Interpretive Approach Research Articles

An interpretable artificial intelligence approach to differentiate between blastocysts with similar or same morphological grades

Abstract STUDY QUESTION Can a quantitative method be developed to differentiate between blastocysts with similar or same inner cell mass (ICM) and trophectoderm (TE) grades, while also reflecting their potential for live birth? SUMMARY ANSWER We developed BlastScoringNet, an interpretable deep-learning model that quantifies blastocyst ICM and TE morphology with continuous scores, enabling finer differentiation between blastocysts with similar or same grades, with higher scores significantly correlating with higher live birth rates. WHAT IS KNOWN ALREADY While the Gardner grading system is widely used by embryologists worldwide, blastocysts having similar or same ICM and TE grades cause challenges for embryologists in decision-making. Furthermore, human assessment is subjective and inconsistent in predicting which blastocysts have higher potential to result in live birth. STUDY DESIGN, SIZE, DURATION The study design consists of three main steps. First, BlastScoringNet was developed using a grading dataset of 2760 blastocysts with majority-voted Gardner grades. Second, the model was applied to a live birth dataset of 15 228 blastocysts with known live birth outcomes to generate blastocyst scores. Finally, the correlation between these scores and live birth outcomes was assessed. The blastocysts were collected from patients who underwent IVF treatments between 2016 and 2018. For external application study, an additional grading dataset of 1455 blastocysts and a live birth dataset of 476 blastocysts were collected from patients who underwent IVF treatments between 2021 and 2023 at an external IVF institution. PARTICIPANTS/MATERIALS, SETTING, METHODS In this retrospective study, we developed BlastScoringNet, an interpretable deep-learning model which outputs expansion degree grade and continuous scores quantifying a blastocyst’s ICM morphology and TE morphology, based on the Gardner grading system. The continuous ICM and TE scores were calculated by weighting each base grade’s predicted probability and summing the predicted probabilities. To represent each blastocyst’s overall potential for live birth, we combined the ICM and TE scores using their odds ratios (ORs) for live birth. We further assessed the correlation between live birth rates and the ICM score, TE score, and the OR-combined score (adjusted for expansion degree) by applying BlastScoringNet to blastocysts with known live birth outcomes. To test its generalizability, we also applied BlastScoringNet to an external IVF institution, accounting for variations in imaging conditions, live birth rates, and embryologists’ experience levels. MAIN RESULTS AND THE ROLE OF CHANCE BlastScoringNet was developed using data from 2760 blastocysts with majority-voted grades for expansion degree, ICM, and TE. The model achieved mean area under the receiver operating characteristic curve values of 0.997 (SD 0.004) for expansion degree, 0.903 (SD 0.031) for ICM, and 0.943 (SD 0.040) for TE, based on predicted probabilities for each base grade. From these predicted probabilities, BlastScoringNet generated continuous ICM and TE scores, as well as expansion degree grades, for an additional 15 228 blastocysts with known live birth outcomes. Higher ICM and TE scores, along with their OR-combined scores, were significantly correlated with increased live birth rates (P < 0.0001). By fine-tuning, BlastScoringNet was applied to an external IVF institution, where higher OR-combined ICM and TE scores also significantly correlated with increased live birth rates (P = 0.00078), demonstrating consistent results across both institutions. LIMITATIONS, REASONS FOR CAUTION This study is limited by its retrospective nature. Further prospective randomized trials are required to confirm the clinical impact of BlastScoringNet in assisting embryologists in blastocyst selection. WIDER IMPLICATIONS OF THE FINDINGS BlastScoringNet provides an interpretable and quantitative method for evaluating blastocysts, aligned with the widely used Gardner grading system. Higher OR-combined ICM and TE scores, representing each blastocyst’s overall potential for live birth, were significantly correlated with increased live birth rates. The model’s demonstrated generalizability across two institutions further supports its clinical utility. These findings suggest that BlastScoringNet is a valuable tool for assisting embryologists in selecting blastocysts with the highest potential for live birth. The code and pre-trained models are publicly available to facilitate further research and widespread implementation. STUDY FUNDING/COMPETING INTEREST(S) This work was supported by the Vector Institute and the Temerty Faculty of Medicine at the University of Toronto, Toronto, Ontario, Canada, via a Clinical AI Integration Grant, and the Natural Science Foundation of Hunan Province of China (2023JJ30714). The authors declare no competing interests. TRIAL REGISTRATION NUMBER N/A.

