Construct Knowledge Research Articles

StructuGraphRAG: Structured Document-Informed Knowledge Graphs for Retrieval-Augmented Generation

Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external data sources beyond their training sets and querying predefined knowledge bases to generate accurate, context-rich responses. Most RAG implementations use vector similarity searches, but the effectiveness of this approach and the representation of knowledge bases remain underexplored. Emerging research suggests knowledge graphs as a promising solution. Therefore, this paper presents StructuGraphRAG, which leverages document structures to inform the extraction process and constructs knowledge graphs to enhance RAG for social science research, specifically using NSDUH datasets. Our method parses document structures to extract entities and relationships, constructing comprehensive and relevant knowledge graphs. Experimental results show that StructuGraphRAG outperforms traditional RAG methods in accuracy, comprehensiveness, and contextual relevance. This approach provides a robust tool for social science researchers, facilitating precise analysis of social determinants of health and justice, and underscores the potential of structured document-informed knowledge graph construction in AI and social science research.

Modeling Teachers’ Acceptance of Generative Artificial Intelligence Use in Higher Education: The Role of AI Literacy, Intelligent TPACK, and Perceived Trust

This study delves into the factors that drive teachers’ adoption of generative artificial intelligence (GenAI) technologies in higher education. Anchored by the technology acceptance model (TAM), the research expands its inquiry by integrating the constructs of intelligent technological pedagogical content knowledge (TPACK), AI literacy, and perceived trust. Data were gathered from a sample of 237 university teachers through a structured questionnaire. The study employed structural equation modeling (SEM) to determine the relationships among the constructs. The results revealed that both AI literacy and perceived ease were the most influential factors affecting teachers’ acceptance of GenAI. Notably, intelligent TPACK and perceived trust were found to be pivotal mediators in this relationship. The findings underscore the importance of fostering AI literacy and adapting intelligent TPACK frameworks to better equip educators in the age of AI. Furthermore, there is a clear need for targeted professional development initiatives focusing on practical training that enhances AI literacy. These programs should provide hands-on experience with GenAI tools, boosting educators’ confidence and ability to integrate them into their teaching practices.

Using the ibsr technique as a psychological intervention to alleviate student stress in biology learning: Impacts on motivation, knowledge construction, and cognitive anxiety

Learning difficulties are a common issue faced by students, with stress being a significant contributing factor. One psychological treatment that has been shown to effectively reduce stress is Inquiry-Based Stress Reduction (IBSR). The objective of this study is to integrate IBSR into a discovery learning strategy in Biology in the classroom, with the aim of increasing students' learning motivation and knowledge construction while reducing their learning difficulties and cognitive anxiety. This is quasi-experimental research that used a post-test non-equivalent control group design. The study involved 72 11th-grade science students from two different classes at one of the public high schools in Bandung City. One class, consisting of 36 students, received IBSR treatment, while the other class, also consisting of 36 students, did not. Both classes used a discovery learning framework for teaching. Data on motivation, learning difficulties, and cognitive anxiety were collected using a rating scale questionnaire with eight scales. Students' ability to construct knowledge was measured using the German Cognitive Load (GCL) instrument in the form of a written test with indicators taken from Mayer's cognitive taxonomy (2002) in the realm of understanding. The study found that incorporating IBSR techniques into learning strategies for the immune system material can reduce student stress and improve learning performance, motivation, and knowledge construction (GCL), while also decreasing learning difficulties and cognitive anxiety.

Social Diversity in Focus: Assessing the Impact of Socioeconomic Backgrounds and Work Experience on Psychological Well-Being and Academic Confidence Among German First-Year Medical Students

This investigation pioneers an examination of the scarcely explored terrain of social diversity in medical education, assessing the complex impacts of socioeconomic status (SES), prior working experiences, and completed apprenticeships on a spectrum of psychological and academic facets among first-year medical students (n = 336) in an urban university setting. By utilizing a systematic and detailed approach, the study illuminates prior anatomical knowledge and various psychological constructs, marking a significant stride into a domain where knowledge remains profoundly limited. Analyses indicated that SES significantly affects financial anxiety (F(4, 331) = 17.391, p < 0.001) and academic behavioral confidence (F(4, 331) = 4.323, p = 0.002). Students with prior working experience reported higher self-perceived clinical experience but lower A-level grades (t(279.459) = −6.690, p < 0.001), competence in natural sciences (t(321.045) = −3.178, p = 0.002), and online competence (t(319.429) = −2.026, p = 0.044). Those who completed an apprenticeship showed higher resilience, academic confidence, self-efficacy, and greater concerns about balancing studies and work (t values ranging from 2.020 to 3.158, p < 0.05). Correlation analysis revealed a positive relationship between resilience (RQS) and coping with academic stress (CAS) (r = 0.632, p < 0.001), as well as between resilience and academic behavioral confidence (ABC) (r = 0.608, p < 0.001). Negative correlations were observed between resilience, coping with academic stress, academic confidence, and cognitive test anxiety (CTA) (r values from −0.235 to −0.404, p < 0.001). The findings emphasize the need for tailored support for students from diverse SES backgrounds and with varying experiences. The study highlights the value of a comprehensive approach in medical education, considering the diverse backgrounds and experiences of students. Future research should explore the long-term impact of these factors on professional competencies and patient care, leveraging the diversity of the student body for a holistic educational experience.

