Active Learning Techniques Research Articles

Using text-scrolling to increase student engagement in the STEM classroom: a collaboration

The benefits of using active-learning approaches to increase student engagement and participation in the HE classroom are well known (Allsop et al., 2020). In STEM disciplines specifically, active-learning approaches can contribute to a reduction in achievement gaps for underrepresented students by promoting self-efficacy and a sense of belonging (Kovarik, Robinson and Wenzel, 2022). Despite these benefits, academics in those disciplines may be reluctant to adopt active learning for reasons such as lack of familiarity or more time spent in traditional, lecture-style delivery (Arnaud, 2021). This presentation reported on the outcome of a small-scale pedagogical innovation in one tutorial of a first-year undergraduate theory module in Chemistry. The aim was to increase students’ classroom engagement in the tutorial by using a text-mapping activity with scrolled research papers (Abegglen et al., 2019), with the additional benefit of introducing tutors to this active-learning technique. The transcript of a professional conversation between a Chemistry lecturer and Learning Developer discussing the approach along with slides outlining a typical session were circulated to tutors a week prior to the timetabled tutorial. Qualitative feedback from tutors was presented to indicate the success of the text-mapping activity as a way of increasing student engagement in the tutorial. Insights were also gained about tutors’ own perceptions of pedagogical value and confidence in adopting such approaches in future. Implications were presented for how the first-year tutorials might be redesigned to include more active learning, as well as how Learning Developers can work in collaboration with academic colleagues in STEM programmes.

Curricular Redundancy in Medical Undergraduate Course: Critical Insights from Various Stakeholders in Medical Institutes in India

Background Medical education is continuously evolving to keep pace with the dynamic field of medicine. This study addresses the issue of curricular redundancy in medical education, highlighting the necessity for periodic reviews to eliminate outdated or irrelevant topics. Method A descriptive qualitative approach was employed, involving participants from various medical schools across India. An online questionnaire was used to gather data on redundant topics, suggested replacements, and improvements in the curriculum for both didactic and non-didactic subjects, along with inputs related to assessment and evaluation methods. Content analysis was used for thematic identification and qualitative interpretation. Results Out of 71 respondents from a wide geographic distribution, 30% were female, and 70% were male, with an age range of 17 to 36 years. Participants expressed concerns about redundant theoretical (32%) and practical (51%) topics. Qualitative analysis highlighted the need for integrating different subjects and placing a stronger focus on practical clinical skills. Participants emphasized the importance of a curriculum that keeps pace with advancements in medicine, such as genomics and artificial intelligence, while also addressing mental health. Specifically, they suggested combining anatomy and surgery courses, incorporating more active learning techniques, and utilizing ongoing assessments to gauge progress. Conclusion The study highlights the necessity of eliminating curricular redundancy in medical education. Recommendations include developing a flexible curriculum, emphasizing region-specific content, and implementing a formative assessment system. Additionally, the importance of faculty development and stakeholder involvement in curriculum design is emphasized. Key Message Key insights for updating the medical undergraduate curriculum include the following:

EASE: An enhanced active learning framework for aspect-based sentiment analysis based on sample diversity and data augmentation

Aspect-Based Sentiment Analysis (ABSA) has received considerable attention in recent studies. Powerful pre-trained models were proposed which can be fine-tuned for many Natural Language Processing (NLP) tasks, including ABSA. However, fine-tuning these models needs a relatively large amount of labeled data. In this research, we propose EASE; an active learning framework to minimize manual labeling effort. We extend the active learning technique by incorporating the concept of sample diversity where similar samples are not selected for labeling. Furthermore, we maximize the utility of these samples by incorporating data augmentation. EASE was evaluated on three benchmark ABSA datasets from three different domains. The results show that the reduction of the number of needed labeled samples ranges from 88% to 94% among the three datasets while maintaining accuracy. Our results show that active learning is an effective approach to reduce manual labeling effort while maintaining comparable performance. Moreover, it is possible to reduce the number of labeled data even further by incorporating sample diversity and data augmentation while maintaining performance.

