Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (165)

Search Parameters:
Keywords = exam grades

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
7 pages, 1853 KiB  
Interesting Images
Mucinous Carcinoma, Mucinous Borderline Tumor and Pseudomyxoma Ovarii in a Cystic Teratoma: A Histological Conundrum
by Cinzia Giacometti, Mariateresa Mirandola, Camillo Aliberti, Filippo Molinari, Lisa Marcolini, Daniele Mautone and Guido Martignoni
Diagnostics 2025, 15(15), 1957; https://doi.org/10.3390/diagnostics15151957 (registering DOI) - 4 Aug 2025
Abstract
Mature teratomas account for approximately 20% of all ovarian tumors identified in pathological studies. Benign or malignant somatic neoplasms developing within teratomas can arise from any tissue in up to 2% of mature cystic teratomas, including low-grade malignant mucinous neoplasms. This report presents [...] Read more.
Mature teratomas account for approximately 20% of all ovarian tumors identified in pathological studies. Benign or malignant somatic neoplasms developing within teratomas can arise from any tissue in up to 2% of mature cystic teratomas, including low-grade malignant mucinous neoplasms. This report presents the case of a 34-year-old woman with no previous gynecological or general health issues, who was admitted to our Hospital after an asymptomatic pelvic mass was detected during a routine exam. A transvaginal ultrasound revealed a unilateral pelvic mass in the left adnexal region, measuring 8 cm. The CT scan showed a cystic-appearing formation measuring nearly 12 cm, which indented the bladder dome. Final diagnosis indicated a mucinous carcinoma arising from a mucinous borderline lesion within the context of a mature ovarian teratoma. No other involvement or lymphadenopathies were detected on 18FDG-PET CT scan, and the patient is now well and free of recurrences. Full article
(This article belongs to the Special Issue Pathology and Diagnosis of Gynecologic Diseases, 3rd Edition)
Show Figures

Figure 1

27 pages, 3562 KiB  
Article
Automated Test Generation and Marking Using LLMs
by Ioannis Papachristou, Grigoris Dimitroulakos and Costas Vassilakis
Electronics 2025, 14(14), 2835; https://doi.org/10.3390/electronics14142835 - 15 Jul 2025
Cited by 1 | Viewed by 488
Abstract
This paper presents an innovative exam-creation and grading system powered by advanced natural language processing and local large language models. The system automatically generates clear, grammatically accurate questions from both short passages and longer documents across different languages, supports multiple formats and difficulty [...] Read more.
This paper presents an innovative exam-creation and grading system powered by advanced natural language processing and local large language models. The system automatically generates clear, grammatically accurate questions from both short passages and longer documents across different languages, supports multiple formats and difficulty levels, and ensures semantic diversity while minimizing redundancy, thus maximizing the percentage of the material that is covered in the generated exam paper. For grading, it employs a semantic-similarity model to evaluate essays and open-ended responses, awards partial credit, and mitigates bias from phrasing or syntax via named entity recognition. A major advantage of the proposed approach is its ability to run entirely on standard personal computers, without specialized artificial intelligence hardware, promoting privacy and exam security while maintaining low operational and maintenance costs. Moreover, its modular architecture allows the seamless swapping of models with minimal intervention, ensuring adaptability and the easy integration of future improvements. A requirements–compliance evaluation, combined with established performance metrics, was used to review and compare two popular multilingual LLMs and monolingual alternatives, demonstrating the system’s effectiveness and flexibility. The experimental results show that the system achieves a grading accuracy within a 17% normalized error margin compared to that of human experts, with generated questions reaching up to 89.5% semantic similarity to source content. The full exam generation and grading pipeline runs efficiently on consumer-grade hardware, with average inference times under 30 s. Full article
Show Figures

