Short Answer Research Articles

The Use of Deep Learning in Open Learning: A Systematic Review (2019 to 2023)

No records of systematic reviews focused on deep learning in open learning have been found, although there has been some focus on other areas of machine learning. Through a systematic review, this study aimed to determine the trends, applied computational techniques, and areas of educational use of deep learning in open learning. The PRISMA protocol was used, and the Web of Science Core Collection (2019–2023) was searched. VOSviewer was used for networking and clustering, and in-depth analysis was employed to answer the research questions. Among the main results, it is worth noting that the scientific literature has focused on the following areas: (a) predicting student dropout, (b) automatic grading of short answers, and (c) recommending MOOC courses. It was concluded that pedagogical challenges have included the effective personalization of content for different learning styles and the need to address possible inherent biases in the datasets (e.g., socio-demographics, traces, competencies, learning objectives) used for training. Regarding deep learning, we observed an increase in the use of pre-trained models, the development of more efficient architectures, and the growing use of interpretability techniques. Technological challenges related to the use of large datasets, intensive computation, interpretability, knowledge transfer, ethics and bias, security, and cost of implementation were also evident.

Automated Grading Model with Adjusted Level of Lenience for Short Answer Questions using Natural Language Processing

Automated grading of short answer questions is a challenging task that involves understanding and evaluating free-text responses. This research presents an innovative model that combines the capabilities of the language model all-mpnet-base-v2 with a machine learning-based lenience adjustment mechanism to enhance the accuracy and fairness of automated grading systems. The proposed model utilizes all-mpnet-base-v2 for natural language understanding and feature extraction from student responses. To address the variability in acceptable answers and provide a fair grading system, a machine learning-based model is integrated to adjust the level of lenience dynamically. This dual approach ensures that the grading system can handle a wide range of responses while maintaining consistency and reliability. The experimental results demonstrate that the combination of all-mpnet-base-v2 with the lenience adjustment model significantly improves grading accuracy compared to traditional methods. This model represents a significant advancement in the field of educational technology, offering a robust solution for automated grading systems that can adapt to diverse educational contexts and requirements.

Framework for automation of short answer grading based on domain-specific pre-training

In the education sector, there is a growing need for efficient Automatic Short Answer Grading (ASAG) systems that require less training time, have faster inference, and provide higher accuracy. Over the past five years, researchers have made progress using deep learning for ASAG, but acquiring domain-specific labeled data remains a significant challenge. This study introduces an ASAG framework designed to learn from unlabeled domain-specific contexts while minimizing training and inference times. Our framework involves three main phases: 1) Building an unlabeled domain-specific corpus. 2) Training a pre-trained language model with this corpus. 3) Fine-tuning the pre-trained model with limited labeled domain-specific data. We explored various domain adaptations using two types of vocabulary during the pretraining stage. Our approach achieved an accuracy of 88.77% and an F1-score of 91.59% on the SPRAG dataset, improving state-of-the-art methods by 4%–5.7%. The models, including one trained from scratch with domain-specific data and vocabulary, showed robust performance, enhancing accuracy by 5.7% and F1-score by 4.84%. However, the framework's effectiveness in handling different languages or multilingual datasets remains to be explored. This framework's adaptability and efficiency enable educators to use AI for automated grading in various educational domains.

Do Androids Dream of Bad TV?: Un/originality in Neil Burger’s Voyagers

Critics did not take kindly to Neil Burger’s Voyager (2021). On Rotten Tomatoes, the film scored a dismal 25%, and the consensus is that it’s a trip best not taken: “It has a game cast and a premise ripe with potential, but Voyagers drifts in familiar orbit rather than fully exploring its intriguing themes.” This article seeks neither to reclaim the film as an unjustly neglected cinematic masterpiece nor to assert its importance in the canon of dystopian works. Rather, it treats Voyagers as a test case for exploring our own critical investment in the genre. Our aims are twofold. First, we argue that the film speaks to the dystopian genre’s fundamental distrust of future generations to make the best decisions. It effectively exposes the central irony that we presume to know best though we had signally failed to do right by our planet in the first place. Secondly, we reveal how unoriginal work can still point to new ways forward. By the end of the film, the Humanitas mission is back on course, following Zac’s (Fionn Whitehead) demise. Sela (Lily-Rose Depp) is surely right to wonder, to Christopher (Tye Sheridan), how they should ensure that mutiny doesn’t recur. The short answer? They can’t—and they probably shouldn’t. The capacity for events, like those we witness in Voyagers, to recur—and many times over too—is at least partially responsible for the dystopian genre’s appeal and it contributes to the genre’s persistent ethical ruminations. This essay advances scholarship by suggesting that even the most derivative of cinema can offer profound insights into our world, in this case, how democracies work.

