Student Answers Research Articles

Enhancing Student Performance Prediction on Learnersourced Questions with SGNN-LLM Synergy

Learnersourcing offers great potential for scalable education through student content creation. However, predicting student performance on learnersourced questions, which is essential for personalizing the learning experience, is challenging due to the inherent noise in student-generated data. Moreover, while conventional graph-based methods can capture the complex network of student and question interactions, they often fall short under cold start conditions where limited student engagement with questions yields sparse data. To address both challenges, we introduce an innovative strategy that synergizes the potential of integrating Signed Graph Neural Networks (SGNNs) and Large Language Model (LLM) embeddings. Our methodology employs a signed bipartite graph to comprehensively model student answers, complemented by a contrastive learning framework that enhances noise resilience. Furthermore, LLM's contribution lies in generating foundational question embeddings, proving especially advantageous in addressing cold start scenarios characterized by limited graph data. Validation across five real-world datasets sourced from the PeerWise platform underscores our approach's effectiveness. Our method outperforms baselines, showcasing enhanced predictive accuracy and robustness.

Evaluating IBM’s Watson natural language processing artificial intelligence as a short-answer categorization tool for physics education research

Recent advances in publicly available natural language processors (NLP) may enhance the efficiency of analyzing student short-answer responses in physics education research (PER). We train a state-of-the-art NLP, IBM’s Watson, and test its agreement with human coders using two different studies that gathered text responses in which students explain their reasoning on physics-related questions. The first study analyzes 479 student responses to a lab data analysis question and categorizes them by main idea. The second study analyzes 732 student answers to identify the presence or absence of each of the two conceptual themes. When training Watson with approximately one-third to half of the samples, we find that samples labeled with high confidence scores have similar accuracy to human agreement; yet for lower confidence scores, humans outperform the NLP’s labeling accuracy. In addition to studying Watson’s overall accuracy, we use this analysis to better understand factors that impact how Watson categorizes. Using the data from the categorization study, we find that Watson’s algorithm does not appear to be impacted by the disproportionate representation of categories in the training set, and we examine mislabeled statements to identify vocabulary and phrasing that may increase the rate of false positives. Based on this work, we find that, with careful consideration of the research study design and an awareness of the NLP’s limitations, Watson may present a useful tool for large-scale PER studies or classroom analysis tools. Published by the American Physical Society 2024

Student Motivations for Choosing the Re-Engineered First-Year Program at the University of Saskatchewan

As part of program evaluation and continuous improvement, the University of Saskatchewan deployed a survey across the common Re-Engineered First-Year (REFY) program in September 2022. Student answers to open-ended questions about their motivation to choose the REFY program were analyzed qualitatively using expectancy-value theory. This framework establishes four subjective task values that motivate behaviour (intrinsic, attainment, utility, and cost). Statistical analysis using logistic regression was then used to examine correlations between these motivators and student demographics. Results indicate costs specifically related to lack of final exams (24%) and costs unrelated to final exams (26%) were the most common motivators for choosing the REFY program, followed by intrinsic (17%) and utility (16%), with attainment (4%) being the lowest. The program features that students found most influential in their decision to join the REFY program included the opportunity to learn about different engineering disciplines, a lack of final exams, and competency-based assessment. Students also valued the program being designed to support them and to help them succeed; this program aspect is important to maintain because it strengthens motivation.

СРАВНИТЕЛЬНЫЙ АНАЛИЗ УРОВНЯ ИНФОРМИРОВАННОСТИ СТАРШЕКЛАССНИКОВ И СТУДЕНТОВ МЕДИЦИНСКОГО ВУЗА В ВОПРОСАХ СОЦИАЛЬНО-ЗНАЧИМЫХ ЗАБОЛЕВАНИЙ И ПРОФИЛАКТИКИ ИППП