Figure 1

20 pages, 976 KiB  
Article
Disordered Eating Behaviors, Perceived Stress and Insomnia During Academic Exams: A Study Among University Students
by Elena-Gabriela Strete, Mădălina-Gabriela Cincu and Andreea Sălcudean
Medicina 2025, 61(7), 1226; https://doi.org/10.3390/medicina61071226 - 6 Jul 2025
Viewed by 488
Abstract
Background and Objectives: During exam sessions, many students experience high levels of stress caused by the large volume of material to study, tight deadlines, and pressure to achieve top grades. This study aimed to examine the relationship between academic stress, sleep disturbances, and [...] Read more.
Background and Objectives: During exam sessions, many students experience high levels of stress caused by the large volume of material to study, tight deadlines, and pressure to achieve top grades. This study aimed to examine the relationship between academic stress, sleep disturbances, and eating behaviors by using validated questionnaires administered to a student sample. As stress levels increased, the data revealed a higher frequency of insomnia symptoms and disordered eating, including behaviors such as compulsive eating and irregular meal patterns. Materials and Methods: This cross-sectional, correlational study was conducted on a convenience sample of 317 university students from various academic centers across Romania. Participants were recruited via online distribution of a self-administered questionnaire during a four-month period, including exam sessions. The survey included the Perceived Stress Scale (PSS), the Insomnia Severity Index (ISI), and the Eating Disorder Examination Questionnaire (EDE-Q), alongside additional items assessing perceived links between stress, sleep, and eating behaviors, and the use of medication. Data were analyzed using SPSS with Spearman correlations, t-tests, and linear regression. Results: Statistical analyses revealed significant and positive associations between perceived stress levels and insomnia, as indicated by Spearman’s correlation (p < 0.01). A similar significant correlation was identified between perceived stress and disordered eating behaviors among students. Specifically, the feeling of being overwhelmed by academic workload showed a strong positive correlation with a lack of control over eating behaviors (r = 0.568). Furthermore, linear regression analysis confirmed a significant predictive relationship between feeling overwhelmed and the tendency to eat excessively beyond initial intentions, with a standardized regression coefficient B = 0.581 (p < 0.001). A separate regression analysis focusing on exam-related stress and episodes of compulsive eating behavior demonstrated a comparable result (B = 0.573, p < 0.001), indicating a robust positive association. Additionally, independent samples t-tests demonstrated that students experiencing high levels of stress during the exam period reported significantly greater difficulties with sleep initiation and higher levels of disordered eating compared to their peers with lower stress levels. The difference in insomnia scores was highly significant (t = 11.516, p < 0.001), as was the difference in eating behavior scores (t = 10.931, p < 0.001). Conclusions: These findings underscore the need for emotional support services and effective stress management strategies, enabling students to navigate academic demands without compromising their mental or physical well-being. Full article
(This article belongs to the Special Issue Public Mental Health Crisis during SARS-CoV-2 Pandemic—Part 2)
Show Figures

Figure 1

11 pages, 566 KiB  
Article
Reliability and Sources of Variation of Preclinical OSCEs at a Large US Osteopathic Medical School
by Martin Schmidt, Sarah Parrott and Maurice Blodgett
Int. Med. Educ. 2025, 4(3), 25; https://doi.org/10.3390/ime4030025 - 5 Jul 2025
Viewed by 243
Abstract
The objective structured clinical examination (OSCE) is a well-established tool for assessing clinical skills, providing reliability, validity, and generalizability for high-stakes examinations. Des Moines University College of Osteopathic Medicine (DMU-COM) adapted the OSCE for formative assessments in undergraduate medical education, focusing on interpersonal [...] Read more.
The objective structured clinical examination (OSCE) is a well-established tool for assessing clinical skills, providing reliability, validity, and generalizability for high-stakes examinations. Des Moines University College of Osteopathic Medicine (DMU-COM) adapted the OSCE for formative assessments in undergraduate medical education, focusing on interpersonal aspects in the primary care setting. Students are graded by standardized patients and faculty observers on interpersonal skills, history/physical examination, oral case presentation, and documentation. The purpose of the study is to establish the reliability and to identify sources of variation in the DMU-COM OSCE to aid medical educators in their understanding of the accuracy of clinical skills. We examined student performance data across five OSCE domains. We assessed intra- and inter-OSCE reliability by calculating KR20 values, determined sources of variation by multivariate regression analysis, and described relationships among observed variables through factor analysis. The results indicate that the OSCE captures student performance in three dimensions with low intra-OSCE reliability but acceptable longitudinal inter-OSCE reliability. Variance analysis shows significant measurement error in rubric-graded scores but negligible error in checklist-graded portions. Physical exam scores from patients and faculty showed no correlation, indicating value in having two different observers. We conclude that a series of formative OSCEs is a valid tool for assessing clinical skills in preclinical medical students. However, the low intra-assessment reliability cautions against using a single OSCE for summative clinical skills competency assessments. Full article
Show Figures

