Online Question Research Articles

Development and Evaluation of Online Question Answering Information Management System

Development and Evaluation of Online Question Answering Information Management System

The Comparative Performance of Large Language Models on the Hand Surgery Self-Assessment Examination.

Generative artificial intelligence (AI) models have emerged as capable of producing human-like responses and have showcased their potential in general medical specialties. This study explores the performance of AI systems on the American Society for Surgery of the Hand (ASSH) Self-Assessment Exams (SAE). ChatGPT 4.0 and Bing AI were evaluated on a set of multiple-choice questions drawn from the ASSH SAE online question bank spanning 5 years (2019-2023). Each system was evaluated with 999 questions. Images and video links were inserted into question prompts to allow for complete AI interpretation. The performance of both systems was standardized using the May 2023 version of ChatGPT 4.0 and Microsoft Bing AI, both of which had web browsing and image capabilities. ChatGPT 4.0 scored an average of 66.5% on the ASSH questions. Bing AI scored higher, with an average of 75.3%. Bing AI outperformed ChatGPT 4.0 by an average of 8.8%. As a benchmark, a minimum passing score of 50% was required for continuing medical education credit. Both ChatGPT 4.0 and Bing AI had poorer performance on video-type and image-type questions on analysis of variance testing. Responses from both models contained elements from sources such as PubMed, Journal of Hand Surgery, and American Academy of Orthopedic Surgeons. ChatGPT 4.0 with browsing and Bing AI can both be anticipated to achieve passing scores on the ASSH SAE. Generative AI, with its ability to provide logical responses and literature citations, presents a convincing argument for use as an interactive learning aid and educational tool.

Awareness, access, and adoption of natriuretic peptides for diagnosis of heart failure.

This survey investigates natriuretic peptide (NP) testing in community and hospital settings, assessing awareness, accessibility, and utilization. This investigator-initiated survey, conceived within the HFA of the European Society of Cardiology, comprised 14 questions. It underwent validation and pilot testing to ensure question readability and online system functionality. The survey was accessible for 87days, from 5 April 2023 to 1 July 2023 via a web platform. There were 751 healthcare professionals across 99 countries who responded. Of them, 92.5% had access to NPs testing in hospital whereas 34.3% had no access to NTproBNP in community settings. Access to point of care NP testing was uncommon (9.6%). Public insurance fully covered NPs testing in 31.0% of cases, with private insurance providing coverage in 37.9%. The majority (84.0%) of participants believed that the medical evidence supporting NPs testing was strong, and 54.7% considered it cost-effective. Also, 35.8% found access, awareness, and adoption to be in favour of NPs testing both in hospital and community settings. Strategies to optimize NP testing involved regular guideline updates (57.9%), prioritizing NPs testing for dyspnoea assessment (36.4%), and introducing clinician feedback mechanisms (21.2%). Notably, 40% lacked a community-based HF diagnostic pathway for referring high-NP patients for echocardiography and cardiology evaluation. This survey reveals NP awareness, access, and adoption across several countries. Highlighting the importance of community-based early heart failure diagnosis and optimizing HF diagnostic pathways remains a crucial, unmet opportunity to improve patient outcomes.

Artificial intelligence in orthopaedic education: A comparative analysis of ChatGPT and Bing AI's Orthopaedic In‐Training Examination performance