A Systematic Literature Review: Emotional Intelligence, Positive Affect, and Customer Satisfaction in Tourism

Objective: To perform a rigorous systematic review of the literature, with the aim of identify the most relevant studies on emotional intelligence and positive affect and their relationship with customer satisfaction in the tourism industry, and a bibliometric analysis of scientific production to lay the foundations of such relationships. Theoretical Framework: This paper presents the key concepts and theories that underpin the research. Emotional intelligence, positive affect and customer satisfaction in the tourism industry are highlighted to provide a solid basis for understanding the context of the research. Method: The methodology used in this research is based on the Constructivist Knowledge Development Process (Proknow-C), which facilitates the organisation of a systematic literature review to select and analyse bibliographical references and generate the necessary knowledge. Results and Discussion: The resulting portfolio of 17 relevant articles in line with the object of the study made it possible to identify the main approaches proposed by the authors on this subject. In essence, the review of the literature showed a clear consensus on the relationship between the emotional intelligence and positive affect of service providers and customer satisfaction in the tourism industry. Research Implications: This research is useful for the academic community in conducting significant and relevant research on the study axes, laying the foundations to continue advancing in future lines of research. In addition, the results are profitable from a professional standpoint. Organizations in the tourism sector may reflect on and promote best practices in developing emotional and positive affect skills among their service staff given their influence on customer satisfaction. Originality/Value: This study contributes to the literature as scientific research on this subject remains scarce. Furthermore, the results can have an impact on the performance of tourism businesses and thus on the economic development of the destination.

The impact of perceived knowledge on marketing agility in the context of big data: role of deployment level

PurposeAgainst the backdrop of dynamic capabilities theory, this research examines the relationship between knowledge and marketing agility in the context of big data marketing analytics (BDMA). The relevant knowledge constructs under investigation are business/marketing, relational, technological and technology management. The level of BDMA deployment is also examined to determine its impact on these relationships.Design/methodology/approachA survey was used to gather data from marketing professionals working in firms with at least limited experience in big data (BD) deployment in the United States and Canada. The results were analyzed using partial least squares structural equation modeling (PLS-SEM) with a sample of 236 responses.FindingsThe results indicate that marketing professionals perceived the knowledge and marketing agility constructs differently than the previous research on IT professionals. The knowledge construct was perceived as a two-dimensional construct consisting of broad knowledge skills and specific technical knowledge skills. Only the broad knowledge skills construct was significantly related to the marketing agility construct, with progressively high predictive validity and relevance when the deployment of BDMA progresses.Originality/valueThe paper's originality stems from the different conceptualizations of the knowledge and marketing agility constructs due to the use of a novel sample of marketing professionals in this study. The research also contributes to the dynamic capabilities theory by emphasizing the critical role of vital knowledge when aiming to enhance marketing agility.

Prediction of the Future Trends of Housing Project Development with Modified Delphi Technique

This research was initiated to study the trend of the housing projects in the next ten years (2022-2031), with the applied Modified Delphi Technique. The research was conducted by interviewing five experts with more than ten years of knowledge and experience in design, construction, technology, location, and marketing. The gathered trends were applied to create questionnaires in order to conduct two rounds of surveys to assess the consensus level of ten experts with at least ten years of experience in the real estate industry, according to the consensus analysis method from the Modified Delphi Technique. Thirteen trends were found from the study. There are four design trends: more beautiful façade, soundproof wall, universal design furniture, and universal design house building. In addition, eco-friendly materials and modular construction systems were found to be construction trends while smart home device installation and active air flow technology were found to be technology trends. Regarding the trend of the project location, the projects tend to be located in areas expanding into the suburbs. Finally, four marketing trends were also reported: Virtual Reality utilization in sales presentation, advertising to reach more customers, inviting social media influencers to play a role in reviewing projects, providing credit consulting services and refunding of reservation money if a customer’s loan is not approved. The results of the study provide information to all parties involved in planning strategies and operating a business in developing housing estates in the future.