Figure 1

17 pages, 1567 KiB  
Article
Association Between Parental Attendance at Early Adolescence’s Parent–Teacher Conferences and Their Children’s Performance in Standardized Exams for High School and College Entrance
by Sydney L. Fu, Sean O. Fu, Rebecca Y. Chen, Earl Fu, Martin M. Fu, Tony Szu-Hsien Lee and Hsun-Yu Chan
Educ. Sci. 2025, 15(6), 750; https://doi.org/10.3390/educsci15060750 - 13 Jun 2025
Viewed by 485
Abstract
Adolescents’ performance in high-stakes standardized examinations plays a pivotal role in shaping their educational trajectories. This longitudinal study investigated whether parental attendance at parent–teacher conferences (PTCs) during early adolescence is associated with students’ performance in standardized examinations required for high school and college [...] Read more.
Adolescents’ performance in high-stakes standardized examinations plays a pivotal role in shaping their educational trajectories. This longitudinal study investigated whether parental attendance at parent–teacher conferences (PTCs) during early adolescence is associated with students’ performance in standardized examinations required for high school and college entrance. Drawing on data from the Taiwan Youth Project, we analyzed responses from 1294 ninth-grade students and 524 twelfth-grade students with available exam results. Parental participation in PTCs was recorded in both seventh and eighth grades, along with two other types of school-based involvement and covariates, such as parental education level, household income, students’ birth order, prior academic rank, peer relationships, parental support, and parental expectations. Hierarchical linear modeling was employed to control for individual and school-level variables. The results showed that parental attendance at PTCs in eighth grade was associated with higher scores on high school entrance exams in ninth grade. Furthermore, attending PTCs in both seventh and eighth grades was significantly associated with better performance in college entrance exams in twelfth grade (β = 3.02, p < 0.01). These findings suggest that sustained parental engagement in PTCs contributes to improved academic performance in adolescence. Policies that promote equitable and continued parent–teacher collaboration may support long-term student success. Full article
(This article belongs to the Section Education and Psychology)
Show Figures

Figure 1

32 pages, 2079 KiB  
Review
The Use of Large Language Models in Ophthalmology: A Scoping Review on Current Use-Cases and Considerations for Future Works in This Field
by Ye King Clarence See, Khai Shin Alva Lim, Wei Yung Au, Si Yin Charlene Chia, Xiuyi Fan and Zhenghao Kelvin Li
Big Data Cogn. Comput. 2025, 9(6), 151; https://doi.org/10.3390/bdcc9060151 - 6 Jun 2025
Viewed by 796
Abstract
The advancement of generative artificial intelligence (AI) has resulted in its use permeating many areas of life. Amidst this eruption of scientific output, a wide range of research regarding the usage of Large Language Models (LLMs) in ophthalmology has emerged. In this study, [...] Read more.
The advancement of generative artificial intelligence (AI) has resulted in its use permeating many areas of life. Amidst this eruption of scientific output, a wide range of research regarding the usage of Large Language Models (LLMs) in ophthalmology has emerged. In this study, we aim to map out the landscape of LLM applications in ophthalmology, and by consolidating the work carried out, we aim to produce a point of reference to guide the conduct of future works. Eight databases were searched for articles from 2019 to 2024. In total, 976 studies were screened, and a final 49 were included. The study designs and outcomes of these studies were analysed. The performance of LLMs was further analysed in the areas of exam taking and patient education, diagnostic capability, management capability, administration, inaccuracies, and harm. LLMs performed acceptably in most studies, even surpassing humans in some. Despite their relatively good performance, issues pertaining to study design, grading protocols, hallucinations, inaccuracies, and harm were found to be pervasive. LLMs have received considerable attention through their introduction to the public and have found potential applications in the field of medicine, and in particular, ophthalmology. However, using standardised evaluation frameworks and addressing gaps in the current literature when applying LLMs in ophthalmology is recommended through this review. Full article
Show Figures