Construction of Al–Si interatomic potential based on Bayesian active learning

Nanoscale simulations for optimizing the performance and processing of Al–Si alloys are currently facing two major obstacles: the scarcity of high-quality semi-empirical potentials tailored to complex alloy systems, and the prohibitively high computational cost associated with ab initio molecular dynamics simulations. In order to enhance simulation efficiency and accuracy of the Al–Si alloys’ microstructural evolution, this study employs a dynamic active learning technique, FLARE, to develop a non-parametric machine learning potential that combines the high accuracy of density functional theory (DFT) with the efficiency of classical molecular dynamics (MD). Without relying on extensive initial ab initio molecular dynamics data or existing databases, collection of the necessary data is progressively made during the active learning process, thereby constructing a potential capable of accurately simulating the structure and dynamics of high-temperature Al–Si alloys. By comparing with experimental measurements and ab initio molecular dynamics calculations, the high accuracy and computational efficiency of this potential is demonstrated in predicting energy, force, structure, and dynamic properties. The results provide novel theoretical insights for optimizing Al–Si alloy processing and underscore the usefulness of active learning methods in constructing high-accuracy potentials.

Estimating high-resolution snow depth over the North Hemisphere mountains utilizing active microwave backscatter and machine learning

While ground meteorological stations provide accurate snow depth data, their limited spatial coverage results in observational gaps. Satellites offer long-term, large-scale observations, addressing these gaps. Existing snow depth retrieval algorithms mainly use passive microwave remote sensing data with a 25 km resolution, insufficient for capturing snow depth variability in mountainous areas. This paper introduces active microwave backscatter data and machine learning techniques for high-resolution snow depth estimation. We conducted a preliminary exploration of the relationship between Sentinel-1 backscatter coefficient σ0 and snow depth. Due to factors such as vegetation coverage and underlying soil properties, the relationship between σ0 and snow depth is complex and nonlinear. Consequently, six machine learning models were trained to learn this relationship using σ0 and auxiliary data as input features, with in-situ snow depth serving as the target variable. After extensive validation, the Extreme Random Trees (ERT) model was selected for its high accuracy and stability. Using the ERT model, we generated 500 m-resolution snow depth data for northern hemisphere mountains, then analyzed temporal snow depth variations and altitudinal stratification.

Development of a Natural Language Processing (NLP) model to automatically extract clinical data from electronic health records: results from an Italian comprehensive stroke center

IntroductionData collection often relies on time-consuming manual inputs, with a vast amount of information embedded in unstructured texts such as patients’ medical records and clinical notes. Our study aims to develop a pipeline that combines active learning (AL) and NLP techniques to enhance data extraction in an acute ischemic stroke cohort. Materials and methodsConsecutive acute ischemic stroke patients who received reperfusion therapies at IRCCS Humanitas Research Hospital were included. The Italian NLP Bidirectional Encoder Representations from Transformers (BERT) model was trained with AL to automatically extract clinical variables from electronic health text. Simulated active learning performances were evaluated on a set of labels representing patients’ comorbidities, comparing Bayesian Uncertainty Sampling by Disagreement (BALD) and random text selection. Prognostic models predicting patients’ functional outcomes using Gradient Boosting were trained on manually labelled and semi-automatically extracted data and their performance was compared. ResultsThe active learning process initially showed null performance until around 20% of texts were labelled, possibly due to root layers freezing in the BERT model, yet overall, active learning improves model learning efficiency across most comorbidities. Prognostic modelling showed no significant difference in performance between models trained on manually labelled versus semi-automatically extracted data, indicating effective prediction capabilities in both settings. ConclusionsWe developed an efficient language model to automate the extraction of clinical data from Italian unstructured health texts in a cohort of ischemic stroke patients. In a preliminary analysis, we demonstrated its potential applicability for enhancing prediction model accuracy.