AbstractBackgroundThis study evaluated the performance of generative artificial intelligence (AI) models on the Orthopaedic In‐Training Examination (OITE), an annual exam administered to U.S. orthopaedic residency programs.MethodsChatGPT 3.5 and Bing AI GPT 4.0 were evaluated on standardised sets of multiple‐choice questions drawn from the American Academy of Orthopaedic Surgeons OITE online question bank spanning 5 years (2018–2022). A total of 1165 questions were posed to each AI system. The performance of both systems was standardised using the latest versions of ChatGPT 3.5 and Bing AI GPT 4.0. Historical data of resident scores taken from the annual OITE technical reports was used as a comparison.ResultsAcross the five datasets, ChatGPT 3.5 scored an average of 55.0% on the OITE questions. Bing AI GPT 4.0 scored higher with an average of 80.0%. In comparison, the average performance of orthopaedic residents in national accredited programs was 62.1%. Bing AI GPT 4.0 outperformed ChatGPT 3.5 and Accreditation Council for Graduate Medical Education examinees, and analysis of variance analysis demonstrated p < 0.001 among groups. The best performance was by Bing AI GPT 4.0 on OITE 2020.ConclusionGenerative AI can provide a logical context across answer responses through its in‐depth information searches and citation of resources. This combination presents a convincing argument for the possible uses of AI in medical education as an interactive learning aid.

INCEPT: A Framework for Duplicate Posts Classification with Combined Text Representations

Dealing with many of the problems related to the quality of textual content online involves identifying similar content. Algorithmic solutions for duplicate content classification typically rely on text vector representation, which maps textual information into a set of features. Ideally, this representation would capture all aspects of the underlying text, including length, word frequencies, syntax, and semantics. While recent advancements in text representation have led to improved performance, a comprehensive approach that explicitly incorporates all text features has not yet been proposed. In this study, we present the INCEPT framework that utilizes multiple representation methods to detect duplicate text pairs, taking advantage of their individual strengths. The core of our approach involves using a stacking ensemble of pairwise vector distance measurements that are computed from multiple text representation methods. A stacking classifier then utilizes these distance scores as input and learns to identify duplicate posts. We assess the proposed framework’s effectiveness in identifying duplicate posts in an online Question and Answer platform. By combining several text representation methods, INCEPT performs well in the duplicate posts classification task. Our experiments demonstrate that specific framework configurations outperform the accuracy scores obtained from individual text representation methods. Therefore, we also infer that no single text representation method can independently capture a text’s features.

In-depth analysis of ChatGPT’s performance based on specific signaling words and phrases in the question stem of 2377 USMLE step 1 style questions

ChatGPT has garnered attention as a multifaceted AI chatbot with potential applications in medicine. Despite intriguing preliminary findings in areas such as clinical management and patient education, there remains a substantial knowledge gap in comprehensively understanding the chances and limitations of ChatGPT’s capabilities, especially in medical test-taking and education. A total of n = 2,729 USMLE Step 1 practice questions were extracted from the Amboss question bank. After excluding 352 image-based questions, a total of 2,377 text-based questions were further categorized and entered manually into ChatGPT, and its responses were recorded. ChatGPT’s overall performance was analyzed based on question difficulty, category, and content with regards to specific signal words and phrases. ChatGPT achieved an overall accuracy rate of 55.8% in a total number of n = 2,377 USMLE Step 1 preparation questions obtained from the Amboss online question bank. It demonstrated a significant inverse correlation between question difficulty and performance with rs = -0.306; p < 0.001, maintaining comparable accuracy to the human user peer group across different levels of question difficulty. Notably, ChatGPT outperformed in serology-related questions (61.1% vs. 53.8%; p = 0.005) but struggled with ECG-related content (42.9% vs. 55.6%; p = 0.021). ChatGPT achieved statistically significant worse performances in pathophysiology-related question stems. (Signal phrase = “what is the most likely/probable cause”). ChatGPT performed consistent across various question categories and difficulty levels. These findings emphasize the need for further investigations to explore the potential and limitations of ChatGPT in medical examination and education.