Figure 1

18 pages, 555 KiB  
Article
Evaluation of Undergraduate Dental Students’ Opinions on the Use of Digital Versus Conventional Design in Prosthodontics
by Lucian Toma Ciocan, Mihaela Pantea, Vlad Gabriel Vasilescu, Ana Maria Cristina Țâncu, Ruxandra Sfeatcu, Andreea Cristiana Didilescu, Alexandra Ripszky, Alexandra Popa, Silviu Mirel Pițuru and Marina Imre
Dent. J. 2025, 13(6), 242; https://doi.org/10.3390/dj13060242 - 29 May 2025
Viewed by 413
Abstract
Background/Objectives: The integration of digital technologies into dental education is becoming increasingly important, particularly in prosthodontics, where digital design tools offer enhanced precision and efficiency. This study aimed to evaluate second-year dental students’ perceptions regarding conventional versus digital design in prosthodontics, assessing [...] Read more.
Background/Objectives: The integration of digital technologies into dental education is becoming increasingly important, particularly in prosthodontics, where digital design tools offer enhanced precision and efficiency. This study aimed to evaluate second-year dental students’ perceptions regarding conventional versus digital design in prosthodontics, assessing their theoretical knowledge, practical skills, and attitudes toward these approaches. Methods: A total of 141 dental students enrolled in Faculty of Dentistry from “Carol Davila” University of Medicine and Pharmacy, Bucharest, Romania, participated in an online survey consisting of 19 questions evaluating their understanding, preferences, attitudes, and expectations regarding digital and conventional prosthodontic workflows. Additionally, students’ practical exam grades and task completion times for both conventional and digital design methods were evaluated. Results: Participating students reported sufficient understanding of theoretical concepts in both conventional (92.9%) and digital design (91.5%). A significant proportion (78.7%) felt confident in their practical skills for conventional design, while 78% expressed the same for digital design. Statistically significant correlations indicated that students who believed digital design could replace conventional methods associated digital design with greater accuracy (p = 0.020), predictability (p = 0.048), and sustainability (p = 0.032). Students who believed they had acquired enough skills in digital design responded more frequently that the time allocation for digital design by the university was sufficient (p < 0.001). Moreover, students scored significantly higher in digital design practical exams compared to conventional design (p < 0.001). Task completion times were also shorter for digital workflows, further supporting their efficiency. Conclusions: The findings suggest that students are highly receptive to digital technologies in prosthodontics, favoring digital workflows over conventional techniques. These results highlight the need for continued integration of digital tools into dental curricula to enhance students’ competency and prepare them for modern clinical practice. Full article
(This article belongs to the Special Issue Dental Education: Innovation and Challenge)
Show Figures

Figure 1

13 pages, 1170 KiB  
Article
A Statistical Procedure for Exploring a Skeletal Age-Explicative Tool for Growing Patients
by Michele Tepedino, Rosa Esposito, Maurizio Delvecchio, Domenico Ciavarella, Giuseppe Rofrano and Francesco Masedu
Appl. Sci. 2025, 15(10), 5593; https://doi.org/10.3390/app15105593 - 16 May 2025
Viewed by 350
Abstract
Background: Skeletal age estimation plays a fundamental role in orthopedic treatments. Since the most reliable methods are based on ionizing radiation, this study aimed to use machine learning techniques to explore a skeletal age assessment method not based on additional radiographies. Methods: [...] Read more.
Background: Skeletal age estimation plays a fundamental role in orthopedic treatments. Since the most reliable methods are based on ionizing radiation, this study aimed to use machine learning techniques to explore a skeletal age assessment method not based on additional radiographies. Methods: Patients aged between 6 and 16 years old whose clinical records included orthopantomography, radiographs of the second phalanx of the third finger, and biometric data were enrolled for the study. The radiographs were analyzed to estimate the maturation degree of the left lower first premolars, the midpalatal suture, and the second phalanx of the third finger. Both an explicative data analysis and a multivariate analysis were performed. Results: The sample comprised 111 subjects. The multivariate analysis revealed an explanatory role for sex (p < 0.01) and chronological age (p < 0.01). The ordinal tool showed how the use of height (p = 0.02) and weight (p = 0.03) was explicative of skeletal age against a loss of statistical significance corresponding to the use of body mass index (p = 0.6). The median palatine suture (p = 0.01) was explicative. Conclusions: The combined evaluation of weight, height, sex, chronological age, and grade of maturation of the midpalate suture provides an explicative tool for assessing skeletal age without additional radiographic exams, besides a routine orthopantomography. Full article
(This article belongs to the Special Issue Orthodontics: Advanced Techniques, Methods and Materials)
Show Figures