A method for predicting remaining useful life using enhanced Savitzky–Golay filter and improved deep learning framework

Ensuring operational integrity in large-scale equipment hinges on effective fault prediction and health management. Prognostics and health management (PHM) face the challenge of accurately predicting remaining useful life (RUL) using multivariate sensor data. Traditional methods often require extensive prior knowledge for indicator construction and processing. Deep learning offers a promising alternative. This study presents a multi-channel multi-scale deep learning approach. Initially, an improved Savitzky‒Golay filter (ISG) addresses challenges posed by large and rapidly changing data volumes, enhancing data preprocessing. Subsequently, a framework integrates convolutional neural networks (CNNs) with long short-term memory (LSTM) to capture hierarchical signal information and make integrated predictions. The CNN extracts spatial features from multi-channel input data, while the LSTM captures temporal dependencies. By fusing outputs from both components, the framework enhances predictive accuracy and robustness for complex operational datasets. Experimental validation on the C-MAPSS dataset tests various fusion methods and CNN depths, determining parameters and evaluating filtering effectiveness. Comparative analyses show promising performance, particularly under dynamic conditions. While not optimal for predicting multiple fault types, it outperforms classical algorithms, especially in single fault type prediction tasks.

Breaking Math Anxiety: A Success Story From an Indian Government School

Mathematics anxiety and fear among children pose significant educational challenges worldwide. This study examines the efficacy of a hybrid learning approach that combines digital game-based learning with hands-on activities to enhance mathematics engagement, reduce anxiety, and improve numeracy skills while fostering algebraic and mathematical thinking. The research was conducted at Government School, Ramagondanahalli, Bengaluru (RGHL), involving over 400 children aged 6-10 years from grades 1-5. Participants were primarily first-generation learners from economically disadvantaged backgrounds with limited access to educational resources. The intervention comprised weekly 70-minute sessions over six months, featuring the digital game "Magic Math Spell Caster" alongside modified traditional board games such as Snakes & Ladders, Bingo with Place Value Cards, and a custom Memory Card Game. The curriculum also incorporated activity worksheets with math manipulatives and practice sheets. The didactical approach underpinning the intervention was based on six key principles: Treating mathematics as a language to be spoken, promoting algebraic thinking; Structuring games into levels with well-defined learning objectives to scaffold mathematical thinking; Connecting concrete and abstract concepts to deepen understanding; Employing a hands-on approach to reinforce learning; Providing resources to every child to ensure equal access; Integrating assessments as digital interactive worksheets within gameplay. This approach allowed children to explore, make connections, and construct knowledge independently, fostering both algebraic and broader mathematical thinking skills. The program encouraged peer-to-peer learning by grouping children with different math proficiencies. Students progressed through game levels at their own pace, often exceeding curriculum expectations. This study contributes to the growing body of evidence supporting hybrid learning approaches in mathematics education for all children, emphasizing the development of robust mathematical and algebraic thinking skills.

CiteSpace에 기반한 중국 대운하 문화상품 디자인 특성 및 트렌드 분석 연구

This study will analyze the current state and trends in the field of the China Grand Canal cultural product design. By screening relevant literature from the CNKI database between 2014 and 2024, the study employs CiteSpace software to conduct bibliometric analysis and construct knowledge maps. The aim of this research is to uncover the key issues and emerging trends in the field of Grand Canal cultural product design, and to explore possible directions for its future development. Through co-occurrence analysis of keywords, analysis of author collaboration, and distribution of institutions, the study delves into the research dynamics and collaboration networks in this field. The findings suggest that although research on Grand Canal cultural product design has gradually increased since 2014, it remains largely exploratory, with relatively dispersed collaboration among researchers. Future development is likely to focus on interdisciplinary integration and the combination of regional cultural creativity to promote sustained progress in this field.

Role of Web-Based Learning in Teaching English: Pathway to Sustainable Development Goals (SDG)