As is known, the sexually transmitted infection (STI) incidence continues to be a pertinent issue: high contagiousness and negative impact on public health puts STIs on the list of socially significant diseases. The consequences of these diseases directly affect the demographic situation in the country, due to the deterioration of the reproductive health of the population with a subsequent decrease in the birth rate. This issue becomes especially pronounced among teenagers. This paper demonstrates the results of a study on socially significant diseases and STI prevention issues conducted among high school and medical students in Moscow with the aim of studying and identifying youth awareness problems, differentiating the knowledge of STI prevention among high school and college students, as well as determining respondents’ interest in getting information on these diseases online. Purpose: To study and identify problems of youth awareness, determine the difference in the knowledge of STI prevention among the high school and college students, as well as determine the interest of respondents in obtaining information on these diseases online. Materials and methods of research: The study includes the results of anonymous questionnaires filled out by schoolchildren of 15-17 years (115 respondents) and 3rd year students of the Faculty of Medicine (134 respondents). Research methods: analytical, statistical, sociological. Results: Based on the research data, we identified a difference in the answers of schoolchildren and college students in several types of questions. Thus, medical school students clearly appear as more mature, independent and busy people with more extensive knowledge on the given topics. The vast majority of respondents showed interest and wanted to obtain information on socially significant diseases and STI prevention. The best way to do so is to communicate comprehensive, high-quality knowledge of socially significant diseases and STI prevention using online technologies.

Knowledge, Attitudes, and Perceptions of Medical and Paramedical Students Toward Human Milk Banks and Breast Milk Donation.

Background and objectives Human milk benefits for both mothers and babies are widely acknowledged. Human milk banks (HMBs) are essential in providing newborns who would not otherwise have access to pasteurized and stored human milk. The objective of this research was to investigate the understanding, opinions, and outlooks of medical and paramedical students regarding breast milk donation and the concept of an HMB. Material and methods A total of 398 professional female students specializing in physiotherapy, nursing, and medicine were given an online self-administered questionnaire as part of a descriptive cross-sectional study. Data on the characteristics, HMB knowledge, awareness levels, and attitudes toward HMB and breast milk donation were to be gathered through the questionnaire. Every student's answer to the survey was kept private and confidential. Result According to the survey, 188 students (47.24%) belong to the medical college, 126 students (31.66%) belong to the physiotherapy college, and the remaining 84 students (21.11%) are from the nursing college. A total of 294 students (74.12%) had heard about human milk banking before and received information from health professionals (195 students, 48.99%), the news (67 students, 16.83%), and family and friends (61 students, 15.33%). However, only 224 students (56.28%) are willing to feed their babies with HMB milk in the future. On the other hand, 216 students (54.27%) are ready to donate breast milk to HMB. The majority of students have a favorable opinion of breast milk donation. A staggering 394 students (98.99%) think that donating human milk can save babies. Furthermore, 379 students (95.23%) think that all the nutrients needed for a baby's healthy development are found in human milk. Merely 350 students (87.93%) think that breastfeeding does not result in malnourishment for either the mother or the baby. When there is an excess of milk, the majority of students (378 or 94.97%) think that there is nothing wrong with donating it. Moreover, 312 (80.41%) students are happy to donate milk in the future. A total of 373 students (93.71%) are overjoyed that a sick baby will survive because of their donated milk. Only 100 students (25.12%) will give milk, though, and only to the infants of their friends and relatives, never to complete strangers. Conclusion A dearth of knowledge pertaining to human milk banking is rampant among medical and paramedical female students, yet the gravity of the circumstances remains concealed. Consequently, it is imperative to extensively educate all Indian communities about the concept of human milk banking to gain widespread acceptance. This research sheds light on the issue and promotes scientific knowledge of HMB, as many students are unaware of it.

SELF TRANSCENDENCE: THE IDEALITY DIMENSIONS OF AL-ISLAM AND KEMUHAMMADIYAHAN LEARNING IMPACT IN MUHAMMADIYAH SCHOOL

The terms al-Islam and Kemuhammadiyahan used by Muhammadiyah schools for learning Islamic religious education are in line with the educational objectives contained in the national education law. Developing the potential of students to have religious spiritual strength is a concrete form of achievement to be realized through the implementation of education. This context has an equivalent to the hierarchy of self-transcendence which is the final level of Maslow's theory of needs. This qualitative-based research with a case study uses a content analysis model on student answers in the form of a description with 1 single question. Respondents used as many as 379 students in Muhammadiyah schools at the junior high school level. The results showed that 53 students' answers lead to a desire to achieve the hierarchical dimension of self-transcendence which is reflected in changes in behavior. Based on the results of the study, it can be concluded that in the perspective of students learning al-Islam to achieve the ideal dimension, namely self-transcendence.

