Task Analysis Research Articles

Policy analysis combining artificial intelligence and text mining technology in the perspective of educational informatization

In order to explore the application potential of artificial intelligence (AI) and text mining technology in educational policy analysis and evaluate their impact on the psychological perception of policy audiences, this study firstly introduces the application of AI and text mining technology in education. Secondly, it explores the application of psychological theories in educational policy analysis. Finally, this study constructs an educational policy text analysis model and verifies the feasibility of the optimized model through performance comparison experiments and case analysis. The experimental results show that the optimized model exhibits higher accuracy, recall rate, and F1 score compared to traditional models when handling educational policy text analysis tasks with different data volumes. This finding highlights the importance of optimizing models for specific tasks and the potential of improving the understanding and analysis capabilities of models for specific text types through careful adjustments. In addition, the application of psychological theories to the analysis of educational policy texts provides a new perspective and method for understanding the impact of policies on audience psychological states, which helps in formulating more effective and humanized policies. Therefore, the study has certain reference significance for the use of AI and text mining technology to support educational policy analysis and formulation, providing valuable insights and guidance for future related research and practice.

An Incongruent 2-Minute Stroop Task Alters the Response Time Performance in Semi-Elite Soccer Players: A Pilot Study

Introduction: Mental fatigue is a key factor in soccer that can affect physical performance. Mental fatigue protocols based on the Stroop test used in soccer involve extensive time, ranging from 10 to 30 min. Offering a protocol with a shorter duration that is more applicable in ecological situations seems to be an exciting challenge. Objective: To analyze the effects of a mental fatigue induction protocol (2 min Stroop test in its incongruent mode) on decision-making, response time, and technical execution accuracy in soccer players. Methods: A total of 18 semi-elite soccer male players, 25.83 (4.71) years from a Spanish soccer team, participated in this cross-sectional study. The 2 min incongruent Stroop test was used like mental fatigue protocol, followed by a specific analytical soccer task. The Wilcoxon signed-rank and Chi-squared tests were used to analyze the statistical differences. Results: A significant increase in participants’ response time after the fatigue protocol (p < 0.001; r = 0.878) was observed. Regarding the variables of correct decision (p = 0.457; r = 0.031) and technical execution accuracy (p = 1; r < 0.001), no significant differences were found. Additionally, no differences were observed between the first and second attempts of the 2 min incongruent Stroop test, in terms of execution accuracy, errors, or total words. Conclusions: The 2 min Stroop incongruent task may induce some degree of mental fatigue, leading to slower response time during certain technical tasks in semi-elite soccer players. However, this Stroop task was insufficient to promote significant changes in the accuracy of technical execution and the effectiveness of decision-making.

AWA-GCN: Enhancing Chinese sentiment analysis with a novel GCN model for Triplet and Quadruplet Extraction at SIGHAN 2024 dimABSA Task

This study presents the AWA-GCN (Attention-Weighted Affine with Graph Convolutional Networks) model, a new method designed exclusively for the SIGHAN 2024 Chinese Dimensional Aspect-Based Sentiment Analysis (dimABSA) Task. This test requires participants to identify sentiment triples and sentiment quadruples from textual data. The data comprises aspects, sentiment views, categories, and intensities across valence-arousal dimensions. Our model differs from existing models by utilizing a complex multi-layer attention mechanism within a GCN architecture, instead of relying on pipeline techniques or Grid Tagging Schemes (GTS). This design successfully captures the intricate interconnections among many sentiment components. The AWA-GCN model is very innovative in its ability to effectively handle quadruple extraction, which is a complex problem that has not been handled by traditional methods. Our approach enhances the understanding of aspect-sentiment interactions by including sophisticated techniques like word-level attention and semantic graph representations. The AWA- GCN model outperforms previous baselines in precision, recall, and F1 score on the dimABSA dataset, as demonstrated by empirical assessments. Additionally, the model exhibits significant enhancements in capturing the dimensional features of sentiment expressions. The results validate the models exceptional ability to handle the complex nuances necessary for successful sentiment analysis in simple Chinese.