AI-Driven Patient Education in Chronic Kidney Disease: Evaluating Chatbot Responses against Clinical Guidelines.

Chronic kidney disease (CKD) patients can benefit from personalized education on lifestyle and nutrition management strategies to enhance healthcare outcomes. The potential use of chatbots, introduced in 2022, as a tool for educating CKD patients has been explored. A set of 15 questions on lifestyle modification and nutrition, derived from a thorough review of three specific KDIGO guidelines, were developed and posed in various formats, including original, paraphrased with different adverbs, incomplete sentences, and misspellings. Four versions of AI were used to answer these questions: ChatGPT 3.5 (March and September 2023 versions), ChatGPT 4, and Bard AI. Additionally, 20 questions on lifestyle modification and nutrition were derived from the NKF KDOQI guidelines for nutrition in CKD (2020 Update) and answered by four versions of chatbots. Nephrologists reviewed all answers for accuracy. ChatGPT 3.5 produced largely accurate responses across the different question complexities, with occasional misleading statements from the March version. The September 2023 version frequently cited its last update as September 2021 and did not provide specific references, while the November 2023 version did not provide any misleading information. ChatGPT 4 presented answers similar to 3.5 but with improved reference citations, though not always directly relevant. Bard AI, while largely accurate with pictorial representation at times, occasionally produced misleading statements and had inconsistent reference quality, although an improvement was noted over time. Bing AI from November 2023 had short answers without detailed elaboration and sometimes just answered "YES". Chatbots demonstrate potential as personalized educational tools for CKD that utilize layman's terms, deliver timely and rapid responses in multiple languages, and offer a conversational pattern advantageous for patient engagement. Despite improvements observed from March to November 2023, some answers remained potentially misleading. ChatGPT 4 offers some advantages over 3.5, although the differences are limited. Collaboration between healthcare professionals and AI developers is essential to improve healthcare delivery and ensure the safe incorporation of chatbots into patient care.

Innovating Web Probing: Comparing Written and Oral Answers to Open-Ended Probing Questions in a Smartphone Survey

Abstract Cognitive interviewing in the form of probing is key for developing methodologically sound survey questions. For a long time, probing was tied to the laboratory setting, making it difficult to achieve large sample sizes and creating a time-intensive undertaking for both researchers and participants. Web surveys paved the way for administering probing questions over the Internet in a time- and cost-efficient manner. In so-called web probing studies, respondents first answer a question and then they receive one or more open-ended questions about their response process, with requests for written answers. However, participants frequently provide very short or no answers at all to open-ended questions, in part because answering questions in writing is tedious. This is especially the case when the web survey is completed via a smartphone with a virtual on-screen keypad that shrinks the viewing space. In this study, we examine whether the problem of short and uninterpretable answers in web probing studies can be mitigated by asking respondents to complete the web survey on a smartphone and to record their answers via the built-in microphone. We conducted an experiment in a smartphone survey (N = 1,001), randomizing respondents to different communication modes (written or oral) for answering two comprehension probes about two questions on national identity and citizenship. The results indicate that probes with requests for oral answers produce four to five times more nonresponse than their written counterparts. However, oral answers contain about three times as many words, include about 0.3 more themes (first probing question only), and the proportion of clearly interpretable answers is about 6 percentage points higher (for the first probing question only). Nonetheless, both communication modes result in similar themes mentioned by respondents.

Enhancing Assessment towards Flexible Medical Education: A Deep Dive into Preclinical Short Answer Questions through Item Analysis

Short answer questions (SAQs) and other forms of similarly structured examination methods are employed as evaluation tools to gauge the competency of medical students at various levels of study. However, item analyses for these questions have rarely been conducted. Evaluating the quality of examination questions through item analysis ensures that stakeholders, especially those undergoing learning in various flexible pathways in medical education, are provided with reliable and relevant assessments, promoting effective learning and competency development. In this study, we performed item analyses on SAQs by extracting the passing index (PI) and discrimination index (DI) for each sub-question. Data were analysed using Microsoft Excel (Microsoft Corporation, United States) and Jeffreys’s Amazing Statistics Program (JASP) (University of Amsterdam, The Netherlands). Twentyseven sub-questions from five SAQs were analysed. The DI of the sub-questions ranged from 0.043 to 0.935 with a mean of 0.449 ± 0.223, while the PI returned a range of 0.012 to 0.971 with a mean value of 0.597 ± 0.246. In conclusion, the SAQs administered during a professional examination of preclinical medical students exhibited an acceptable range and mix of PI and DI values. However, improvements must be made to the sub-questions that return poor PI and DI values.