Diagnosis disclosure patterns among patients with plasma cell disorders.

e19536 Background: Disclosing or withholding information relating to a precancer or cancer diagnosis – including plasma cell disorders (PCDs) like monoclonal gammopathy, smoldering myeloma, and multiple myeloma – across social networks may impact how patients cope with their diagnosis and prognosis. The purpose of this survey was to investigate diagnosis disclosure patterns among patients with PCDs and identify areas for interventions that effectively utilize social support to navigate cancer diagnoses. Methods: We invited participants with PCDs to answer a 34 question online survey about their diagnosis disclosure patterns and perceptions on the HealthTree Cure Hub between April and December 2024. De-identified aggregated responses were analyzed. Results: A total of 510 participants responded (84% with cancer and 15% with precancer). Almost all (98%) reported sharing their diagnosis (Table 1). The most frequent primary individuals to share with were a spouse, domestic partner, or significant other (60%) and friend (s) (10%). Common reasons that participants chose to share included expecting support (45%), empowering others/spreading awareness (31%), and feeling in control (29%). Most (79%) participants reported that sharing information (with the individual they shared the most with) had a positive impact in their coping, with only 4% reporting a negative effect. Study limitations include selection bias. Conclusions: Patients with PCDs have a variety of motivations for sharing their diagnosis and generally perceive disclosure among their primary social networks to be beneficial to their coping. Oncologists may promote coping by encouraging disclosure. [Table: see text]

Whole-cycle management of women with epilepsy of child-bearing age: ontology construction and application.

The effective management of epilepsy in women of child-bearing age necessitates a concerted effort from multidisciplinary teams. Nevertheless, there exists an inadequacy in the seamless exchange of knowledge among healthcare providers within this context. Consequently, it is imperative to enhance the availability of informatics resources and the development of decision support tools to address this issue comprehensively. The development of the Women with Epilepsy of Child-Bearing Age Ontology (WWECA) adhered to established ontology construction principles. The ontology's scope and universal terminology were initially established by the development team and subsequently subjected to external evaluation through a rapid Delphi consensus exercise involving domain experts. Additional entities and attribute annotation data were sourced from authoritative guideline documents and specialized terminology databases within the respective field. Furthermore, the ontology has played a pivotal role in steering the creation of an online question-and-answer system, which is actively employed and assessed by a diverse group of multidisciplinary healthcare providers. WWECA successfully integrated a total of 609 entities encompassing various facets related to the diagnosis and medication for women of child-bearing age afflicted with epilepsy. The ontology exhibited a maximum depth of 8 within its hierarchical structure. Each of these entities featured three fundamental attributes, namely Chinese labels, definitions, and synonyms. The evaluation of WWECA involved 35 experts from 10 different hospitals across China, resulting in a favorable consensus among the experts. Furthermore, the ontology-driven online question and answer system underwent evaluation by a panel of 10 experts, including neurologists, obstetricians, and gynecologists. This evaluation yielded an average rating of 4.2, signifying a positive reception and endorsement of the system's utility and effectiveness. Our ontology and the associated online question and answer system hold the potential to serve as a scalable assistant for healthcare providers engaged in the management of women with epilepsy (WWE). In the future, this developmental framework has the potential for broader application in the context of long-term management of more intricate chronic health conditions.

Educational Limitations of ChatGPT in Neurosurgery Board Preparation.

Objective This study evaluated the potential of Chat Generative Pre-trained Transformer (ChatGPT) as an educational tool for neurosurgery residents preparing for the American Board of Neurological Surgery (ABNS) primary examination. Methods Non-imaging questions from the Congress of Neurological Surgeons (CNS) Self-Assessment in Neurological Surgery(SANS) online question bank were input into ChatGPT. Accuracy was evaluated and compared to human performance across subcategories. To quantify ChatGPT's educational potential, the concordance and insight of explanations were assessed by multiple neurosurgical faculty. Associations among these metrics as well as question length were evaluated. Results ChatGPT had an accuracy of 50.4% (1,068/2,120), with the highest and lowest accuracies in the pharmacology (81.2%, 13/16) and vascular (32.9%, 91/277) subcategories, respectively. ChatGPT performed worse than humans overall, as well as in the functional, other, peripheral, radiology, spine, trauma, tumor, and vascular subcategories. There were no subjects in which ChatGPT performed better than humans and its accuracy was below that required to pass the exam. The mean concordance was 93.4% (198/212) and the mean insight score was 2.7. Accuracy was negatively associated with question length (R2=0.29, p=0.03) but positively associated with both concordance (p<0.001, q<0.001) and insight (p<0.001, q<0.001). Conclusions The current study provides the largest and most comprehensive assessment of the accuracy and explanatory quality of ChatGPT in answering ABNS primary exam questions. The findings demonstrate shortcomings regarding ChatGPT's ability to pass, let alone teach, the neurosurgical boards.