Figure 1

15 pages, 284 KiB  
Article
Perceptions of Learning Assessment in Practicum Students vs. Initial Teacher Education Faculty in Chilean Physical Education: A Comparative Study of Two Cohorts
by Francisco Gallardo-Fuentes, Bastian Carter-Thuillier, Sebastián Peña-Troncoso, Samuel Pérez-Norambuena and Jorge Gallardo-Fuentes
Educ. Sci. 2025, 15(4), 459; https://doi.org/10.3390/educsci15040459 - 8 Apr 2025
Viewed by 696
Abstract
An education oriented towards learning must necessarily include assessment techniques and instruments that effectively achieve this goal. Currently, assessment has become a crucial element, leading to the promulgation of legal regulations to govern it. This study aimed to explore the perceptions of assessment [...] Read more.
An education oriented towards learning must necessarily include assessment techniques and instruments that effectively achieve this goal. Currently, assessment has become a crucial element, leading to the promulgation of legal regulations to govern it. This study aimed to explore the perceptions of assessment in three Chilean universities among faculty members vs. practicum students from two cohorts of Chilean Initial Teacher Education in Physical Education (ITEPE) from two cohorts from subsequent moments, with a difference of four years. The study followed a quantitative, cross-sectional, and comparative approach and the sample consisted of a total of 458 participants, including 1st Group: n = 162 practicum students (S1) 2019–20 (M = 22.5, SD = 3.1) and 44 faculty members (FM1) from the same cohort (M = 42.3, SD = 11.2) vs. 197 practicum students (S2) 2023–24 (M = 23.6, SD = 2.2) and 55 faculty members (FM2) from this cohort (M = 40.4, SD = 10.4). Data were collected using the “Questionnaire for the Study of the Assessment System”. The results revealed significant differences between students and faculty regarding the perception of the use of assessment instruments in ITEPE. The 2023–24 cohort students perceived a greater presence of portfolios compared to their peers from four years ago, while faculty from the latest cohort indicated a perception of higher use of traditional exams. In conclusion, it can be observed that decision-making predominantly falls on the faculty, as evidenced by discrepancies regarding feedback and student participation in grade determination. This reinforces the idea that the process remains teacher-centered. Full article
(This article belongs to the Section Higher Education)
13 pages, 223 KiB  
Article
Students’ & Faculty Members’ Attitudes Towards Learning and Teaching Reaction Mechanisms in Organic Chemistry
by Oluwatobi Odeleye and Nghiem Tieu
Educ. Sci. 2025, 15(3), 357; https://doi.org/10.3390/educsci15030357 - 13 Mar 2025
Viewed by 668
Abstract
Organic Chemistry has typically been identified as a difficult course for many undergraduate students and has a notoriously high failure rate. The part of the subject dealing with reaction mechanisms is considered the most challenging area, and several papers have been published on [...] Read more.
Organic Chemistry has typically been identified as a difficult course for many undergraduate students and has a notoriously high failure rate. The part of the subject dealing with reaction mechanisms is considered the most challenging area, and several papers have been published on how to facilitate students’ understanding of mechanisms. During Fall 2022 and Spring 2023, we surveyed 127 students, and interviewed 3 students and 5 faculty members about their opinions towards teaching and learning Organic Chemistry, especially reaction mechanisms. The students’ attitudes were surveyed through the Attitude towards the Subject of Chemistry Inventory (ASCIv2), and its relationship with grades was also investigated. The results show that most students have negative attitudes towards Organic Chemistry; however, those with more positive attitudes performed better in the course. Students mostly viewed Organic Chemistry as a course required for their major/degree or professional exams without knowing the actual applications of the subject in their respective fields. Professors were able to relate organic chemistry to other fields besides chemistry (Health Science) but found it difficult to give examples of where else reaction mechanisms would be used outside of Organic Chemistry. A suggestion for a change of Organic Chemistry course is discussed in the conclusion of this study. Full article
17 pages, 2384 KiB  
Article
A Cognitive Diagnosis Model Using Convolutional Neural Networks to Predict Student Scores
by Jianwen Mo, Longhua Hao, Hua Yuan and Zhaoyu Shou
Appl. Sci. 2025, 15(6), 2875; https://doi.org/10.3390/app15062875 - 7 Mar 2025
Viewed by 1046
Abstract
Smart education is an important direction of future educational development, aiming to improve the intelligence level of the existing digital education system and achieve the deep integration of information technology and mainstream education business. Most of the existing cognitive diagnostic models are trained [...] Read more.
Smart education is an important direction of future educational development, aiming to improve the intelligence level of the existing digital education system and achieve the deep integration of information technology and mainstream education business. Most of the existing cognitive diagnostic models are trained and tested based on the answers to known questions, and the dependence on the trained questions leads to poor prediction results of the model for unknown questions. To solve that problem, this paper divides the questions of the dataset into the usual quizzes (known questions) and the final exam questions (unknown questions), which are used for training and testing, respectively. The cognitive diagnosis model based on a convolutional neural network (CNNCD) is proposed. Firstly, the attention mechanism is used to dig out the intra-layer relationships among students, questions and knowledge points, which alleviates the problem of insufficient information mining among students, questions and knowledge points. Secondly, two multi-layer (general and special) one-dimensional convolutional neural networks are combined to model the cognitive diagnosis of the process from students’ usual grades to students’ mastery of knowledge points. Finally, two multi-layer (general and special) one-dimensional convolutional neural networks are used to predict students’ final exam scores. Experiments on three public datasets and self-made BOIT datasets show that the proposed method is superior to other comparison models on these three evaluation indexes, indicating the feasibility and effectiveness of the proposed model. Full article
Show Figures