Abstract 2508: A multiscale framework combining mechanistic models and LSTM-GCN networks for predicting drug sensitivity

Abstract Understanding tumor evolution and treatment resistance requires an integrative approach that combines cellular dynamics with molecular interactions. While mechanistic models excel in capturing physiological processes and predicting behaviors beyond the original data, their specificity limits their generalizability. Conversely, deep learning enables universal predictions but often lacks interpretability, posing challenges for application in cancer research. To address these limitations, we propose a novel computational framework that integrates mechanistic simulations, graph-based modeling, Long Short-Term Memory (LSTM) networks, and Bayesian inference to predict the sensitivity of six cancer types to targeted therapies, chemotherapy agents, immunotherapies, and their combinations. In this framework, mechanistic models provide an individualized baseline simulation for different cancer types, while deep learning integrates these outputs with drug-related information to generate robust and interpretable predictions tailored to specific types. Our hybrid framework leverages a mechanistic pan-cancer model that simulates molecular signaling pathways, cell cycle dynamics, and apoptosis across four biological compartments. The model is parameterized using published gene expression profiles and mutation data from xenograft models, including key mutations such as KRAS, EGFR, and TP53. Simulations are performed for six cancer types, including breast carcinoma, colorectal cancer, and pancreatic carcinoma, to approximate patient-specific tumor biology. Tumor cell populations generated from these simulations are represented as graphs, with each node corresponding to an individual cell characterized by proliferation status and dynamic molecular states (e.g., protein concentrations and phosphorylation levels). Edges are weighted and defined based on molecular similarity between cells. The graph is processed using a Graph Convolutional Network (GCN), which generates embeddings that capture tumor population heterogeneity. These embeddings are then fed into an LSTM to extract the temporal dynamics of the tumor population. The final hidden states computed by the LSTM are further combined with embeddings of drug chemical structure and drug-target interactions to make drug sensitivity predictions. To enhance the robustness of predictions, Bayesian inference is incorporated to quantify uncertainty in estimated drug responses. This framework bridges the gap between mechanistic modeling and machine learning, offering a scalable and interpretable approach to studying tumor evolution under the selective power of drug treatment. By integrating the physiological insights of mechanistic models with the predictive power of deep learning, it enables the identification of molecular drivers of resistance and informs the development of personalized therapies. Citation Format: Chenhui Ma, Evren Gurkan-Cavusoglu. A multiscale framework combining mechanistic models and LSTM-GCN networks for predicting drug sensitivity [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 2508.

Recognizing and Addressing Health Care Barriers for Transgender and Nonbinary People Living With a Chronic Illness or Disability.

This paper explores the health care experiences of individuals who are transgender and/or nonbinary (TGNB) and live with a chronic illness and/or disability (CI/D). Using an interpretivist epistemological worldview and an intersectional lens, the research team explored the compounded barriers faced by this patient population and propose solutions for improving their care. The study conducted in-depth interviews with TGNB individuals who self-identified as having a CI/D to understand their health and health care experiences. The interdisciplinary research team, which includes individuals with diverse backgrounds and experiences related to gender identity and CI/D, analyzed the data thematically using an iterative interpretive approach. Participants described barriers such as diagnostic overshadowing and provider skepticism that were exacerbated by their dual TGNB-CI/D identities. Participants interacted with health care systems frequently due to ongoing medical needs, which increased the likelihood of negative encounters like misdiagnosis, inappropriate questioning related to their gender identity, and skepticism of their CI/D. Gaslighting experiences further eroded trust in health care providers and contributed to health care inequities. The lack of LGBTQ+ competent care, coupled with discriminatory attitudes, led some participants to forgo seeking essential health care services altogether. Participants identified several strategies to mitigate barriers, including advocating for LGBTQ+ competent care through provider education and training; structural changes to address financial barriers and insurance issues; leveraging telehealth services; and increasing community support networks. By enacting the suggested actionable solutions, which were grounded in participants' voices and experiences, the health care system can reduce disparities and provide better, more affirming health care to this group.