Responsiveness and minimal important change of the Family Reported Outcome Measure (FROM-16)

BackgroundThe FROM-16 is a generic family quality of life (QoL) instrument that measures the QoL impact of patients’ disease on their family members/partners. The study aimed to assess the responsiveness of FROM-16 to change and determine Minimal Important Change (MIC).MethodsResponsiveness and MIC for FROM-16 were assessed prospectively with patients and their family members recruited from outpatient departments of the University Hospital Wales and University Hospital Llandough, Cardiff, United Kingdom. Patients completed the EQ-5D-3L and a global severity question (GSQ) online at baseline and at 3-month follow-up. Family members completed FROM-16 at baseline and a Global Rating of Change (GRC) in addition to FROM-16 at follow-up. Responsiveness was assessed using the distribution-based (effect size-ES, standardized response mean -SRM) and anchor-based (area under the receiver operating characteristics curve ROC-AUC) approaches and by testing hypotheses on expected correlation strength between FROM-16 change score and patient assessment tools (GSQ and EQ-5D). Cohen’s criteria were used for assessing ES. The AUC ≥ 0.7 was considered a good measure of responsiveness. MIC was calculated using anchor-based (ROC analysis and adjusted predictive modelling) and distribution methods based on standard deviation (SD) and standard error of the measurement (SEM).ResultsEighty-three patients with 15 different health conditions and their relatives completed baseline and follow-up questionnaires and were included in the responsiveness analysis. The mean FROM-16 change over 3 months = 1.43 (SD = 4.98). The mean patient EQ-5D change over 3 months = −0.059 (SD = 0.14). The responsiveness analysis showed that the FROM-16 was responsive to change (ES = 0.2, SRM = 0.3; p < 0.01). The ES and SRM of FROM-16 change score ranged from small (ES = 0.2; SRM = 0.3) for the distribution-based method to large (ES = 0.8, SRM = 0.85) for anchor-based methods. The AUC value was above 0.7, indicating good responsiveness. There was a significant positive correlation between the FROM-16 change scores and the patient’s disease severity change scores (p < 0.001). The MIC analysis was based on data from 100 family members of 100 patients. The MIC value of 4 was suggested for FROM-16.ConclusionsThe results of this study confirm the longitudinal validity of FROM-16 which refers to the degree to which an instrument is able to measure change in the construct to be measured. The results yield a MIC value of 4 for FROM-16. These psychometric attributes of the FROM-16 instrument are useful in both clinical research as well as clinical practice.

CyberQ: Generating Questions and Answers for Cybersecurity Education Using Knowledge Graph-Augmented LLMs

Building a skilled cybersecurity workforce is paramount to building a safer digital world. However, the diverse skill set, constantly emerging vulnerabilities, and deployment of new cyber threats make learning cybersecurity challenging. Traditional education methods struggle to cope with cybersecurity's rapidly evolving landscape and keep students engaged and motivated. Different studies on students' behaviors show that an interactive mode of education by engaging through a question-answering system or dialoguing is one of the most effective learning methodologies. There is a strong need to create advanced AI-enabled education tools to promote interactive learning in cybersecurity. Unfortunately, there are no publicly available standard question-answer datasets to build such systems for students and novice learners to learn cybersecurity concepts, tools, and techniques. The education course material and online question banks are unstructured and need to be validated and updated by domain experts, which is tedious when done manually. In this paper, we propose CyberGen, a novel unification of large language models (LLMs) and knowledge graphs (KG) to generate the questions and answers for cybersecurity automatically. Augmenting the structured knowledge from knowledge graphs in prompts improves factual reasoning and reduces hallucinations in LLMs. We used the knowledge triples from cybersecurity knowledge graphs (AISecKG) to design prompts for ChatGPT and generate questions and answers using different prompting techniques. Our question-answer dataset, CyberQ, contains around 4k pairs of questions and answers. The domain expert manually evaluated the random samples for consistency and correctness. We train the generative model using the CyberQ dataset for question answering task.