AI MyData: Fostering Middle School Students’ Engagement with Machine Learning through an Ethics-Infused AI Curriculum

As initiatives on artificial intelligence (AI) education in K-12 learning contexts continues to evolve, researchers have developed curricula among other resources to promote AI across grade levels. Yet, there is a need for more effort regarding curriculum, tools, and pedagogy, as well as assessment techniques to popularize AI at the middle school level. Drawing on prior work, we created original curriculum activities with innovative use of existing technology, a new computational teaching tool, and a series of approaches and assessments to evaluate students’ engagement with the learning resources. Our curriculum called AI MyData comprises elements of ML and data science infused with ethical orientation. In this paper, we describe the novel AI curriculum and further discuss how we engaged students in learning and critiquing AI ethical dilemmas. We gathered data from two pilot studies conducted in the Northeast United States, one Artificial Intelligence Afterschool (AIA) program, and one virtual AI summer camp. The AIA program was carried out in a local public school with four middle school students aged 12 to 13; the program consisted of eleven two-hour sessions. The summer camp consisted of two-hour sessions over four consecutive days, with eighteen students aged 12 to 15. We facilitated both pilot programs with hands-on plugged and unplugged activities. The method of capturing data included artifact collection, structured interviews, written assessments, and a pre- to post-questionnaire tapping participants’ dispositions about AI and its societal implication. Participant artifacts, written assessments, survey, observation, and analysis of tasks completed revealed that the children improved in their knowledge of AI. In addition, the AI curriculum units and accompanying approaches developed for this study successfully engaged the participants, even without prior knowledge of related concepts. We also found an indication that introducing ethics of AI to adolescents will help their development as ethically responsive citizens. Our study results also indicate that lessons establishing links with students’ personal lives (e.g., letting students choose personally meaningful datasets) and societal implications using unplugged activities and interactive tools were particularly valuable for promoting AI and the integration of AI in middle school education across the subject domains and settings. Based on these results, we discuss our findings, identify their limitations, and propose future work.

Deep Learning for Text Sentiment Analysis: A Survey

Abstract. With the continuous improvement of many factors such as corpus, computing power, data scale, and laboratory conditions, how to quickly and accurately understand the emotional tendency in the text has become an important issue in many fields. The current state of affairs and the trajectory that deep learning is pursuing in the realm of text emotion analysis hold significant importance. This article first introduces the definition, importance and classification of emotional analysis, including the analysis of emotional polarity, emotional detection and fine-grained emotion. Subsequently, the key technologies of deep learning were discussed and the application of deep learning in natural language processing, especially LSTM, Bert, and their specific applications in emotional analysis within deep learning models. Then reveal the advantages and limitations of each model by comparing the performance of different deep learning models in emotional analysis tasks. Finally, in combination with current deep learning research, this study summarizes the challenges and research trends in the field of text emotional analysis.

Towards Holistic Functional Task Analysis

ABSTRACTTask analysis (TA) can contribute to work systems design, accident investigation, risk assessment, human error identification, planning, and training. Despite the advantages of existing sequential and hierarchical methods, they decompose tasks into their structure and focus on the order in which tasks are accomplished. They do not trace all interactions among elements/subtasks/operations at different levels. As the complexity of tasks increases, not keeping track of all interactions may result in poor, unwanted outcomes. This research introduces a different approach to TA that decomposes tasks into their constituent functions, describes the functionality of the overall work system, traces (dynamic nonlinear) interactions among functions, and highlights the role of functional variability in forming emergent outcomes. This approach to TA is called functional task analysis (FTA). A case study on nursing work was used to demonstrate the suitability of the FTA approach. The findings of this study show that the FTA approach contributes to task modeling by building a nonsequential, nonhierarchical functional model of a complex task considering dynamic, nonlinear interactions among functions. The FTA also contributes to task description by explaining different ways a task can be accomplished. It also increases the understanding, interpretation, and analysis of how changes in work conditions shape good/acceptable and poor/unacceptable outcomes. The FTA can complement the TA by adding some aspects, including functionality, nonlinearity, dynamics, and emergence, that the TA does not normally consider. The findings highlight how the functional approach to TA can be deployed as an alternative (or complement) to other task analysis methods.