Investigating block teaching at Hasselt University: benefits and challenges for disadvantaged students

ABSTRACT Evidence suggests that a block model curriculum in higher education can support learning for students from disadvantaged backgrounds. However, previous research, predominantly quantitative, has not specified how this contribution happens and suggests that the improvement in learning could also be attributed to the simultaneous implementation of student-centred pedagogy. This paper aims to address this gap by investigating at a deeper level the specific circumstances under which block teaching can offer advantages and limitations for disadvantaged students. We conducted seventeen in-depth interviews with students from Hasselt University and analysed their narratives using an interpretative phenomenological approach. Our findings support previous quantitative studies indicating that the block model can indeed enhance opportunities for students from disadvantaged backgrounds. The fast feedback enables students to adjust their study methods early on, the structured schedule facilitates the development of time management and academic skills, and the decreased workload during exams gives students time to address educational gaps. However, disadvantaged participants state that it is important to consider increases in stress levels due to inadequate curriculum design, lack of inclusive feedback mechanisms, and insufficient rest time between blocks. Moreover, findings suggest that the block model may be especially beneficial for supporting disadvantaged students in the first year. This study provides insights that contribute to the development of more inclusive curricula and enhanced student support by highlighting specific mechanisms through which the block model can influence learning experiences.

NITEO: A qualitative study of a supported education program for students experiencing disruptions to their college education because of a mental health condition.

The rates and severity of mental health conditions among young adults are troublesome. Mental health conditions among college students impact educational attainment, future employment and earnings, as well as quality of life. Our objective was to assess students' experience and perceptions of the core components of NITEO, a college reentry program designed to assist young adults who have dropped out of or taken a leave of absence from college. We conducted a qualitative study of the core components of NITEO, employing an applied interpretive approach and conducting semistructured interviews with 31 former NITEO students. Data were examined using thematic analysis. Analyses revealed four themes: (a) NITEO catalyzes personal growth and connection, (b) coaching builds skills and promotes accountability, (c) peer mentors are supportive role models, and (d) other students in the program impact the program experience. These findings suggest that the different components of NITEO foster skills and resilience while providing a supportive community. Our study illuminates the potential of programs such as NITEO to facilitate recovery and return to college for students on leave or who have dropped out due to mental health conditions. (PsycInfo Database Record (c) 2025 APA, all rights reserved).

Simple Fermionic backflow states via a systematically improvable tensor decomposition

Strongly correlated electrons give rise to an array of electronic properties increasingly exploited in many emerging materials and molecular processes. However, the reliable numerical simulation of this quantum many-body problem still poses an outstanding challenge, in particular when accounting for the fermionic statistics of electrons. In this work, we introduce a compact and systematically improvable fermionic wave function based on a CANDECOMP/PARAFAC (CP) tensor decomposition of backflow correlations in second quantization. This ansatz naturally encodes many-electron correlations without the ordering dependence of other tensor decompositions. We benchmark its performance against standard models, demonstrating improved accuracy over comparable methods in Fermi-Hubbard and molecular systems and competitive results with state-of-the-art density matrix renormalization group (DMRG) in ab initio 2D hydrogenic lattices. By considering controllable truncations in the rank and range of the backflow correlations, as well as screening the local energy contributions for realistic Coulomb interactions, we obtain a scalable and interpretable approach to strongly correlated electronic structure problems that bridges tensor factorizations and machine learning-based representations.

Ukhuwah and succession questions of an Indonesian Muslim’s family business

Purpose The purpose of this paper is to explore the practice of ukhuwah, that is, the bond of brotherhood in Islam, from a Muslim’s family business and further probes its role in the succession questions for a family business. Design/methodology/approach This paper uses qualitative research method. The primary data was gathered from a single case study of a family business in Makassar, Sulawesi, Indonesia. Open interview and direct observation were mainly engaged in data collection, complemented by data from Facebook posts and WhatsApp status of the family business owners. Findings The interpretative approach reveals how ukhuwah has been practiced in the family business and how the practice supports the business sustainability during the recent COVID-19 pandemic. The finding of this study draws the inclusion of Islamic value within small business practices in the debates of succession question of family business. Research limitations/implications The generalisability of the finding is limited to the single case study of family business in Makassar, Sulawesi, Indonesia. Originality/value To the best of the authors’ knowledge, this study may be the first to draw evidence from a single case study of a Muslim’s family business in Indonesia, probing ukhuwah within succession questions of family business.