Perceptions and use of evidence-based revision methods among undergraduate medical students.

To assess awareness, perceptions and use related to evidence-based revision methods by undergraduate medical students. The descriptive cross-sectional study was conducted in three medical colleges of Rawalpindi, Islamabad, Pakistan, from December 01, 2019, to January 31, 2020, after approval from the ethics review committee of Army Medical College, Rawalpindi. The sample comprised undergraduate medical students of either gender. Data was collected online using a 10-item standardised questionnaire. Students were asked about the revision methods they used routinely and their perceptions of conventional and evidence-based revision methods. Data was analysed using SPSS 23. Of the total 136 respondents, 92(67%) were females and 44(32.3%) were male students. The response from preclinical and clinical years was 67 (50.7%) and 69(49.2%), respectively. Highlighting was the most widely used revision method among students (70 (51%) students), followed by re-reading important points (65 (47.7%) students). 126 (92%) students had the opinion that conventional revision methods were effective learning tools. Only 52 (38.2%) students were aware of the term 'evidence-based revision methods'. Digital tools based on principles of evidence-based revision were used by a minority of students which included use of online question banks by 21 (15.4%) students, osmosis by 40 (29.4%) students, sketchy pharma by 35 (25%)students, flashcards by 19 (14%) and picmonic by only 3 (2.2%). More than 114 (80%) students responded that they wanted evidence-based revision methods to be incorporated into curriculum, and 116 (85%) students said they would like to have a workshop on these techniques. Most medical students were not aware of and were not using evidence-based revision methods, and relied on conventional revision tools. They were, however, eager to learn about newer revision strategies.

Association of perceived stress and sleep quality among medical students: the mediating role of anxiety and depression symptoms during COVID-19.

COVID-19 has intensified the influence on medical students by changing the lifestyle, online study and clinical practice which bring out series of stress, sleep disturbance and mental health problems. This cross-sectional study aim to explore the association between perceived stress and sleep quality among medical students and investigated whether anxiety and depression mediated this association during pandemic. A total of 1,021 medical students in two universities who were from Guangdong Province, China participated this study and from January to September 2020 through the online question are, with 28.80% reporting sleep disturbances. The medical students were finished various self-reported questionnaires, including the Perceived Stress Scale-10, Pittsburgh Sleep Quality Index, Generalized Anxiety Disorder-7 Scale, and Patient Health Questionnaire-9, the study found positive correlations among sleep quality, perceived stress, anxiety, and depression. The data was analyzed with The Amos 26.0 system. Result demonstrated that perceived stress was associated with poor sleep quality. Anxiety and depression partially mediated the association between perceived stress and poor sleep quality, explaining 73.08% of the association. This study's structural equation model offers a useful framework for assessing mechanisms mediating associations between perceived stress and sleep quality. The findings emphases the importance of addressing psychological factors in high-pressure situations, which can exacerbate sleep disturbances among medical students. It is important to screen the level of stress, mental health problems and investigate the risk factors of sleep quality among medical students during emergency public health events.

Knowledge transfer to aid social coding: The case of Stack Overflow

Focused online question and answer (Q&A) communities aid social coding. Despite the growing importance of social coding, knowledge transfer in this context remains under-researched. Our primary objective is to understand the knowledge transfer process in this context. We conceptualize knowledge transfer as a process that is impacted by the prior knowledge transfer interactions (network) among participants and is augmented by gamification. We argue that social capital resulting from prior knowledge transfer network interactions impact answer quality. Moreover, we also argue that the relationship between social capital and answer quality is moderated by the complexity of the knowledge transferred. Hence, our models draw from multiple related research streams: online communities, knowledge transfer, social capital, and gamification. These models are empirically tested using data from Stack Overflow (SO), a popular online Q&A community that aids social coding. Our results help to understand knowledge transfer in Q&A communities that aid social coding. Moreover, our results have implications for research on other types of Q&A communities and can inform development of platforms to support online communities.