PSVII-28 A comparative analysis on student learning using DNA barcoding in undergraduate biology courses

Abstract DNA barcoding is a growing field and is increasingly used to identify animal and plant specimens down to the species level. This type of molecular work is beneficial for animal science students for its use in identifying insect pests or bacterial infections. However, it is equally important for students outside of STEM concentrations to be exposed to molecular work to develop a better understanding of science and combat the growing distrust in science. The overall goal of this project was to train non-molecular biologists in DNA barcoding using active learning techniques. The objectives of the present study were to 1) expose two groups of students (BSCI145 and BSCI467) to molecular lab work, particularly DNA barcoding, 2) effectively communicate how molecular methods can be applied to ecological purposes, and 3) demonstrate that this molecular method can be used for university-level education at two scales. We hypothesized that students at both the 100 and 400 level would exit this experience with a proportionally deeper understanding of how DNA barcoding works and an appreciation for its applications as a result of the hands-on module. We did not expect there to be a significant barrier between the ability to learn this molecular method of 100 and 400 level students. To assess these hypotheses, students in both courses were given a survey at the beginning and end of the semester with the same or very similar questions to observe how their knowledge of DNA barcoding did or did not change. One semester of BSCI145 and 2 semesters of BSCI467 were sampled (n = 24 100 level students, n = 84 400 level students). Surveys were collected anonymously and evaluated using rubrics to assess “correctness”. An ANOVA revealed statistically significant effects from both the course level (P = 0.004) and the survey scores (P = 0.001), indicating that both course level and basal knowledge contribute to explaining the variance in learning. Additionally, Tukey HSD test results displayed students in BSCI 145 exhibited a significantly greater mean learning change when compared with both BSCI 467 2022 and BSCI 467 2023 (P = 0.008 and P = 0.006 respectively). Finally, a linear regression analysis displayed a significant negative relationship between pre-survey scores and mean learning change (β = -0.850, P = 0.001). This means that students with a greater initial learning reference point will not increase in learning as much when compared with students with a decreased initial learning reference point. In conclusion, we accept our hypotheses that students at different academic levels with different backgrounds can successfully learn molecular techniques when provided hands-on modules. This is relevant to education and extension when working with individuals who may not know hard science.

Manajemen Kurikulum Berbasis Pesantren untuk Membentuk Karakter Siswa di SMP Al-Azhar Menganti Gresik

The results of this study show that curriculum planning based on pesantren is carried out by involving several parties both from sekolah and from pesantren, namely education bureaus and leadership bureaus. At this stage of planning, the two bureaus designed the books that would be made referenced and studied in the Madrasa. Two methodologies are used in the implementation of learning: conventional methods such as bandongan and, when necessary, active learning techniques. Evaluation of the pesantren-based curriculum focuses on students' morality and discipline both at home and in the educational environment.

Improving Online Childbirth Education: A Role for Active Learning.

Teaching online poses unique challenges for keeping participants engaged. To enhance the effectiveness of virtual childbirth education, this article explores how active learning techniques can guide the design of online prenatal classes. Active learning involves encouraging class participants to process and engage with ideas as the instructor presents them in class, rather than just hearing about concepts through lectures. This article draws from pedagogical literature on active learning and applies its key components to the needs of childbirth instructors in an online setting. Specific recommendations for activities to involve participants and create lasting learning are also provided for synchronous online classes.

Building an Active Classroom Using the Active Learning Pedagogy Sequence

This paper is a practical how-to guide to help you start using active learning or to have greater success and more fun with it. We categorize active learning techniques as Think, Pair, Share, Composite, Group, Move, or Lead and discuss how to implement activities in each category, along with advice on creating engaging, effective, and equitable learning experiences. We introduce the Active Learning Pedagogy Sequence (ALPS) which orders these categories by difficulty and time for instructors and students. We believe both instructors' teaching skills and students' learning skills develop along the ALPS.

The study of an innovative Eéducationnel practice in Greek students: The flipped learning

The purpose of this paper is to compare the effectiveness of using flipped teaching against traditional teaching, with active learning techniques, in physics and mathematics courses. The study was conducted on 100 middle and high school students who were first subjected to traditional teaching (control group) and then subjected to flipped teaching (experimental group). To check the effectiveness of the two methods, the students were submitted to an assessment test in the lesson taught with the two methods. To test the existence of a statistically significant difference between the performance of the two groups, the independent sample t-test and ANOVA test were used for continuous variables. In addition, multiple logistic regression analysis with Odds Ratios was used to predict student achievement depending on the teaching method used. The results of the study showed that there is no statistically significant difference in the average performance of students with the two teaching methods.