Exploring the role of embodiment in the production and experience of wild atmospheres in nature

Embodied and emotional experiences are heightened in encounters with nature, especially in blue spaces. Thus, drawing on the works of Husserl and Merleau-Ponty, we analyse the role of the body in the production and experience of wild atmospheres through the practice of wild swimming in natural blue spaces. Using an interpretive approach involving interviews and ethnographic observations with forty-six wild swimmers, our analysis foregrounds embodiment and illuminates the central role of the body in the relational production and experience of atmospheres in nature. In so doing, we extend current understandings of embodiment by advancing a granular account of the emergence of ‘wild swimming atmospheres’ produced and experienced haptically and somatically through intimate and personal connections and entanglements between human bodies and natural surroundings. The paper concludes with suggestions for exploring embodied haptic and somatic experiences in other consumption contexts within natural settings.

On the Road to Transformation: How Self-Drive Tourism Transforms Travelers

Self-drive tourism, with its emphasis on traveler autonomy, independence, and engagement, plays a critical role in facilitating personal transformation. This study examines the transformative effects of self-drive tourism on travelers. Building on the concepts of experience and transformation economies, it highlights how tourism can transcend providing emotional experiences to foster deeper lifestyle transformations. In recent years, research on this topic has been conducted under the umbrella of transformational tourism. Tourism types such as volunteer tourism and studying abroad transform tourists through diverse experiences at their destinations. However, transformational tourism in the context of travel experiences between destinations remains underexplored. This study adopts a descriptive and interpretive narrative approach, using a semi-structured interview survey for data collection and analysis. The findings identify key factors driving tourist transformation: spontaneity, novel experiences, challenges, cultural shocks, and deep interpersonal connections formed during the journey. Notably, the confined space of cars in self-drive tourism promotes reflection, communication, and problem-solving, which are essential for sparking self-transformation. Additionally, traveling to multiple destinations provides continuous opportunities for reflection and learning, creating a cycle of action that supports ongoing personal transformations. The study further reveals that independence, problem-solving skills (such as handling car trouble or navigating unfamiliar routes), and interactions with travel companions significantly contribute to self-improvement. These experiences are closely tied to tourists’ pursuit of authenticity, which amplifies their transformation by the journey’s end. The findings contribute to the implementation of transformational tourism by identifying the mechanisms facilitating transformation in self-drive tourism. These insights are crucial for developing targeted marketing strategies aimed at consumers seeking not only adventure but also meaningful, transformative experiences. By understanding the factors that promote personal transformation, tourism providers can create authentic and engaging offerings to meet the growing demand for transformation-driven tourism.

From margin to center: positioning centers for teaching and learning as strategic partners in Israeli higher education

Abstract Centers for teaching and learning (CTLs) increasingly influence teaching quality in higher education, yet their operational dynamics remain understudied in specific national contexts. This study examines the evolution of CTLs in Israeli higher education from peripheral support units to strategic institutional partners, analyzing their operations through leadership perspectives and organizational relationships. Using an interpretive phenomenological approach, the study analyzed data from semi-structured interviews with 31 CTL directors (77.5% of Israeli CTLs), nine former directors, and five national stakeholders. Three critical patterns emerged: (a) a significant “recognition-resources gap” where institutional appreciation does not translate into operational support (77.4% of directors); (b) distinct faculty engagement dynamics characterized by veteran resistance (71%) and consistent early-adopter groups (10–15%); and (c) enhanced crisis response capabilities demonstrated during the COVID-19 pandemic (87.1%). These patterns informed the development of the CTL operational–impact Framework, integrating structural, professional, and relational dimensions of CTL operations. This study advances CTL literature by providing an integrated framework for understanding how these centers navigate institutional complexities while maintaining effectiveness. The findings suggest the need for formal funding mechanisms aligned with institutional recognition, differentiated faculty engagement strategies, and systematic approaches to crisis response. As the first comprehensive examination of CTL operations in Israeli higher education, this research illuminates how teaching centers evolve within specific national contexts while responding to global challenges, offering insights for analyzing CTL operations worldwide.