GraphPCA: a fast and interpretable dimension reduction algorithm for spatial transcriptomics data

The rapid advancement of spatial transcriptomics technologies has revolutionized our understanding of cell heterogeneity and intricate spatial structures within tissues and organs. However, the high dimensionality and noise in spatial transcriptomic data present significant challenges for downstream data analyses. Here, we develop GraphPCA, an interpretable and quasi-linear dimension reduction algorithm that leverages the strengths of graphical regularization and principal component analysis. Comprehensive evaluations on simulated and multi-resolution spatial transcriptomic datasets generated from various platforms demonstrate the capacity of GraphPCA to enhance downstream analysis tasks including spatial domain detection, denoising, and trajectory inference compared to other state-of-the-art methods.

Challenges and Opportunities for Tool Adoption in Industrial UX Research Collaborations

UX research practitioners analyze qualitative data to comprehend users' needs and synthesize design implications for software systems. Collaborating with multiple stakeholders is inevitable for these professionals and adds additional pressure to their already laborious data analysis tasks. In this paper, we investigate how these practitioners' multi-stakeholder collaboration affects their data analysis practices. Specifically, we investigate the challenges qualitative UX research (QUXR) practitioners face, limitations of the current qualitative data analysis (QDA) support tools they use, and design implications for future QDA tools to address the limitations. Through semi-structured interviews combined with diagramming activities with thirteen industry QUXR practitioners, we have revealed that collaboration becomes a bigger challenge than data analysis and that it often leads to (1) preferring simple tools despite the QDA specialized tools' beneficial features and (2) wanting to triangulate their work to convince stakeholders. Finally, we have synthesized these results and suggest design implications for QDA support tools.

Determining skill mix and optimal multidisciplinary team composition: A scoping review.

Holistic care models aligned to population care needs are needed to help leaders shed pre-existing mindsets when determining skill mix and Multidisciplinary Team (MDT) composition. Using a PRISMA flowchart, a narrow eligibility criterion, and a research question, this scoping review resulted in 9 frameworks/models published between January 2000 and September 2023. Analysis showed common methodological elements such as a population needs-based approach, a systematic process, engagement, three or more professions reporting task or competency level analysis, change advocacy, and reliance on population and workforce supply data. Key system enablers were sponsorship, access to population needs-based and workforce supply data, a learning management system for MDT development, and health human resource policies and governance to drive health system redesign to distribute an equitable workforce. This scoping review offers health leaders and policy-makers options and next-step considerations to inspire fresh thinking for making evidence-informed decisions about skill mix and MDT composition.

When ChatGPT Meets Smart Contract Vulnerability Detection: How Far Are We?

With the development of blockchain technology, smart contracts have become an important component of blockchain applications. Despite their crucial role, the development of smart contracts may introduce vulnerabilities and potentially lead to severe consequences, such as financial losses. Meanwhile, large language models, represented by ChatGPT, have gained great attentions, showcasing great capabilities in code analysis tasks. In this paper, we presented an empirical study to investigate the performance of ChatGPT in identifying smart contract vulnerabilities. Initially, we evaluated ChatGPT's effectiveness using a publicly available smart contract dataset. Our findings discover that while ChatGPT achieves a high recall rate, its precision in pinpointing smart contract vulnerabilities is limited. Furthermore, ChatGPT's performance varies when detecting different vulnerability types. We delved into the root causes for the false positives generated by ChatGPT, and categorized them into four groups. Second, by comparing ChatGPT with other state-of-the-art smart contract vulnerability detection tools, we found that ChatGPT's F-score is lower than others for 3 out of the 7 vulnerabilities. In the case of the remaining 4 vulnerabilities, ChatGPT exhibits a slight advantage over these tools. Finally, we analyzed the limitation of ChatGPT in smart contract vulnerability detection, revealing that the robustness of ChatGPT in this field needs to be improved from two aspects: its uncertainty in answering questions; and the limited length of the detected code. In general, our research provides insights into the strengths and weaknesses of employing large language models, specifically ChatGPT, for the detection of smart contract vulnerabilities.

Sleep Management: The Use of Continuous Physiological Monitoring to Support Patient Self-Care

Circadian misalignment (CM) is a sleep disruption where an individual’s circadian rhythm and actual sleep-wake cycle are unsynchronized. CM is frequently misdiagnosed and difficult to treat but can adversely impact short-term and long-term health outcomes. CM often interacts bidirectionally with chronic conditions affecting cognitive and physical functionality. Continuous physiological monitoring (CPM) of the hormone melatonin would support real-time, patient-driven interventions to address CM. However, patient-driven self-care tasks involve complex information processing and decision-making. Effective CPM use requires situation awareness regarding current circadian health and projected future status, sufficient background knowledge to identify circadian intervention alternatives, and selection of appropriate alternatives given their current state. Melatonin data has characteristics distinct from biomarkers previously subject to CPM, introducing further challenges around data presentation. Task analysis efforts can identify the cognitive processes involved in five different tasks associated with a continuous melatonin monitor to identify necessary informational elements to include in interface design.