Track and Field Pedagogy: Practices, Trends, and Students' Engagement in Middle Schools

The study was conducted to examine the pedagogical practices and development patterns of track and field education at Xin Ying Middle School, as well as its link to student engagement, and to use the findings to design an enhanced model for sports education. The study utilized a quantitative approach utilizing the descriptive comparative - correlational research design to understand the relationships between the variables presented in the statement of the problem. This approach was used to evaluate the answers of instructors and students and to present the study findings. The research was conducted in Xin Ying Middle School among 100 students and 30 teacher respondents. The research made use of a self-made questionnaire as the research instrument that includes all the necessary information as reflected in the objectives of the study. The findings suggested that there are low levels of assessment on the current situation of pedagogical practices across all indicators as assessed by the students; and according to the teachers, very low level in curriculum and teachers’ level, and low level in facilities and teaching quality. Also, the school do not follow the development trends in track and field education as the teaching platforms are outdated. The results from the level of students’ engagement as assessed by the students and the teachers shows that the students are overwhelmed with the course, do not find the course interesting, always feel like they’re not doing well in the course, are losing interest in the course, and worry a lot about matters related to track and field. The assessment of the students differs significantly based on their year level in the variables of the present situation of pedagogical practices, indicating that students from different class level has different experiences on the pedagogical practices of track and field teachers. There are no significant differences in the overall assessment of the teachers and that of the students in development trends based on their demographic profiles, and over-all assessment of the students on the present situation is significantly higher compared to teachers. There is no relationship between the overall assessment of development trends and the current situation of pedagogical practices in track and field education of the school. The study developed a strategic plan that will help fix the findings on the low level of teaching experiences, outdated curriculum for track and field physical education classes, poor teaching quality, and lack of technological equipment and facilities for teaching track and field education of middle school students.

Improving students' creative thinking in biology learning through Remap-TPS integrated flipped classroom

Implementing the Remap-TPS integrated flipped classroom has not yet been carried out to improve creative thinking skills in biology learning. This study aims to determine the effect of the Remap-TPS integrated flipped classroom model on students' creative thinking skills in biology learning. This study is a mixed method. The research design used was a pretest-posttest nonequivalent control group design. The research sample comprised 72 class X students at SMAN 9 Malang, East Java, Indonesia. They were divided into one experimental class and one control class. The Remap-TPS integrated flipped classroom was taught in the experimental class, while the TPS model was taught in the control class. Quantitative data was collected through pretest and posttest using essay question that refer to creative thinking indicators: curiosity, fluency, originality, elaboration, flexibility, divergent, messiness/risk taking and with others. This essay's questions have previously been tested to show valid and reliable results because Cronbach's alpha value is 0.778. Qualitative data is used together with quantitative data from the results of student answers. Analysis was carried out using the ANCOVA test with a significance level of 5%, then continued with the LSD test. Data is also explained qualitatively from the results of student answers. The study results show that the Remap-TPS integrated flipped classroom model affects students' creative thinking skills. This is proven by a significance value of 0.00<0.05. Therefore, the Remap-TPS integrated flipped classroom can be used as an alternative learning model to improve students' creative thinking in biology learning. Implementing the Remap-TPS integrated flipped classroom requires adapting learning instruments and tools to the learning model used and the skills measured to improve learning activities, especially in improving students' creative thinking skills.

MATHEMATICAL LITERACY SKILLS BY USING REALISTIC MATHEMATICS EDUCATION-BASED WORKSHEETS

This research aims to measure students' mathematical literacy skills after using e-worksheets based on the Realistic Mathematics Education (RME) Approach. This research uses a descriptive qualitative approach. Students in class VIII of SMP N 1 Talang Kelapa, each with low, medium, and high literacy skills, were the subjects of this research. The categorization of students is based on the number of mathematical literacy components resulting from student answers on the test. Data was collected through observation, tests, and interviews. The purpose of observation is to measure the implementation of learning through RME, and the test is to measure students' literacy skills. In data analysis, the elements that appear most frequently are communication, mathematization, and the use of symbolic, formal, and technical language operations. Component 1 appears when students write a statement containing information about a problem and representing the results obtained. Component 2 emerges when students create a mathematical model of the problem, and component 7 emerges when students use formal forms that conform to mathematical definitions and rules. The results of learning observations carried out using e-worksheets based on the RME approach show that learning can be said to be of good quality according to the established criteria.

Use of an Asynchronous Discussion Platform During the Pre-clerkship Curriculum: A Multiyear Retrospective Study.