Research on Flood Forecasting in the Pa River Basin Based on the Xin’anjiang Model

This study explores flood forecasting in the Pa River basin, a major tributary of the Beijiang River in South China, by integrating the Xin’anjiang hydrological model with the Shuffled Complex Evolution-University of Arizona (SCE-UA) algorithm for parameter calibration. Fifteen observed flood events from April to August 2024 were employed in this study, with twelve events used for model calibration and the remaining three for validation. Additionally, to assess model performance under extreme conditions, a 50-year return period flood event from June 2020 was incorporated as a supplementary validation case. The calibrated model reproduced flood hydrographs with high accuracy, achieving Nash–Sutcliffe Efficiency (NSE) values of up to 0.98, relative peak discharge errors generally within ±10%, and peak timing deviations under 3 h. The validation results demonstrated consistent performance across both typical and extreme events, indicating that the proposed framework provides a feasible and physically interpretable approach for flood forecasting in data-limited catchments.

Reconstructing the complete force-deformation response envelope for unreinforced masonry walls using self-supervised learning

This article introduces an interpretable data-driven approach to reconstructing the complete force-deformation response envelope (backbone curve) of unreinforced masonry (URM) walls using the structural properties as inputs. The framework utilizes supervised and unsupervised learning combined with autoencoder neural networks. The dataset used to develop the predictive model includes crack texture images, design, and mechanical properties, as well as the backbone curves associated with 165 brick and block URM walls subjected to quasi-static cyclic loading. Most of the walls in the experimental database experienced hybrid failure modes. Therefore, autoencoder networks are used to extract informative features from the backbone curves, which are incorporated into an unsupervised learning model to identify potential failure modes. A representative backbone curve (or baseline backbone) is then formulated for each failure mode. The recorded force-deformation response for each test specimen is then decomposed into a combination of the scaled baseline backbones. Finally, the supervised learning model is used to establish a relationship between the participation weights of each baseline backbone (the output) and the wall properties (the input). Manual labeling is also conducted to validate the results obtained from the clustering models, ensuring that the most likely failure mode is assigned to each URM wall. Unlike conventional codes and standards which estimate specific points along the backbone curve, the proposed model reconstructs the complete backbone curve given the mechanical and design properties of the wall with an accuracy level that exceeds 90% in both the test and train datasets.

The invisibility of anxiety in young, traumatised South African children

The high prevalence of anxiety in young traumatised children has been well established in literature. However, the body of literature that explores how anxiety manifests in classroom settings in the South African context is still growing. The ways in which it presents at the personal level for individual children, in particular, need to be examined in greater depth. The current study posed the question, ‘How does anxiety manifest in young, traumatised South African children in classroom settings?’ The researchers adopted an interpretive phenomenological approach and used a combination of intervention and vignette research. Data were collected from individualised, intuitive, and integrative psychotherapeutic processes. Primary participants ( n = 5) ranged in ages from 8 to 14 years, while secondary participants included parents and teachers. An analysis of parental and teacher interviews as well as vignettes for each participant revealed high levels of anxiety invisibility in classroom settings for all the study participants. This finding was triangulated from the teacher interviews, parental interviews, therapeutic engagement, and vignettes. The study identified the need for capacity development in teachers in terms of mental health and wellbeing, and recommended that additional support mechanisms be provided for young, traumatised children suffering from anxiety.

BoolXAI: Explainable AI Using Expressive Boolean Formulas

In this tool paper, we design, develop, and release BoolXAI, an interpretable machine learning classification approach for Explainable AI (XAI) based on expressive Boolean formulas. The Boolean formula defines a logical rule with tunable complexity according to which input data are classified. Beyond the classical conjunction and disjunction, BoolXAI offers expressive operators such as AtLeast, AtMost, and Choose and their parameterization. This provides higher expressiveness compared to rigid rules- and tree-based approaches. We show how to train BoolXAI classifiers effectively using native local optimization to search the space of feasible formulas. We provide illustrative results on several well-known public benchmarks that demonstrate the competitive nature of our approach compared to existing methods. Our work is embodied in the open-source BoolXAI library with a high-level user interface to serve researchers and practitioners. BoolXAI can be used either as a standalone interpretable classifier or for post-hoc explanations of other black-box models or observed behavior. We highlight several desirable benefits of our tool, especially in industrial settings where rapid experimentation, reusability, reproducibility, deployment, and maintenance are of great interest. Finally, we showcase a deployed service powered by BoolXAI as an enterprise application.