Wide human-like neural network incorporating driving styles for human-like driving intention analysis

Enhancing the synergy between autonomous and human-driven vehicles at the societal level requires understanding drivers’ behaviors and cognitive patterns, as well as conducting human-like driving intention analysis. To achieve this goal, this study designs a novel framework for analyzing human-like driving intention. Firstly, a spectral clustering method is employed to characterize driving styles. Secondly, a misclassification cost matrix is tailored to different driving needs. Finally, inspired by the complex neural networks found in the human brain, we develop a specialized lightweight neural network, termed the Width Human-like Neural Network (WNN), aimed at realizing personalized cognition and facilitating human-like decision-making in driving intention. Experimental studies and validation based on natural driving trajectory data from Kunming, China, demonstrate that the method accurately infers internal implicit driving intention from external explicit and observable driving behaviors, achieving a prediction accuracy of 99.8%. This framework strategically allocates limited computational resources to critical areas for autonomous vehicles and exemplifies best practices for improving neural network performance in driving intention analysis tasks.

Development and Evaluation of a Novel Resuscitation Teamwork Model for Out-of-Hospital Cardiac Arrest in the Emergency Department

Cardiopulmonary resuscitation (CPR) is critical for out-of-hospital cardiac arrest patients but is prone to rapid changes and errors. Effective teamwork and leadership are essential for high-quality CPR. We aimed to introduce the Airway-Circulation-Leadership-Support (A-C-L-S) teamwork model in the emergency department (ED) to address these challenges. The study comprised 2 phases. The development phase involved reviewing CPR videos, categorizing problems, and formulating strategies using the Systems Engineering Initiative for Patient Safety model. Resuscitation tasks were organized into A-C-L-S domains using hierarchical task analysis. Equipment and environmental deficits were optimized ergonomically with a pit-crew style arrangement. Mnemonics enhanced teamwork and leadership. The evaluation phase assessed postimplementation ED resuscitation team performance, focusing on adherence, timeliness, and quality of A-C-L-S tasks. The development phase produced a structured teamwork model, assigning tasks, tools, mnemonics, and positions based on A-C-L-S domains. The A-team manages the airway and optimizes end-tidal CO2 levels; the C-team focuses on high-quality chest compressions and defibrillation. Leadership coordinates resuscitation efforts using goal-directed mnemonics (DABCD2E3), whereas the S-team handles medications, timekeeping, and recording. The evaluation phase showed improvements in adherence and timeliness of A-C-L-S tasks, with sustained increases in chest compression fraction before mechanical CPR, from 67.2% preimplementation to 83.0% postimplementation, 89.1% after 1 year, and 86.1% after 2 years. Overall, chest compression fraction also improved from 81.7% to 88.6%, peaking at 92.2% after 1 year and maintaining 90.8% after 2 years. The A-C-L-S teamwork model is feasible, applicable, and effective. Further research is needed to assess its influence on patient outcomes.