Asynchronous online message boards (OMBs) allow users to write questions or comments and share them with an online group. While the use of OMBs has been associated with positive outcomes in several educational settings, their use has not been studied in pre-clerkship undergraduate medical education (UME). This multiyear, observational, longitudinal study examined patterns of OMB use in pre-clerkship UME. Descriptive statistics were used to report the number of students and instructors who logged on and contributed, the number of posts, instructor answers, post views, and the average time to answer. Patterns of use by first- and second-year medical students as well as students undergoing remote versus in-person learning were compared using Wilcoxon signed-rank tests. A total of 9870 posts were made to OMBs, initiated by 3869 student questions. There were 3078 total posts made by instructors and academic support staff and 1024 student answers to student questions. First-year medical students posted significantly more questions (149.83 vs. 83.7, p < 0.001), which resulted in significantly more instructor answers (125.0 vs. 59.1, p < 0.001). Modules during the remote learning period received more student questions (152.0 vs. 96.7, p < 0.001) and produced more instructor answers (123.8 vs. 74.7, p < 0.001) as compared to modules that took place during in-person learning. Online message boards represent a readily available tool to stimulate asynchronous discussion in pre-clerkship UME. First-year medical students and students during remote learning were more active on OMBs.

ANALYSIS OF STUDENTS' ERROR IN WORKING ON MATHEMATICS PROBLEMS BASED ON THE CIRCULAR MATERIAL BASED ON KASTOLAN THEORY

The purpose of this study is to describe the types of student errors in solving HOTS-based circle questions based on kastolan theory, then it will also be explored regarding the factors that cause errors, and the percentage of student errors when solving problems. The method that will be used is descriptive qualitative. The instruments in this study consisted of written tests, interviews, and documentation. Data analysis techniques include data reduction, presenting data, and drawing conclusions. The subjects in this study were 13 students from class VIII A of SMP Negeri 4 Randublatung in semester 2 of the 2022/2023 academic year. Then interviews will be conducted by taking 3 samples of student answers grouped based on types of conceptual, procedural, and technical errors. The results showed that the most dominant errors occurred in technical errors where errors were made in the counting process with a percentage of 69.23%. Student procedural errors were made due to the incompatibility of the steps in solving the questions which resulted in wrong answers, with a percentage of 53.84%. Students' conceptual errors were made because students misinterpreted concepts and incorrectly determined the problem solving formula, with a percentage of 46.15%. Factors that cause students to make mistakes in solving HOTS-based questions are: students are not careful in the process of calculating ranks, use formulas that do not meet the prerequisites of the formula, and incompatibility of steps in solving problems.Keywords: Error Analysis, Cricles, HOTS Type Questions, Kastolan Theory

Misconceptions of mathematics in higher education universities when learning with Google classroom based on learning styles and gender differences

The purpose of this study is to comprehensively describe the results of the analysis of the ability to understand concepts and misconceptions in terms of differences in learning styles, as well as gender differences. The data to be collected in this study is in the form of primary data and secondary data. The primary data is obtained from primary sources and secondary data is obtained from secondary sources. The primary source in this study is informants, namely students, and the secondary source is documentation of student test scores as an illustration of student abilities. The instruments in this study are student learning style tests and auxiliary instruments in the form of misconception diagnostic tests. Learning style test in the form of a questionnaire. This instrument is used to uncover visual, auditorial, and kinesthetic learning style variables. Misconception diagnostic tests use the Certainty of Response Index (CRI). The results of the CRI analysis based on student answer criteria are: (a) 5.83% of student problem solving do not know the concept (lucky guess); (c) 22.30% of the student problem solvers did not know the concept; (b) 50.18% of student problem solving mastered the concept well; and (d) 21.69% of student problem solving occurred misconceptions.

Analisis Kesulitan Belajar Matematika dalam Menyelesaikan Soal Cerita Peserta Didik Kelas 1

This study aims to determine the learning difficulties of students in terms of solving story problems in the mathematics subject of Addition material. This research was conducted at SD N Pati Wetan 01 with a total of 5 students. The type of research used is descriptive qualitative. While the source of data obtained using interviews, observations, documentation in the form of student answers. Newman's theory is used as a reference in the analysis of learners' learning difficulties. The result of the study was that all five subjects experienced some difficulties. like; 1) AZ has learning difficulties in the form of a lack of understanding of the content of the reading in the form of stories; 2) MF has a dislike of mathematics learning; 3) AR has difficulty solving story problems in terms of finding formulas and studying story problems; 4) NB has a lack of understanding in the content of the story problem and is able to solve the problem but the answer is not right; and AH has difficulty yet understanding the addition operation. Some difficulties are concluded to be a lack of understanding of the construction of mathematical models, a lack of understanding of addition operations, and a lack of precise answers from learners.