The role of answer content and length when preparing answers to questions

Research suggests that interlocutors manage the timing demands of conversation by preparing what they want to say early. In three experiments, we used a verbal question-answering task to investigate what aspects of their response speakers prepare early. In all three experiments, participants answered more quickly when the critical content (here, barks) necessary for answer preparation occurred early (e.g., Which animal barks and is also a common household pet?) rather than late (e.g., Which animal is a common household pet and also barks?). In the individual experiments, we found no convincing evidence that participants were slower to produce longer answers, consisting of multiple words, than shorter answers, consisting of a single word. There was also no interaction between these two factors. A combined analysis of the first two experiments confirmed this lack of interaction, and demonstrated that participants were faster to answer questions when the critical content was available early rather than late and when the answer was short rather than long. These findings provide tentative evidence for an account in which interlocutors prepare the content of their answer as soon as they can, but sometimes do not prepare its length (and thus form) until they are ready to speak.

Stress Resistance of Personality in the Conditions of Organizational Culture in Ukraine. Specific Dependent Phenomena

So far, the focus of safety psychology, coping strategies, and occupational safety has been predominantly on physical factors and self-regulation tools. However, this article outlines the poorly researched neuro-dependent phenomena of Ukrainian organizational culture, where parallel new proactive and old reactive tendencies are observed. The purpose of this article is to identify the main neurodependent destructive tools of deceptive psychological self-protection in the context of contemporary organizational culture. These phenomena proved to be dependent on both general and personal culture, through which the instincts of psychological self-preservation and primitive unconscious defenses such as shame, guilt, excessive responsibility, competition avoidance, mythological attitudes, rituals, etc. are refracted. Methods of sociological survey by means of posing provocative questions with short answer time, intervisional and independent observations of production teams (with the subsequent neurointerpretative analysis) allowed to make a number of important conclusions. The main ones are the objectification and explanation of two intensions of Ukrainian organization culture, the determination of neuro-markers of destructive manifestations of personal deontological culture and the conclusion of a systematizing table of the stages of development of organization culture with procedural-attributive and neurodestructive explication. Also in the conclusions by psychological and pedagogical modeling and expedient selection of tools the authors concluded a set of recommendations for the acquisition of stress resistance in the context of the culture of the organization. The article can become a theoretical basis for the development of effective training programs and non-invasive neuropsychological tools for the correction of neurocultural deviations.

Are healing abutments being reused in periodontics residency programs in the United States? A survey-based study.

Recent studies indicate that reusing healing abutments (HAs) may pose a risk of biomaterial cross contamination among patients. The intent is to investigate whether postgraduate periodontics residency programs in the United States are reusing dental implant HAs and determine if there is a standardization in the decontamination and sterilization protocol of used HAs. An electronic survey consisting of-seven multiple choice and/or short answer questions pertaining to the re-use of HAs among postdoctoral periodontics programs was sent to program directors of 57 accredited dental schools in the United States via an online survey system (Qualtrics). Three follow-up remainder emails were sent to programs that did not respond after over a 6-month period. Data were analyzed using descriptive statistics. Of the 57 postdoctoral periodontics program directors contacted, only 14 responded with three programs (3/14, 21%) reported reusing HAs. Approximately, 46% stated their residents place dental implants in two stages, while ∼54% stated they used a one-stage protocol indicating varied time exposure of HA to the oral cavity. Even in a two-stage protocol, the extended time HA remained in situ varied from 4 weeks to 6 months. Each program reusing HAs employed a distinct decontamination approach highlighting a notable lack of standardization in practices. The findings from our study suggest that a minority of residency programs in the United States are reusing HAs. However, the limited number of responses leaves uncertainty regarding whether our findings underestimate the prevalence of this practice and accurately reflect the reality. Among those re-using HAs, there seems to be a lack of standardization in their decontamination, potentially leading to cross-contamination of residual biomaterial among patients.

Ostomy Care Nurses' Knowledge and Practice Related to Prevention and Management of Parastomal Hernias in Adults: A Nationwide Survey of UK Stoma Care Nurses.