Вчення Ісуса Христа щодо духовної та фізичної «нечистоти» людини

This research analyses the content, components and essence of one of the topics that causes a lot of debate in the Christian world. The topic of the place of the Law of God and the sanitary law given through Moses in the context of eating clean and unclean animals has generated much discussion and even controversy. The words of Jesus in Mark 7:14-23 seem to confirm that there is no need to observe the commandments concerning clean and unclean food, since all the commandments of the Old Testament were cancelled on the cross. What this biblical passage actually means is the main task of biblical exegesis and critical analysis of this passage. As a result of the analysis of literary sources, it was found that the interpretations of this text vary and are not unanimous. Given the fact that opinions on these texts differ and have different connotations, there is a need for careful research in order to understand with certainty what Jesus Christ meant by these words. It was found that the context of Mark 7:14-23 and the cross-referenced Bible passages indicate that Jesus’ words do not refer to the doctrine of clean and unclean food, but to the traditions of hand and utensil washing held by the Pharisees and scribes. A cultural and historical analysis of this passage shows that the commandment about clean and unclean food was given by God in the desert to remind the Israelites of the division of animals into certain categories, and that they should not adapt to the lives of other peoples who sacrificed such animals or considered them sacred. Later on, Jewish traditions distorted this teaching, which Jesus Christ pointed out to the Pharisees and scribes when they tried to reproach Him for not observing the doctrine of washed hands. After conducting a linguistic analysis, we found that the words of Jesus Christ in Mark 7:14-23 refer exclusively to the fact that the Jews considered food unclean because of unwashed hands and thus lost the true meaning of God’s commandment. In summary, we can note that the problem Jesus Christ highlights is the observance of small regulations that are not even taught in the Bible and because of which the Jewish teachers did not see the essence of God’s commandments: love of God and love of neighbor. That is why the Lord says that it is not the fact that a person is unclean, defiled, or lacking in holiness that makes him unclean, but rather that he does evil deeds that come from his heart. The study also revealed that Mark 7:14-23 does not refer to Christ’s abolition of the laws that regulated the eating of meat from «clean and unclean» animals. Such a position is neither reasonable nor biblically proven. Moreover, the laws of diet are much older than any other laws concerning the physical well-being of man (Genesis 7:2, 3).

Floating offshore wind – an overview of marine spatial planning and the needs of the industry

Abstract The International Energy Agency (IEA) Wind Task 49 aims to accelerate the commercialisation of floating wind. Work package 4 of the task analyses and incorporates the views of key stakeholders to ensure the Task is aligned with industrial needs. Work package 4 is broadly split into innovation management and marine spatial planning (MSP). The innovation management section evaluates the potential social, environmental and economic impact of floating wind innovations by surveying a multidisciplinary group of stakeholders to ask them to compare the potential impact of identified innovations. The survey results will inform a scored ranking of floating wind innovations, and the future research directions for the Task. In the MSP section representatives from partner countries are interviewed to assess their domestic offshore wind sector and discuss the approach the country has taken to MSP, with a focus on floating wind. The other explored parameters include MSP regulations, offshore wind policy and targets, supply chain capabilities, and environmental and fisheries impact assessments. A synthesis of what stakeholders perceive as impactful innovation, and an understanding of the direction of the industry and policy can be built from the two parts. This paper describes the methodology used to create this synthesis and findings from the first year of work are shared.

IRAQIDSAD: A Dataset for Benchmarking Sentiment Analysis Tasks on Iraqi Dialect based Texts

Sentiment analysis is a widely used technique in psychology, politics, and marketing that makes use of computational linguistics and natural language processing. The main focus of this research is a thorough literature assessment on sentiment analysis that is especially used with dialectical Arabic. Different dialects have different syntax, morphology, and grammar, which makes it difficult to classify polarity in dialectical Arabic. Our Systematic literature review investigates several aspects of sentiment analysis for dialectical Arabic in order to address these problems and support scholars working on similar projects. We identify the following phases as crucial: preprocessing, feature extraction, text annotation, and the chosen methodologies. We also present a newly corpus of 14,141 Iraqi dialect Facebook comments for benchmarking all of the text sentiment analysis and polarity classification on Iraqi texts. This corpus can be considered as an invaluable tool for sentiment analysis research in Arabic language setting

Deep Convolutional Backbone Comparison for Automated PET Image Quality Assessment.

Pretraining deep convolutional network mappings using natural images helps with medical imaging analysis tasks; this is important given the limited number of clinically-annotated medical images. Many two-dimensional pretrained backbone networks, however, are currently available. This work compared 18 different backbones from 5 architecture groups (pretrained on ImageNet) for the task of assessing [18F]FDG brain Positron Emission Transmission (PET) image quality (reconstructed at seven simulated doses), based on three clinical image quality metrics (global quality rating, pattern recognition, and diagnostic confidence). Using two-dimensional randomly sampled patches, up to eight patients (at three dose levels each) were used for training, with three separate patient datasets used for testing. Each backbone was trained five times with the same training and validation sets, and with six cross-folds. Training only the final fully connected layer (with ~6,000-20,000 trainable parameters) achieved a test mean-absolute-error of ~0.5 (which was within the intrinsic uncertainty of clinical scoring). To compare "classical" and over-parameterized regimes, the pretrained weights of the last 40% of the network layers were then unfrozen. The mean-absolute-error fell below 0.5 for 14 out of the 18 backbones assessed, including two that previously failed to train. Generally, backbones with residual units (e.g. DenseNets and ResNetV2s), were suited to this task, in terms of achieving the lowest mean-absolute-error at test time (~0.45 - 0.5). This proof-of-concept study shows that over-parameterization may also be important for automated PET image quality assessments.