Hands-on sustainability: designing an engaging undergraduate sustainable business course

Purpose This paper outlines the active learning methods used to develop and deliver a sustainable business course to undergraduate students. Moreover, the paper aims to investigate the effect of the sustainable business course on the students’ engagement in sustainable consumption. Design/methodology/approach From a pedagogical perspective, the paper describes the active learning methods applied in a newly introduced sustainable business course via numerous distinctive assessment techniques. On the empirical front, the research investigates the impact of the sustainable business course on the students’ engagement in sustainable consumption. To test such impact, an online survey was distributed among students who completed the sustainable business course, and as a control group for comparison, students who did not take the course. Findings The research results indicate a positive relationship between completion of the sustainable business course and engagement in sustainable consumption. Furthermore, the data revealed that female students exhibited more engagement in sustainable consumption than male students. Research limitations/implications The study contributes to the literature on student-centered pedagogy, active learning techniques and the relationship between sustainable business education and engagement with sustainable consumption. Practical implications The study contributes to the literature on student-centered pedagogy, active learning techniques and the relationship between sustainable business education and engagement with sustainable consumption. Pedagogically, the nonconventional course curricula and assessment methods described in this study can be used as a reference by instructors aiming to integrate active and experiential teaching methods into their sustainable business curricula. For decision makers in higher education who are working in line with the global direction to achieve sustainability, this research provides preliminary evidence that students’ engagement with sustainability is influenced by their course curricula. Originality/value By depicting innovative approaches to teaching sustainability in business, the research enriches the field of sustainable business pedagogy which remains under-researched in many countries. Furthermore, the research goes further by investigating the effect of the course on students’ sustainable consumption. This acts as evidence of the effectiveness of teaching sustainable business in changing future leaders’ perspectives and priorities to include environmental and social aspects, which has become a global goal. Accordingly, the research has the potential to encourage more business schools to make sustainable business education mandatory.

Education with purpose: Student empowerment, an international perspective

This scientific essay addresses the evolution of education, emphasizing the need to view the human being as a dynamic and multifaceted entity from birth to death. It focuses on the student as a critical pillar of the educational process, highlighting the importance of their philosophical inclusion to enhance the effectiveness of the educational system. The essay underscores the relevance of mobile devices in education, promoting teaching strategies that integrate technology to foster collaboration and interaction. The objective of the essay is to analyze the importance of purpose-driven education that empowers students and meets contemporary needs using technology. Good educational practices include encouraging student-faculty contact, developing reciprocity among students, using active learning techniques, giving prompt feedback, emphasizing time on task, communicating high expectations, and respecting diverse talents. These principles, along with contemporary educational technologies, create dynamic and interactive learning environments. Education has undergone significant transformations, adopting various methodologies to meet evolving needs. Empowering students within the educational process is crucial, enhancing their self-esteem, socialization, and sense of belonging. This empowerment fosters deeper interest and engagement in learning. Integrating empowerment into education cultivates leaders capable of leveraging various leadership styles, generating positive outcomes in academic, social, personal, and professional realms. Such leaders contribute to the well-rounded development of individuals and the overall betterment of society. By ensuring that students are empowered and well-prepared to lead and innovate, education can address complex contemporary problems and promote a harmonious and productive society. The essay concludes by emphasizing the necessity of empowering students in the educational process, improving their self-esteem, socialization, and sense of belonging. This empowerment fosters a deeper interest in learning and promotes a more engaging educational experience. Integrating empowerment into education prepares students for leadership roles, enabling them to generate positive outcomes in various aspects of life, thereby contributing to a more cohesive and progressive society.