Penerapan Model Pembelajaran PBL Berbantuan Aplikasi Geogebra Untuk Meningkatkan Kemampuan Penalaran Matematis Siswa Kelas VIII

This research aims to: (1) improve students' mathematical reasoning abilities by applying the problem based learning model assisted by the Geogebra application in mathematics learning for class VIII students at SMP Negeri 3 Sunggal; (2) describe the process of completing student answers related to students' mathematical reasoning by applying the problem based learning model assisted by the Geogebra application. This research is Class Action Research. The subjects in this research were 28 students in class VIII of SMP Negeri 3 Sunggal. The results of the research show that: (1) students' mathematical reasoning can improve after learning by applying the problem based learning model assisted by the Geogebra application where the average student score in the cycle I reasoning ability test was 65.85, increasing to 85.39 in cycle II and classical completeness in the reasoning ability test in cycle I was 16 students (57.14%) increasing to 26 students (87.88%) in cycle II; (2) the process of students' answers in completing the mathematical reasoning ability test is in the good category, this can be seen from the students' answers which have been able to meet the indicators of mathematical reasoning ability. So it is concluded that the application of the Problem Based Learning learning model assisted by the Geogebra application can improve students' mathematical reasoning abilities.

Pengembangan Media Pembelajaran Matematika Articulate Storyline Terhadap Kemampuan Pemahaman Konsep Matematis Siswa di Kelas VIII-2 MTs Nurul Islam Indonesia Medan

This research aims to determine the validity, practicality, effectiveness and how the students' answers process in completing the conceptual understanding ability test of the developed Articulate Storyline. This type of research is ADDIE model development research. The subjects of this research were 15 students in class VIII-2. The research results showed that the validity of the media was 85% before revision and 98% after revision from material experts and 61.67% before revision and 98% after revision from media experts on very valid criteria. The practicality of the media has met practical criteria, based on teacher responses obtained at 100% and from student responses obtained at 92.36%. The effectiveness of the media has met the effective criteria in terms of classical student learning completeness reaching 86.67%, use of research time in accordance with the RPP, and student response of 91.67%. The N-Gain test result is 0.70 in the high category. For the student answer process on the ability test (pre-test) it was 38.89%, increasing to 46.67% on the final ability test (post-test). Increasing students' ability to understand mathematical concepts strengthens the development of Articulate Storyline mathematics learning media in the classroom learning process.

Studi kasus: Analisis kriteria konvergensi iterasi sederhana berdasarkan tebakan awal

The simple iteration material in the numerical methods course is material related to functions and derivatives. Apart from this, simple iteration material requires one or two initial guesses that do not require bracketing the roots. This method will produce a root approximation as a solution, which will show convergent or divergent results. The convergence criteria are influenced by the derived results and the initial guesses provided. Because of this, this research aims to analyze the results of student answers to prove the convergence criteria of a given simple iterative problem. The method used in this research is a case study, analyzing the results of the answers of five randomly selected students studying numerical methods courses. Based on the results of the analysis of the convergence criteria based on initial guesses, it was concluded that only 5 students could prove the convergence criteria correctly. In general, students made mistakes in deriving algebraic functions, carried out division operations, and incorrectly determined the convergence criteria because they only proved the possibility of the function. given so that students only focus on convergence criteria without carrying out iterative analysis.

Examining the Efficacy of ChatGPT in Marking Short-Answer Assessments in an Undergraduate Medical Program

Traditional approaches to marking short-answer questions face limitations in timeliness, scalability, inter-rater reliability, and faculty time costs. Harnessing generative artificial intelligence (AI) to address some of these shortcomings is attractive. This study aims to validate the use of ChatGPT for evaluating short-answer assessments in an undergraduate medical program. Ten questions from the pre-clerkship medical curriculum were randomly chosen, and for each, six previously marked student answers were collected. These sixty answers were evaluated by ChatGPT in July 2023 under four conditions: with both a rubric and standard, with only a standard, with only a rubric, and with neither. ChatGPT displayed good Spearman correlations with a single human assessor (r = 0.6–0.7, p &lt; 0.001) across all conditions, with the absence of a standard or rubric yielding the best correlation. Scoring differences were common (65–80%), but score adjustments of more than one point were less frequent (20–38%). Notably, the absence of a rubric resulted in systematically higher scores (p &lt; 0.001, partial η2 = 0.33). Our findings demonstrate that ChatGPT is a viable, though imperfect, assistant to human assessment, performing comparably to a single expert assessor. This study serves as a foundation for future research on AI-based assessment techniques with potential for further optimization and increased reliability.