Effectiveness of biopsychosocial approach for subacute neck pain among geriatrics

Background: The geriatric Population faces common health challenges such as Frailty and neck Pain, which increases the risk for adverse ADL. It leads to a greater level of disability & Headache risk, lower physical functioning and reduced quality of life. A Biopsychosocial Approach centred on activities, emphasizing the enhancement of Biological factors, Psychological factors and Social functional performance to achieve the goals of the Biopsychosocial Approach. This involves intensifying exercise training by leveraging the environment, conducting thorough task analysis, providing feedback and consistently repeating training sessions. Objective: To determine the effects of the Biopsychosocial Approach on Subacute Neck Pain in the geriatric population, focusing on pain, neck-specific disability and work status. Methods: 64 samples were randomly allocated into two groups. The experimental group received the Biopsychosocial Approach, which integrated biological, psychological and social aspects activity-centred, emphasizing repeated training sessions over 8 weeks. The control group underwent Conservative Management 3 days/week for the same duration. Pre and post-test assessments were conducted using the PCS, NDI and AQoL-8D. Results: The significant improvements in the experimental group compared to the control group were demonstrated by the Wilcoxon Signed Rank Test and Mann-Whitney Rank scores (p < 0.001). Specifically, participants in the experimental group experienced reduced neck pain, enhanced neck function, and improved quality outcomes. The results suggest that the Biopsychosocial Approach effectively addressed the multifaceted nature of pain. Conclusion: The study provides compelling evidence supporting Biopsychosocial in reducing neck pain and improving overall quality of life among geriatric populations.

DAPNet: A Dual-Attention Parallel Network for the Prediction of Ship Fuel Consumption Based on Multi-Source Data

The precise prediction of ship fuel consumption (SFC) not only serves to enhance energy efficiency to benefit shipping enterprises but also to provide quantitative foundations to aid in carbon emission reduction and ecological environment protection. On the other hand, SFC-related data represent typical multi-source characteristics and heterogeneous features, which lead to several methodological issues (e.g., feature alignment and feature fusion) in SFC prediction. Therefore, this paper proposes a dual-attention parallel network named DAPNet to solve the above issues. Firstly, we design a parallel network structure containing two kinds of long short-term memory (LSTM) and improved temporal convolutional networks (TCNs) for time-series analysis tasks so that different source data can be applied to suitable networks. Secondly, a local attention mechanism is included in each single parallel network so as to improve the ability of feature alignment from different-scale training data. Finally, global attention is employed for the fusion of all parallel networks, which can enrich representation features and simultaneously enhance the performance of SFC prediction. In experiments, DAPNet is compared with 10 methods, including baseline and attention models. The comparison results show that DAPNet and several of its variants obtain the highest accuracy in SFC prediction.

Research on digital discretion—The subjectification of street‐level work in public administration

AbstractThe article presents a systematic review of scholarly articles (n = 168) focused on digital discretion—how digital technologies affect the discretionary autonomy of street‐level bureaucrats. Two analytical tasks are performed concerning how digital transformation has affected (1) the relations between top‐down governing and the work of street‐level bureaucrats and (2) street‐level bureaucrats in the encounter with individuals. The documentation shows an expanding research area, and most articles showcase various subjectification effects when street‐level bureaucrats become screen‐ or system‐level bureaucrats. Street‐level bureaucrats are under increasing pressure from changing political rationalities consisting of streams of scientific knowledge, societal discourses, and the need for changes in governmental practices. The transformation carries political rationalities that fundamentally reshape value structures, organizing, and working methods of street‐level work. Still, the research area needs further development and consolidation. The reviewed research analyzes policies without considering the political content developed during policy initiation, formulation, and decision‐making. Instead, the research is characterized by a short‐sighted analytical perspective on how individual street‐level bureaucrats handle a changing technological development.