Figure 1

12 pages, 4282 KiB  
Article
Simplifying the Diagnosis of Pediatric Nystagmus with Fundus Photography
by Noa Cohen-Sinai, Inbal Man Peles, Basel Obied, Noa Netzer, Noa Hadar, Alon Zahavi and Nitza Goldenberg-Cohen
Children 2025, 12(2), 211; https://doi.org/10.3390/children12020211 - 11 Feb 2025
Viewed by 1081
Abstract
Background/Objectives: To simplify diagnosing congenital and acquired nystagmus using fundus photographs. Methods: A retrospective study included patients with congenital or childhood-acquired nystagmus examined at a hospital-based ophthalmology clinic (September 2020–September 2023) with fundus photos taken. Exclusions were for incomplete data or low-quality images. [...] Read more.
Background/Objectives: To simplify diagnosing congenital and acquired nystagmus using fundus photographs. Methods: A retrospective study included patients with congenital or childhood-acquired nystagmus examined at a hospital-based ophthalmology clinic (September 2020–September 2023) with fundus photos taken. Exclusions were for incomplete data or low-quality images. Demographics, aetiology, orthoptic measurements, and ophthalmologic and neurological exams were reviewed. Two independent physicians graded fundus photos based on amplitude (distance between “ghost” images), the number of images visible, and the direction of nystagmus. Severity was rated on a 0–3 scale using qualitative and quantitative methods. Photographic findings were compared to clinical data, and statistical analysis used Mann-Whitney tests. Results: A total of 53 eyes from 29 patients (16 females, 13 males; mean age 12.5 years, range 3–65) were studied: 25 with binocular nystagmus and 3 with monocular nystagmus. Diagnoses included congenital (n = 15), latent-manifest (n = 3), neurologically associated (n = 2), and idiopathic (n = 9). Types observed were vertical (n = 5), horizontal (n = 23), rotatory (n = 10), and multidirectional (n = 15). Visual acuity ranged from 20/20 to no light perception. Fundus photos correlated with clinical diagnoses, aiding qualitative assessment of direction and amplitude and mitigating eye movement effects for clearer retinal detail visualization. Conclusions: Fundus photography effectively captures nystagmus characteristics and retinal details, even in young children, despite continuous eye movements. Integrating fundus cameras into routine practice may enhance nystagmus diagnosis and management, improving patient outcomes. Full article
(This article belongs to the Section Pediatric Ophthalmology)
Show Figures