"Call-it-in": addressing older informal caregivers' support needs during the COVID-19 pandemic in Aotearoa New Zealand.

This study aims to address the knowledge gap in older informal caregivers' support needs by exploring their caregiving experiences during the COVID-19 pandemic in Aotearoa New Zealand. It proposes a conceptual solution termed "call-it-in". An interpretative qualitative approach was employed, and we conducted in-depth interviews with 81 informal caregivers. Data were analysed using thematic analysis to identify key themes related to participants' support needs. The study found that many participants were disconnected from formal health systems, peer support groups and community organisations, leading to uncertainty about available support systems. Despite the availability of resources and information online, many participants preferred more traditional forms of communication such as phone helplines due to greater familiarity and the emotional support provided by speaking with someone directly. The findings highlight the critical need for a centralised support system, which we term "call-it-in", to provide a single point of contact for accessing information and connecting users to various forms of existing/emergent support. This system aims to enhance informal caregivers' social capital during crises like the pandemic. Implementing "call-it-in" could improve the accessibility and visibility of support services, meeting the actual needs of older informal caregivers and reducing their reliance on personal networks and resources.

Resettled refugee parent and young adult perspectives on mental health after the onset of the COVID-19 pandemic

BackgroundRefugees and other New Americans faced unique mental health barriers before and during the COVID-19 pandemic. Reduced access to mental health supports and services in this population indicates a need for new community-based mental health interventions.AimsThis paper explored refugee parents’ and young adults’ perceptions of the mental health barriers and facilitators encountered by young resettled refugees (ages 10–24) and their parents.MethodsUsing an interpretive phenomenology approach and a form of community-based participatory research (CBPR), we designed a focus group guide with student community members from various refugee and immigrant communities. We held eight gender- and language-concordant focus groups with refugee parents, and four gender-concordant focus groups with refugee young adults (18–24), facilitated by student community members. Translated transcripts were analyzed for major themes using an iterative emergent thematic coding approach.ResultsThe conversations in these focus groups were wide-ranging. Here we explore the themes and subthemes that emerged in three primary areas: the effects of COVID-19 on mental health, mental health stigma and other social barriers to mental health, and community strengths and strategies for addressing mental health.ConclusionsCOVID-19 surfaced and intensified existing mental health challenges within resettled refugee communities. Community-based mental health interventions should be designed in partnership with the communities they aim to serve. The findings of this study suggest several possible intervention points to support refugee youth and parent mental health, including culturally sensitive group and individual therapy in a trusted community setting.

Diverse approaches: educator-centric insights into design thinking practices in entrepreneurship education

PurposeDesign thinking (DT) has emerged in a variety of educational contexts within entrepreneurship and debate continues on the value of integrating DT into entrepreneurship education (EE). Although DT is increasingly recommended for EE practice (Baciagalupo et al., 2020), there are scarce insights into how entrepreneurship educators apply and/or integrate DT into their practice. This study uses a constructivist paradigm of education to answer questions about the educational practice when integrating DT, with a view to understanding the schema that educators construct when encouraging learners to construct their own knowledge.Design/methodology/approachThis study follows a qualitative, interpretive approach, drawing upon semi-structured interviews from 29 entrepreneurship educators from higher education in the UK and Europe. Thus, this study puts focus on the quality of the DT integration in EE – from an educator’s perspective.FindingsThere exists a difference between the scholarly proposed integration of DT and the enacted practice within the classroom. Analysis identified four forms (selective, idea-centric, procedural and holistic) of DT integration in the context of EE, as well as insights into the practical barriers and motivations for utilizing DT. In particular, this study has identified an opportunity for appropriate training of the educators to extend their awareness of the principles of DT.Originality/valueThis research has identified four novel and distinct ways in which DT can be integrated with(in) EE. This allows educators to be more reflexive about why and how they utilize DT in their classrooms, addressing an apparent lack of this understanding in contemporary practice.