Innovative Question Bank Management System – Leveraging Digital Technology for Learning

Aim/Purpose: This paper introduces a web-based question bank management system (QBMS) designed for the "Ground Theory and Aviation Systems Engineering" course at Beihang University. The system, developed using Vue.js and Spring Boot, streamlines question management, practice, and online assessments. Methodology: A software development approach was utilised to design and develop a system to enhance student's knowledge and testing regarding aviation systems engineering. It incorporates a collaborative filtering algorithm to offer personalised practice recommendations, enhancing both teaching efficiency and student learning outcomes. Contribution: This research provides details to a robust educational tool, setting a foundation for future advancements in course-specific educational technology. The smart question management system can scale to all subject areas contributing the body of knowledge in smart education. Findings: The question bank management system addresses scalability issues of manual question management and introduces Spearman Correlation-based question filtering for a more adaptive learning experience. This was shown to be more effective and efficient for the learning and assessment environments.

Multiple Choice Question Difficulty Level Classification with Multi Class Confusion Matrix in the Online Question Bank of Education Gallery

Multiple Choice Question Difficulty Level Classification with Multi Class Confusion Matrix in the Online Question Bank of Education Gallery

THU001 Novel Interactive Text-messaging Curriculum For Endocrinology Board Review

Abstract Disclosure: P. Majety: None. A. Ajayi: None. A. Modest: None. M. Vamvini: Grant Recipient; Self; MV was supported by F32-DK126432, and Joslin Diabetes Center P&amp;F. J. Freed: None. Background: The ABIM certification exam is one of the measures to ensure that physicians have the clinical skills for good care delivery. The five-year average pass rate for the ABIM Endocrinology &amp; Metabolism subspecialty exam is 86%, relatively lower when compared to other subspecialties. The pass rate for first time test takers significantly decreased from a usual range of 84-91% over 2017-2020 to a nadir of 74% in 2021 compared to a mean of 84% for other medicine subspecialties. This represents the lowest pass rate in 2021 for any internal medicine subspecialty exam. Objectives: The primary purpose of our study was to assess the feasibility of a unique text messaging curriculum for endocrinology fellows and its utility in improving their knowledge. We also assessed their study habits and resources available to them for ABIM subspecialty exam preparation. Methods: In 2021, endocrinology fellows from 51 programs across the country were invited to participate in our curriculum. They completed a pre-test, joined a texting group via Remind application and received 1 multiple choice question daily (total n = 78). At the end of curriculum, fellows received a post-test questionnaire, and a feedback survey. After 15 weeks, they completed a post-test and survey. Paired results from pre- and post-test were compared. Results: A total of 89 fellows from 27 programs responded. Of these, 82 fellows, predominantly females (n=60; 73%), filled out the pre-test. On an average, 42 fellows (SD = 12) responded to the questions daily. Thirty fellows completed the post-test. The median number of correct responses on the pre-test was 5 (IQR 3-6), compared to 8 (IQR 6-9) in the post-test. There was a significant improvement (p-value &amp;lt;0.0001) in fellows’ performance in the post-test when compared with the pre-test following our intervention.Final feedback survey was filled out by 33 of them. Ninety-seven percent responded that they use question banks as a resource for exam preparation followed by PowerPoint presentations (52%), journals (48%), online videos (39%), textbooks (33%) and lecture notes (33%). 23 fellows (70%) preferred mobile friendly question bank applications; 5 fellows (15%) preferred online question banks available through company websites only. None of them preferred paper-based question banks.Nineteen of the 33 fellows (58%) found the curriculum very useful. 17 fellows (52%) said it served as a discussion tool sometimes, while 9 fellows (27%) said they used it as a discussion tool often. Thirty two out of 33 fellows (97%) responded that they would like to continue to receive a question daily for the rest of their fellowship. Conclusions: Text-messaging based curriculum for exam preparation is feasible and can improve test performance. Fellows find receiving a daily high yield multiple choice question via text-message as a useful tool for exam preparation. Presentation: Thursday, June 15, 2023