Exploring fracture of H-BN and graphene by neural network force fields

Extreme mechanical processes such as strong lattice distortion and bond breakage during fracture often lead to catastrophic failure of materials and structures. Understanding the nucleation and growth of cracks is challenged by their multiscale characteristics spanning from atomic-level structures at the crack tip to the structural features where the load is applied. Atomistic simulations offer ‘first-principles’ tools to resolve the progressive microstructural changes at crack fronts and are widely used to explore the underlying processes of mechanical energy dissipation, crack path selection, and dynamic instabilities (e.g. kinking, branching). Empirical force fields developed based on atomic-level structural descriptors based on atomic positions and the bond orders do not yield satisfying predictions of fracture, especially for the nonlinear, anisotropic stress–strain relations and the energy densities of edges. High-fidelity force fields thus should include the tensorial nature of strain and the energetics of bond-breaking and (re)formation events during fracture, which, unfortunately, have not been taken into account in either the state-of-the-art empirical or machine-learning force fields. Based on data generated by density functional theory calculations, we report a neural network-based force field for fracture (NN-F3) constructed by using the end-to-end symmetry preserving framework of deep potential—smooth edition (DeepPot-SE). The workflow combines pre-sampling of the space of strain states and active-learning techniques to explore the transition states at critical bonding distances. The capability of NN-F3 is demonstrated by studying the rupture of hexagonal boron nitride (h-BN) and twisted bilayer graphene as model problems. The simulation results elucidate the roughening physics of fracture defined by the lattice asymmetry in h-BN, explaining recent experimental findings, and predict the interaction between cross-layer cracks in twisted graphene bilayers, which leads to a toughening effect.

Adaptive graph active learning with mutual information via policy learning

Graph neural networks entail massive labeled samples for training, and manual labeling generally requires unaffordable costs. Active learning has emerged as a promising approach to selecting a smaller set of informative labeled samples to improve model performance. However, few active learning techniques for graph data account for the cluster structure and redundancy of samples. To address these issues, we propose an approach that employs uncertain information as an observation for a reinforcement learning agent to adaptively learn a node selection policy. We construct states using node information obtained via mutual information, which considers both the graph structure and the node attributes. The proposed method accurately quantifies node information by leveraging the receptive field of the graph convolutional network and capturing the clustering structure of the data, taking into account the low redundancy and diversity of the labeled samples. Experiments conducted on real-world datasets demonstrate the superiority of the proposed approach over several state-of-the-art methods.

Leveraging transfer learning and active learning for data annotation in passive acoustic monitoring of wildlife

Passive Acoustic Monitoring (PAM) has emerged as a pivotal technology for wildlife monitoring, generating vast amounts of acoustic data. However, the successful application of machine learning methods for sound event detection in PAM datasets heavily relies on the availability of annotated data, which can be laborious to acquire. In this study, we investigate the effectiveness of transfer learning and active learning techniques to address the data annotation challenge in PAM. Transfer learning allows us to use pre-trained models from related tasks or datasets to bootstrap the learning process for sound event detection. Furthermore, active learning promises strategic selection of the most informative samples for annotation, effectively reducing the annotation cost and improving model performance. We evaluate an approach that combines transfer learning and active learning to efficiently exploit existing annotated data and optimize the annotation process for PAM datasets. Our transfer learning observations show that embeddings produced by BirdNet, a model trained on high signal-to-noise recordings of bird vocalisations, can be effectively used for predicting anurans in PAM data: a linear classifier constructed using these embeddings outperforms the benchmark by 21.7%. Our results indicate that active learning is superior to random sampling, although no clear winner emerges among the strategies employed. The proposed method holds promise for facilitating broader adoption of machine learning techniques in PAM and advancing our understanding of biodiversity dynamics through acoustic data analysis.