The purpose of this study was to describe the knowledge and practices of ostomy care nurses related to the United Kingdom's Association of Stoma Care Nurses (ASCN) 2016 guidelines for prevention and management of parastomal hernia (PSH) in adults. Cross-sectional descriptive study. The target population was approximately 300 stoma care nurses; 120 useable responses to the survey were received, reflecting a response rate of approximately 40%. A 31-item questionnaire was developed for the purposes of this study, consisting of multiple choice and short answer questions grouped into 2 sections; demographics, and knowledge and practices. The questionnaire was distributed to members of the ASCN who work with adults via an online survey platform with the aim of reaching as many respondents as possible. The Chi-square test was used to determine relationships between the nominal demographic data and the nominal knowledge and practices data. Almost two-thirds of respondents (65%, n =78) rated their knowledge relating to prevention and management of PSH as good or excellent. Nevertheless, 79.8% (n=95) indicated they needed additional education to improve their knowledge and practice related to prevention of PSH. Those who rated their knowledge as excellent or good were significantly more likely to be aware of the guidelines compared to those who ranked their knowledge as average or poor. Study findings suggest variability in knowledge among UK stoma care nurses, along with a desire for additional education in this area of care.

Teaching IELTS Reading Skills

This research describes the teaching of IELTS Reading for students. This research is library research. The analysis shows that the IELTS reading test evaluates participants' understanding of information and language, requiring them to synthesize, interpret, and respond to information. The test consists of 14 types of questions, including Choosing a Title, True False Not Given / Yes No Not Given, Matching Features, Matching Headings, Matching Paragraph Information, Matching Sentence Endings, Sentence Completion, List Selection, Multiple Choice, Short Answer, Summary Completion, Flow Chart Completion, Diagram Completion, and Table Completion. The resulting test is graded on a band scale from range from 0 (did not take the test) to 9 (proficient in English) which indicates students' understanding and ability to read in English. Understanding the types of questions on the IELTS is crucial for students to prepare for the test. However, the test requires precise abilities for success. Teachers can create lesson plans for teaching Reading IELTS to help students prepare for the test and prepare them for the test. To answer IELTS Reading questions, students need fast and accurate reading skills and the right strategy. Teaching reading skills for the IELTS test can be challenging, but several strategies can help teachers structure effective teaching. These include understanding the test format, analyzing previous questions, building academic vocabulary, teaching active reading, practicing explaining the main idea, teaching skimming and scanning techniques, managing class discussion and analysis, practicing with varied reading material, using an integrated approach, giving constructive feedback, simulating reading tests, giving homework, training students to compose an outline, and promoting flexibility in learning.

A psychometric evaluation of an item bank for an English reading comprehension tool using Rasch analysis

This study reports the psychometric evaluation of an item bank for an Assessment for Learning (AfL) tool to assess primary school students’ reading comprehension skills. A pool of 46 primary 1 to 6 reading passages and their accompanying 522 multiple choice and short answer items were developed based on the Progress in International Reading Literacy Study (PIRLS) assessment framework. They were field-tested at 27 schools in Singapore involving 9834 students aged between 7 and 13. Four main comprehension processes outlined in PIRLS were assessed: focusing on and retrieving explicitly stated information, making straightforward inferences, interpreting and integrating ideas and information, and evaluating and critiquing content and textual elements. Rasch analysis was employed to examine students’ item response patterns for (1) model and item fit; (2) differential item functioning (DIF) about gender and test platform used; (3) local item dependence (LID) within and amongst reading passages; and (4) distractor issues about options within the multiple-choice-type items. Results showed that the data adequately fit the unidimensional Rasch model across all test levels with good internal consistency. Psychometric issues found amongst items were primarily related to ill-functioning distractors and local dependence on items. Problematic items identified were reviewed and subsequently amended by a panel of assessment professionals for future recalibration. This psychometrically and theoretically sound item bank is envisaged to be valuable to developing comprehensive classroom AfL tools that provide information for the English reading comprehension instructional design in the Singaporean context.

