relation to language friction is substantial in English teaching methods because it facilitates communication, promotes learning and adaptation, supports social interaction, and encourages strategic thinking.

Graph-Based Similarity of Deep Neural Networks

Understanding the enigmatic black-box representations within Deep Neural Networks (DNNs) is an essential problem in the community of deep learning. An initial step towards tackling this conundrum lies in quantifying the degree of similarity between these representations. Various approaches have been proposed in prior research, however, as the field of representation similarity continues to develop, existing metrics are not compatible with each other and struggling to meet the evolving demands. To address this, we propose a comprehensive similarity measurement framework inspired by the natural graph structure formed by samples and their corresponding features within the neural network. Our novel Graph-Based Similarity (GBS) framework gauges the similarity of DNN representations by constructing a weighted, undirected graph based on the output of hidden layers. In this graph, each node represents an input sample, and the edges are weighted in accordance with the similarity between pairs of nodes. Consequently, the measure of representational similarity can be derived through graph similarity metrics, such as layer similarity. We observe that input samples belonging to the same category exhibit dense interconnections within the deep layers of the DNN. To quantify this phenomenon, we employ a motif-based approach to gauge the extent of these interconnections. This serves as a metric to evaluate whether the representation derived from one model can be accurately classified by another. Experimental results show that GBS gets state-of-the-art performance in the sanity check. We also extensively evaluate GBS on downstream tasks to demonstrate its effectiveness, including measuring the transferability of pretrained models and model pruning.

Graph Contrastive Learning for Tracking Dynamic Communities in Temporal Networks

Graph Contrastive Learning for Tracking Dynamic Communities in Temporal Networks

Post Earthquake House Reconstruction Management Based On Community Participation of Monggang Srihardono Pundong Village of Bantul City Yogyakarta

Abstract Earthquakes are natural disasters that often cause severe damage to infrastructure, including buildings and houses without exception. Srihardono Pundong Village, Bantul, Yogyakarta is one of the areas where many buildings are found flat to the ground, so it is important to carry out effective reconstruction management. to restore affected areas. The problems faced are limited community participation and limited knowledge and skills regarding disasters and their management. The methodology used in this research is qualitative through interviews, sampling and ending with data analysis. The approach applied is community participation-based reconstruction management where local communities are actively involved in the process of planning, implementing and supervising the reconstruction of houses and infrastructure. The results of this research are in the form of maximizing the role of the community and direct learning to all communities about simple building reconstruction.

Developing a Text‐Based Measure of Humility in Inquiry Using Computational Grounded Theory

ABSTRACTWe describe a project in which we develop a text‐based measure of HI in the context of scholarly communication using corpora of scientific publications. The data and analytic approach we use will circumvent known concerns with self‐reported data on humility levels and will be calculable on a large scale. We use a computational grounded theory approach to develop a text‐based measure of HI. We draw from an annotated corpus of scientific articles in economics, psychology, and sociology (2010–2023), generating three supra‐dimensions of HI (Epistemic, Rhetorical, and Transparent) and several novel sub‐codes of HI. We present our initial analysis with a focus on the three dimensions of HI derived from a computational grounded theory approach. The text‐based measure helps us better understand how contextual factors shape HI and contribute to mixed methods in information science research.

Sharing Model of Care Innovations: The American Organization for Nursing Leadership Learning Community

Sharing Model of Care Innovations: The American Organization for Nursing Leadership Learning Community

Split-Level Evolutionary Neural Architecture Search With Elite Weight Inheritance.

Neural architecture search (NAS) has recently gained extensive interest in the deep learning community because of its great potential in automating the construction process of deep models. Among a variety of NAS approaches, evolutionary computation (EC) plays a pivotal role with its merit of gradient-free search ability. However, a massive number of the current EC-based NAS approaches evolve neural architectures in an absolutely discrete manner, which makes it tough to flexibly handle the number of filters for each layer, since they often reduce it to a limit set rather than searching for all possible values. Moreover, EC-based NAS methods are often criticized for their inefficiency in performance evaluation, which usually requires laborious full training for hundreds of candidate architectures generated. To address the inflexible search issue on the number of filters, this work proposes a split-level particle swarm optimization (PSO) approach. Each dimension of the particle is subdivided into an integer part and a fractional part, encoding the configurations of the corresponding layer, and the number of filters within a large range, respectively. In addition, the evaluation time is greatly saved by a novel elite weight inheritance method based on an online updating weight pool, and a customized fitness function considering multiple objectives is developed to well control the complexity of the searched candidate architectures. The proposed method, termed split-level evolutionary NAS (SLE-NAS), is computationally efficient, and outperforms many state-of-the-art peer competitors at much lower complexity across three popular image classification benchmark datasets.

Innovative ongoing support within a multifaceted computational thinking professional learning program improves teachers’ self-efficacy and classroom practices

In-service elementary school teachers need training to teach computational thinking (CT). A common model for CT professional learning programs includes an initial workshop followed by ongoing support. However, little research has examined the efficacy of ongoing support, the most effective types, and its impact on classroom practices. The current study details a multifaceted CT professional learning program with innovative ongoing support to help elementary school teachers implement the Code.org curriculum. It also empirically investigated the impact of the support on teachers' self-efficacy in coding and teaching CT, the effectiveness of each component of the support, and to what extent it affected teachers' classroom practices. Our ongoing support included an additional workshop, grade-level professional learning community (PLC) sessions, instructional videos, and teacher leaders’ support. Data included a pre-survey, four post-surveys, lesson observations, a focus group interview, tracking the number of video views, and surveys from PLC participants and teacher leaders. Results indicated that the ongoing support significantly increased teachers’ self-efficacy in coding and teaching CT. Regarding the effectiveness of the various components of the ongoing support, the additional workshop significantly increased teachers’ self-efficacy in coding and teaching CT. Teachers valued each component of the support, and this support improved teachers’ classroom practices.

Denoising diffusion probabilistic models for generative alloy design

Inverse material design is an extremely challenging optimization task made difficult by, in part, the highly nonlinear relationship linking performance with composition. Quantitative approaches have improved significantly owing to advances in high throughput experimentation and computational thermodynamics. However, existing physics-based tools are mostly forward models; input a chemistry and obtain a prediction. More recently the materials community has leveraged advances in the machine learning community to establish novel inverse design frameworks. Very recently denoising diffusion probabilistic models have been shown to be extremely powerful generators producing synthetic data of various modalities e.g. images, text, audio, tables, etc.. In this work a novel framework for alloy design and optimization is proposed leveraging these class of models. Five key generative tasks are demonstrated (1) unconditional generation (2) composition conditioned generation (3) property conditioned generation (4) multi-feedstock conditioned generation and (5) generative optimization. These methods were tested on three case studies: high entropy alloy design, superalloy binder jet additive manufacturing, and in-situ dual-feedstock wire-arc additive manufacturing. Results indicate that the established models are extremely flexible, expressive, and robust. The architecture’s flexibility and training procedure empower the model to learn complex intra-compositional and composition-property relationships. Furthermore, the probabilistic nature of these models makes them well suited for addressing solution non-uniqueness and tackling uncertainty quantification tasks. While the fidelity and quantity of the underlying training data is paramount, we envision that future alloy design frameworks will make extensive use of these kinds of machine learning models as “search” tools bolstering the utility of experimental and computational approaches.