Figure 1

18 pages, 2710 KiB  
Article
Hybrid ANN-Based and Text Similarity Method for Automatic Short-Answer Grading in Polish
by Marwah Bani Saad, Lidia Jackowska-Strumillo and Wojciech Bieniecki
Appl. Sci. 2025, 15(3), 1605; https://doi.org/10.3390/app15031605 - 5 Feb 2025
Cited by 1 | Viewed by 923
Abstract
Computer-assisted grading plays an important role in an educational context, mainly by reducing the workload of teachers in manual scoring. While electronic choice surveys have long been used in many web applications, automatic scoring of open-ended responses remains an interesting research problem in [...] Read more.
Computer-assisted grading plays an important role in an educational context, mainly by reducing the workload of teachers in manual scoring. While electronic choice surveys have long been used in many web applications, automatic scoring of open-ended responses remains an interesting research problem in natural language processing. In this article, we propose a new hybrid text-processing method for scoring students’ responses based on word splitting and preprocessing, which will then combine textual algorithms with a set of artificial neural network classifiers and a set of heuristic decision rules. This concept has been implemented in the interactive e-test system operating in the local computer network of the Institute of Applied Computer Science at the Lodz University of Technology. The dataset is acquired as questions, reference answers, and students’ answers generated on the basis of exams conducted at our institute in the years 2015–2022 for more than a thousand students. This article extends our previous research and includes comparative tests. The proposed method achieves excellent results and outperforms the previous approaches. The obtained precision is equal to 1, and the recall measure is 0.97 for the final results. Full article
(This article belongs to the Collection Machine Learning in Computer Engineering Applications)
Show Figures

Figure 1

33 pages, 1119 KiB  
Article
Engineered Prompts in ChatGPT for Educational Assessment in Software Engineering and Computer Science
by Ayman Diyab, Russell Morris Frost, Benjamin David Fedoruk and Ahmad Diyab
Educ. Sci. 2025, 15(2), 156; https://doi.org/10.3390/educsci15020156 - 26 Jan 2025
Cited by 2 | Viewed by 3159
Abstract
AI Assess, a ChatGPT-based assessment system utilizing the ChatGPT platform by OpenAI, composed of four components, is proposed herein. The components are tested on the GPT model to determine to what extent they can grade various exam questions based on learning outcomes, generate [...] Read more.
AI Assess, a ChatGPT-based assessment system utilizing the ChatGPT platform by OpenAI, composed of four components, is proposed herein. The components are tested on the GPT model to determine to what extent they can grade various exam questions based on learning outcomes, generate relevant practice problems to improve content retention, identify student knowledge gaps, and provide instantaneous feedback to students. The assessment system has been explored using software engineering and computer science courses and is successful through testing and evaluation. AI Assess has demonstrated the ability to generate practice problems based on syllabus information and learning outcomes. The components have been shown to identify weak areas for students. Finally, it has been shown to provide different levels of feedback. The combined set of components, if incorporated into a complete software system and implemented in classrooms with proposed transparency mechanisms, has vast potential to reduce instructor workload, improve student understanding, and enhance the learning experience. The potential for GPT-powered chatbots in educational assessments is vast and must be embraced by the education sector. Full article
Show Figures

Figure 1

16 pages, 2857 KiB  
Article
Combining Multi-Scale Fusion and Attentional Mechanisms for Assessing Writing Accuracy
by Renyuan Liu, Yunyu Shi, Xian Tang and Xiang Liu
Appl. Sci. 2025, 15(3), 1204; https://doi.org/10.3390/app15031204 - 24 Jan 2025
Cited by 1 | Viewed by 1024
Abstract
Traditional methods of assessing handwritten characters are often too subjective, inefficient, and lagging in feedback, which makes it difficult for educators to achieve fully objective writing assessments and for writers to receive timely suggestions for improvement. In this paper, we propose a convolutional [...] Read more.
Traditional methods of assessing handwritten characters are often too subjective, inefficient, and lagging in feedback, which makes it difficult for educators to achieve fully objective writing assessments and for writers to receive timely suggestions for improvement. In this paper, we propose a convolutional neural network (CNN) architecture that combines the attention mechanism with multi-scale feature fusion; specifically, the features are weighted by designing a bottleneck layer that combines the Squeeze-and-Excitation (SE) attention mechanism to highlight the important information and by applying a multi-scale feature fusion method to enable the network to capture both the global structure and the local details of Chinese characters. Finally, a high-quality dataset containing 26,800 images of handwritten Chinese characters is constructed based on the application scenario of the writing grade test, covering the common Chinese characters in the writing grade exam; The experimental results show that the proposed method achieves 98.6% accuracy on the writing grade exam dataset and 97.05% on the ICDAR-2013 public dataset, significantly improving recognition accuracy. The constructed dataset and improved model are suitable for application scenarios such as writing grade exams, which helps to improve marking efficiency and accuracy. Full article
(This article belongs to the Special Issue Intelligent Systems and Tools for Education)
Show Figures

Figure 1

Back to TopTop