Feasibility Analysis of Laying Chicken Breedering Businesses in Marketing, Financial and Environmental Aspects

This type of research is qualitative research. The method used in this research is a combination of qualitative methods on marketing and environmental aspects and then quantitative methods on financial aspects. The qualitative research method is an interview process regarding the understanding of a matter to obtain data, information, texts of the views of respondents using various methodologies on a problem. The quantitative method is data retrieval based on the numerical calculation data collected and then added up. This study aims to obtain data and information as well as responses when the research is taking place with what is in the field. This writing method uses a centralized interview method by obtaining information by means of face-to-face or online question and answer between the researcher (as an interviewer with or without using an interview guide) and the subject under study and using observation or direct observation by looking at the cage situation, marketing and his finances. The results of the study show that (1) based on the marketing aspect, looking at the market, demand conditions are stable and continue to increase every year due to the egg sales strategy so that this business is feasible to run for 3 years. (2) based on the financial aspect, it can be seen that from 2020-2023 it has increased even though the number of chickens has decreased because the cost of buying seeds was not calculated in 2021, while in 2023 there was an addition of seeds so that it can be seen that profits have increased from 2020-2021. (3) based on environmental aspects it is very conducive, it is kept clean and healthy, so there are no problems in the environment because it has been anticipated by the farm so it is feasible to run. The conclusion of the study shows that marketing, financial and environmental aspects in the feasibility analysis of a small-scale laying hen business are feasible to run because they have fulfilled all the aspects carried out.

Value-Wise ConvNet for Transformer Models: An Infinite Time-Aware Recommender System

Finding the most suitable individual to answer a question using brief content has important usages, including the community of question answering systems and online recommender frameworks. However, one must tackle challenges: Disregarding the indispensable noise in short text contents, authors usually answer the input query with mismatched words that can negatively influence the textual relevance. Moreover, many vocabularies imply various alterations. Finally, not every expert is eager to answer an input query given the time constraint, named the reluctance dilemma. To overcome the challenges, we devise a novel embedding approach that constructs context-aware vectors. We then extract the knowledge domains out of the online contextual content. While we track user textual-temporal behavioral patterns via an infinite continuous-time module, we recommend a set of experts pertinent to the given query and willingly provide the response during the expected time. Experimental results on two real-world datasets of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">StackOverflow</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Yahoo</i> show that our online time-sensitive value-wise transformer can achieve higher effectiveness and efficiency versus other trending rivals in online expert recommendation systems. In addition, we empirically experience that Fourier transformers can automatically infer multi-aspect base signals and overpass manual discrete-time models in obtaining time-specific user profiles.

A deep learning-based approach for identifying unresolved questions on Stack Exchange Q &A communities through graph-based communication modelling

In recent years, online question–answer (Q &A) platforms, such as Stack Exchange (SE), have become increasingly popular for information and knowledge sharing. Despite the vast amount of information available on these platforms, many questions remain unresolved. In this work, we aim to address this issue by proposing a novel approach to identify unresolved questions in SE Q &A communities. Our approach utilises the graph structure of communication formed around a question by users to model the communication network surrounding it. We employ a property graph model and graph neural networks (GNNs), which can effectively capture both the structure of communication and the content of messages exchanged among users. By leveraging the power of graph representation and GNNs, our approach can effectively identify unresolved questions in SE communities. Experimental results on the complete historical data from three distinct Q &A communities demonstrate the superiority of our proposed approach over baseline methods that only consider the content of questions. Finally, our work represents a first but important step towards better understanding the factors that can affect questions becoming and remaining unresolved in SE communities.