Towards adaptive support for self‐regulated learning of causal relations: Evaluating four Dutch word vector models

Advances in computational language models increasingly enable adaptive support for self‐regulated learning (SRL) in digital learning environments (DLEs; eg, via automated feedback). However, the accuracy of those models is a common concern for educational stakeholders (eg, policymakers, researchers, teachers and learners themselves). We compared the accuracy of four Dutch language models (ie, spaCy medium, spaCy large, FastText and ConceptNet NumberBatch) in the context of secondary school students' learning of causal relations from expository texts, scaffolded by causal diagram completion. Since machine learning relies on human‐labelled data for the best results, we used a dataset with 10,193 students' causal diagram answers, compiled over a decade of research using a diagram completion intervention to enhance students' monitoring of their text comprehension. The language models were used in combination with four popular machine learning classifiers (ie, logistic regression, random forests, support vector machine and neural networks) to evaluate their performance on automatically scoring students' causal diagrams in terms of the correctness of events and their sequence (ie, the causal structure). Five performance metrics were studied, namely accuracy, precision, recall, F1 and the area under the curve of the receiver operating characteristic (ROC‐AUC). The spaCy medium model combined with the neural network classifier achieved the best performance for the correctness of causal events in four of the five metrics, while the ConceptNet NumberBatch model worked best for the correctness of the causal sequence. These evaluation results provide a criterion for model adoption to adaptively support SRL of causal relations in DLEs. Practitioner notesWhat is already known about this topic Accurate monitoring is a prerequisite for effective self‐regulation. Students struggle to accurately monitor their comprehension of causal relations in texts. Completing causal diagrams improves students' monitoring accuracy, but there is room for further improvement. Automatic scoring could be used to provide adaptive support during diagramming. What this paper adds Comparison of four Dutch word vector models combined with four machine learning classifiers for the automatic scoring of students' causal diagrams. Five performance metrics to evaluate the above solutions. Evaluation of the word vector models for estimating the semantic similarity between student and model answers. Implications for practice and/or policy High‐quality word vector models could (em)power adaptive support during causal diagramming via automatic scoring. The evaluated solutions can be embedded in digital learning environments (DLEs). Criteria for model adoption to adaptively support SRL of causal relations in DLEs. The increased saliency of (in)correct answers via automatic scoring might help to improve students' monitoring accuracy.

Choosing Objective and Non-objective Test as Instrument for Assessment of EFL Student Learning Outcomes

This research describes the type of questions both objective and non-objective tests, benefits, and weaknesses of EFL students’ learning outcomes. This research is a descriptive qualitative. The analysis shows that the written test can be used as a measuring instrument for knowing students’ abilities. The form of the written test consists of objective and non-objective. An objective test consists of multiple potential answers or responses for students to choose one including completion, multiple-choice, matching, short answer, and true-false test. Non-objective tests consist of essays/descriptions for students to compose or organize answers in their language including an essay in limited/restricted essay and free essay tests. Teachers/lecturers should consider aspects of making the tests. They have differences in measured learning outcomes, preparation of question items, sampling of learning materials, control of student answers, scoring, influence on the learning process, and reliability. However, both objective and non-objective tests also have several advantages and disadvantages.

A Trustworthy Automated Short-Answer Scoring System Using a New Dataset and Hybrid Transfer Learning Method

To measure the quality of student learning, teachers must conduct evaluations. One of the most efficient modes of evaluation is the short answer question. However, there can be inconsistencies in teacher-performed manual evaluations due to an excessive number of students, time demands, fatigue, etc. Consequently, teachers require a trustworthy system capable of autonomously and accurately evaluating student answers. Using hybrid transfer learning and student answer dataset, we aim to create a reliable automated short answer scoring system called Hybrid Transfer Learning for Automated Short Answer Scoring (HTL-ASAS). HTL-ASAS combines multiple tokenizers from a pretrained model with the bidirectional encoder representations from transformers. Based on our evaluation of the training model, we determined that HTL-ASAS has a higher evaluation accuracy than models used in previous studies. The accuracy of HTL-ASAS for datasets containing responses to questions pertaining to introductory information technology courses reaches 99.6%. With an accuracy close to one hundred percent, the developed model can undoubtedly serve as the foundation for a trustworthy ASAS system.