Low-resource entity resolution with domain generalization and active learning

Entity Resolution (ER), a fundamental task in data cleaning and integration, is critical in various fields such as healthcare, e-commerce, and social networks. Traditional ER methods are constrained by the need for substantial labeled samples and the challenge of generalization to unseen domains. To address the low-resource challenge in ER, a novel two-phase framework is proposed. Initially, we introduce the Domain Generalization Entity Resolution (DGER) framework, combining domain adversarial learning and simulated target learning to improve the generalization performance on unseen target domains. Subsequently, to further adapt to the target dataset, we present a novel active learning approach called Domain-Aware Uncertainty Active Learning (DUAL), for fine-tuning the DGER model with minimal annotation cost. DUAL manually annotates target domain samples that are highly uncertain and exhibit high divergence from the source, while assigning pseudo-labels to high-confidence samples. Experimental results on multiple real-world datasets demonstrate that our framework outperforms traditional ER methods in generalizing to unseen domains. Specifically, our DGER method outperforms the best-performing ER baseline in each task, achieving an average F1 score improvement of 9.02% across eight different test tasks. Moreover, within a limited annotation budget during the active learning phase, our DUAL fine-tuning strategy for the ER model outperforms uncertainty-based active learning techniques.

Automated photo filtering for tourism domain using deep and active learning: the case of Israeli and worldwide cities on instagram

Social media platforms like Instagram significantly influence tourists’ travel decisions by providing them with valuable insights, recommendations, authentic information, and points of interest. However, photos shared with location-specific hashtags, even those related to tourist attractions, do not always reflect the actual destination, creating challenges for potential visitors seeking accurate information. To assist tourists in finding pertinent tourism information for specific destinations, we propose VISTA: Visual Identification of Significant Travel Attractions. The proposed method employs deep learning and active learning techniques to automatically classify photos into: ‘Tourism-Related’ photos (i.e., photos related to tourism) and ‘Non-Tourism-Related’ photos (i.e., photos unrelated to tourism). To train our machine learning classifier, we created a dataset containing photos of the 10 most popular Israeli cities on Instagram. The classifier obtained an accuracy score of 0.965 and a weighted F1 score of 0.964. Evaluating our classifier’s global generalization on the InstaCities100K dataset, derived from InstaCities1M, yielded an accuracy score of 0.958 and a weighted F1 score of 0.959. The effectiveness of VISTA was demonstrated by comparing tourism-related and non-tourism-related photos in terms of photo proportion, user engagement, and object comparison. We found that most photos published on Instagram associated with cities are irrelevant to tourists and that tourism-related photos received more likes than non-tourism-related photos. Finally, there was a low overlap between objects in the two photo collections. Based on these results, we conclude that VISTA can help tourists tackle the problem of finding relevant tourism-related photos among the high volume of photos available on Instagram.

Η αντεστραμμένη διδασκαλία έναντι της παραδοσιακής διδασκαλίας στις θετικές επιστήμες: Μια συγκριτική μελέτη

The purpose of this paper is to compare the effectiveness of using the flipped learning method against traditional teaching, with active learning techniques, in physics and mathematics. The study was conducted on 100 middle and high school students who were first subjected to traditional learning (control group) and then subjected to flipped learning (experimental group). In order to check the effectiveness of the two methods, the students were submitted to an evaluation test in the lesson taught with the two methods. To test the existence of a statistically significant difference between the performance of the two groups, the independent sample t-test was used for continuous variables. The results of the study showed that there is no statistically significant difference in the average performance of students with the two teaching methods.

Psychological Principles in Education: Reviewing William James' Impact on Teaching Practices

The well-known psychologist William James made significant contributions to educational theory that significantly affected how teachers imparted knowledge. William James was a prominent psychologist in the late 19th and early 20th century who made substantial contributions to education. Theory and practice in education have been greatly influenced by his knowledge of human consciousness, emotion, and behavior. This review of the literature aims to find out how James' psychological theories have influenced contemporary teaching methods. This review attempts to provide educators with useful guidance for enhancing student growth and learning, with an emphasis on James' theories and their relevance to modern classrooms. The significance of the study is to know about James’ psychological theories that influence modern teaching pedagogies and learning and by studying this study educators can find guidance for improving and enhancing student learning and growth. The conclusion of the study shows that modern teaching methods are highly influenced by James’ ideas like habit formation, students’ attention and engagement, and the nature of awareness moreover, implementation of James’ ideas may help teachers improve the students’ results and performance as these provide more interesting, engaging, and effective learning environments. James’ philosophies are useful for the implication of modern educational trends like active learning techniques, the creation of mindful activities, social and emotional learning, and student-centered learning.