Representation of Local Cultural Wisdom in the Kuta Beach Mini Festival in the Kuta Badung Traditional Village

Purpose: This article aims to revive local cultural wisdom in the Kuta Traditional Village which has been eroded by the influence of globalization Research methods: This research uses an interpretive qualitative approach by collecting data through field observations, interviews and literature reviews Results and discussion: The Kuta Beach Mini Festival is able to create a space for the people of Kuta Badung Traditional Village to strengthen their sense of cultural identity, through dance, music, fine arts and various traditional activities and revive cultural elements that are in danger of being forgotten. Implication: This article has substantial cultural implications by illustrating how the representation of local cultural wisdom in festivals can influence cultural preservation, revolution, and understanding.

Going green or staying grey: modelling the factors of green tech product purchase behaviour through interpretive structural modelling and MICMAC approach

Purpose This study aims to investigate the factors driving consumer behaviour in green tech product purchases and aims to develop a framework by analysing their hierarchical and contextual interactions. Design/methodology/approach The study employed interpretive structural modelling (ISM), drawing on insights from experienced academicians and marketing professionals. To analyse the driving forces and interdependencies among these factors, a Matrice d’Impacts Croises Multiplication Appliques a un Classement (MICMAC) analysis was conducted. Findings The MICMAC analysis revealed that no variables were classified as autonomous determinants, highlighting the significance of all factors. Green attitude and purchase behaviour were identified as dependent determinants with high reliance and moderate influence. Subjective norm and perceived behavioural control were categorised as linkage determinants, showing significant influence and moderate dependence, while environmental knowledge, concern and product availability were noted as independent variables with strong driving power and lower dependence. Practical implications The findings offer actionable strategies for managers to influence green tech product purchase behaviour by focusing on consumer education and transparent pricing. By understanding the hierarchical relationships between determinants, businesses can tailor their marketing strategies to effectively foster green attitudes and address factors driving purchase behaviour. Policymakers can use these insights to create regulations and incentives that promote green tech adoption, such as supporting eco-friendly practices and increasing consumer education, which can drive greater acceptance and sustainability in the green tech market. Originality/value Our study addresses a critical void in the literature by applying ISM and MICMAC to explore the hierarchical and relational dynamics of determinants influencing green tech product purchases. Our study also provides a novel perspective on these factors and their interactions. It also offers valuable insights into green tech product purchase behaviour (GTPB) and advances the field’s understanding.

Heat Capacity of Ionic Liquids: Toward Interpretable Chemical Structure-Based Machine Learning Approaches.

This study focuses on predicting the heat capacity of pure liquid-phase ionic liquids (ILs) using machine learning models from various categories, including support vector machines, instance-based learning, ensemble learning, and neural networks, with linear regression serving as a baseline. A key aim of this work is not only to achieve accurate predictions but also to ensure the interpretability of the results, addressing a gap often overlooked in predictive modeling studies. To accomplish this, we curated and cleaned a comprehensive data set of 13,893 data points covering 322 ILs, using temperature and chemical structure-based features as inputs. We evaluated model performance and conducted a thorough interpretability analysis to reveal the patterns of the top-performing model's predictions, ensuring that they are understandable. All models outperformed the baseline, with XGBoost (eXtreme Gradient Boosting) from the ensemble learning category achieving the best results, with total RMSE, R2, and AARD (%) values of 11.389, 0.997, and 1.212%, respectively. Shallow neural networks also performed competitively, suggesting that complex deep learning architectures may not be necessary. Both 10-fold and leave-one-IL-out (LOILO) cross-validation further validated the robustness of these results. Importantly, the interpretability analysis identified key factors influencing heat capacity predictions, such as anion size (e.g., NTf2 and FAP) and alkyl chain length. These factors were validated by testing the model on previously unseen IL examples. Additionally, a user-friendly web application was developed to make predictions, allowing users to input chemical groups or select compounds from a predefined list of 1633 ILs. This study underscores the importance of combining diverse modeling approaches with robust interpretability techniques to achieve reliable and explainable predictions for IL heat capacity.