Modeling Short Answer Grading Performance Improvement by GPT Augmentation Data

Modeling Short Answer Grading Performance Improvement by GPT Augmentation Data

Retrieval Practice “in the Wild”: Teachers' Reported Use of Retrieval Practice in the Classroom

AbstractRetrieval practice has been shown to be an effective and efficient way to enhance learning and which has led researchers to call for retrieval practice to be part of teachers' regular repertoire of activities within a classroom. Recent policy changes in England have seen retrieval practice being encouraged and emphasized as a strategy that teachers should use in their practice. However, much of the research to support this has been conducted under controlled studies both in laboratory and classroom settings. Therefore, in the present study, we report on how teachers in England are implementing retrieval practice “in the wild”—in their classrooms outside of a controlled study. Findings indicate that teachers are using retrieval practice regularly in the classroom, even if it is not part of a mandatory school policy, with quizzes and short answer questions being the most reported format used. Additionally, teachers are motivated to use retrieval practice beyond the direct benefit of the testing effect.

Optimalisasi Pembelajaran Melalui Pelatihan Pembuatan Media Classpoint bagi Guru Sekolah Dasar

This community service aims to provide guidance to teachers to optimize learning by creating learning media through the Classpoint application. The implementation of this community service activity is done face-to-face (offline), while adhering to applicable health protocols. The method of implementing community service includes problem identification, presentation by the team of lecturers, question and answer sessions and discussions, as well as direct assistance in the process of making interactive Classpoint media. The media developed through the Classpoint application is expected to motivate students to learn and increase their participation in building knowledge. Training at State Elementary School 14 Cakranegara went smoothly with the assistance of 5 members of the community service team and 2 students who guided 10 participants, thus enabling them to overcome obstacles quickly. The speakers were also highly communicative, providing step-by-step guidance, and ensuring that each participant understood the steps before moving on to the next stage. During the training, the five types of Classpoint application features, such as multiple choice, word cloud, short answer, slide description, and image upload, could be effectively applied.

Empowering Educators: Automated Short Answer Grading with Inconsistency Check and Feedback Integration using Machine Learning

Empowering Educators: Automated Short Answer Grading with Inconsistency Check and Feedback Integration using Machine Learning

Pattern of SAQ Used in MBBS First Professional Anatomy Question Papers of Public Universities of Bangladesh

Introduction: Assessment is a very important method of measurement of medical education. Anatomy is an essential part of undergraduate medical curriculum. Short answer question (SAQ) has a better content coverage as compared to long essay question. Objective: To be assess the pattern of SAQ in MBBS first professional written anatomy question papers of public universities of Bangladesh. Method: The cross-sectional study was conducted at Armed Forces Medical College in the department of Anatomy, Dhaka Cantonment. For this study, SAQ papers of anatomy of nine first professional MBBS examinations of Bangladesh University of Professionals (BUP), Dhaka University (DU) and Chittagong University (CU) from May 2017 to November 2021were collected. These were classified as parts and segments. Each segment was categorized as definition, draw and label, unique and open type. They werecalculated as number of segments as well as total weightage. Result: On analysis it was found that the percentage of weightage of definition type questions of BUP, DU and CU were 3.53±2.03, 2.43±1.42 and 2.89±1.12; draw and label type 12.84±4.44, 15.98±3.13,17.053±.65; unique type 24.16±9.88,31.33±6.14, 26.47±3.84 and for open type 56.13±4.77,60.72±5.15, 53.73+5.29. Significant difference was found in draw and label type question in between BUP and CU, in unique type question in between BUP and DU and DU and CU, in open type question in between DU and CU. Conclusion: Different types of SAQ are used to determine the level of cognitive domain. Proper distribution of types of SAQ shall ensure the proportion of these domain mentioned in the curriculum. JAFMC Bangladesh. Vol 19, No 2(December) 2023: 7-11

An exercise-based international polymer syllabus

Abstract The IUPAC Subcommittee on Polymer Education has been pursuing the development of a compact syllabus covering the essential topics required for a tertiary education in polymer science, with numerical and short answer exercises addressing each topic. The primary goal of the document is to provide a framework for a complete course made freely available worldwide so that any educator can implement a professionally-curated course in polymer science for their students without needing expensive textbooks or reliable internet access. An important secondary goal is to popularize the use of approved IUPAC terminology in polymer science by using it consistently throughout the document and providing references to IUPAC source documents. Professor Melissa Chin Han Chan was an active and enthusiastic participant in the project who played a significant role in its design and implementation. The late Professor Richard ‘Dick’ Jones also had a keen interest in the project and had a great influence on its direction and structure. This brief note is dedicated to these two illustrious polymer scientists.

SPRAG: building and benchmarking a Short Programming-Related Answer Grading dataset

SPRAG: building and benchmarking a Short Programming-Related Answer Grading dataset