Context: The Covid-19 pandemic has profoundly altered the global educational landscape, necessitating a rapid shift from traditional face-to-face learning to virtual environments. This transition has highlighted the essential role of digital platforms in modern education, making e-learning and e-resources crucial components of curricula. As education becomes increasingly digitalized, it presents new opportunities for reaching a broader audience and enhancing the learning experience. Objective: The objective of this paper is to investigate the impact of web-based learning on English education during the Covid-19 pandemic. It aims to explore how digital tools and platforms enhance content development and course design, thereby enriching the overall learning experience. Additionally, the paper seeks to evaluate the alignment of these digital advancements with the Sustainable Development Goals (SDGs), particularly focusing on promoting inclusive and equitable quality education. Theoretical Framework: The study is grounded in the constructivist learning theory, which posits that learners construct knowledge through experiences and interactions. This framework supports the integration of digital tools in education, suggesting that these tools facilitate active learning and knowledge construction. The paper also considers the principles of digital pedagogy and e-learning frameworks to provide a comprehensive understanding of how web-based learning complements traditional teaching methods. Methodology: The research employs a mixed-methods approach, combining qualitative and quantitative data collection and analysis. Surveys and interviews with educators and students provide insights into their experiences and perceptions of web-based learning. Additionally, an analysis of digital course materials and e-resources used in English education during the pandemic offers empirical data on the effectiveness and challenges of digital learning tools. Case studies of specific educational institutions implementing web-based learning are also included to illustrate practical applications and outcomes. Results and Discussion: The findings reveal that web-based learning has significantly transformed English education by making it more accessible and flexible. Digital tools have enhanced content development and course design, allowing for more interactive and engaging learning experiences. However, the transition to virtual learning also presents challenges, such as digital divide issues, varying levels of digital literacy among educators and students, and the need for effective digital pedagogy training. The discussion highlights the importance of addressing these challenges to maximize the benefits of web-based learning. Originality and Value: This paper contributes to the growing body of research on digital education by specifically focusing on English education during the Covid-19 pandemic. It provides original insights into how digital tools can be integrated within the constructivist learning theory framework to enhance educational outcomes. The study's emphasis on aligning digital advancements with the SDGs adds value by connecting educational innovations to global development goals. Implications and Conclusions: The research underscores the potential of web-based learning to transform traditional educational practices and promote inclusive and equitable quality education. The implications for educators and policymakers include the need for ongoing professional development in digital pedagogy, investment in digital infrastructure, and the creation of policies that support equitable access to digital learning resources. The paper concludes that while web-based learning presents numerous opportunities, addressing the accompanying challenges is crucial for achieving sustainable and impactful educational transformations.

Exploring the implicit meanings of 'cultural diversity': a critical conceptual analysis of commonly used approaches in medical education.

Existing approaches to cultural diversity in medical education may be implicitly based on different conceptualisations of culture. Research has demonstrated that such interpretations matter to practices and people concerned. We therefore sought to identify the different conceptualisations espoused by these approaches and investigated their implications for education. We critically reviewed 52 articles from eight top medical education journals and subjected these to a conceptual analysis. Via open coding, we looked for references to approaches, their objectives, implicit notions of culture, and to implementation practices. We iteratively developed themes from the collected findings. We identified several approaches to cultural diversity teaching that used four different ways to conceptualise cultural diversity: culture as 'fixed patient characteristic', as 'multiple fixed characteristics', as 'dynamic outcome impacting social interactions', and as 'power dynamics'. We discussed the assumptions underlying these different notions, and reflected upon limitations and implications for educational practice. The notion of 'cultural diversity' challenges learners' communication skills, touches upon inherent inequalities and impacts how the field constructs knowledge. This study adds insights into how inherent inequalities in biomedical knowledge construction are rooted in methodological, ontological, and epistemological principles. Although these insights carry laborious implications for educational implementation, educators can learn from first initiatives, such as: standardly include information on patients' multiple identities and lived experiences in case descriptions, stimulate more reflection on teachers' and students' own values and hierarchical position, acknowledge Western epistemological hegemony, explicitly include literature from diverse sources, and monitor diversity-integrated topics in the curriculum.

Augmented Reality as a Tool to Support the Connection Between Reality and Mathematical Knowledge: A Case for Teaching Parallel Relations of Planes in Space

In the 11th−grade Vietnamese Mathematics Curriculum, students learn about parallel relations between planes in space. This is cognitively challenging for many students. Studies have shown difficulties relating to limited spatial imagination and drawing representations. The teacher’s approach also causes difficulties for some students; for example, some teachers do not approach new knowledge from practice. These approaches lead students to learn math only in that class rather than to relate math knowledge to real life, whereas real-life objects can be good tools for illustrating knowledge of spatial geometry. This study uses an action research method using GeoGebra 3D Calculator software to design teaching situations about parallel relations of lines and planes in space. This study was conducted with 40 students in 11th grade in Long An Province, Vietnam. It was found that learning tasks can be designed to help students construct knowledge effectively and overcome difficulties. The results of this research show that AR software for 3D Geometry, in particular GeoGebra, creates a connection between reality and abstract knowledge about the parallel relations of lines and surfaces in space. The research also shows that the application of augmented reality in teaching helps students understand and test hypotheses, eliminate false hypotheses, and build new knowledge about parallel relations effectively.

Transformative Impact: Dramatic Arts for Grade 12 Academic Excellence

The study investigated the influence of dramatic arts on academic performance among Grade 12 students. The study was framed within the social constructivism theory, which posits that learning is an active, social process where students construct knowledge through interaction with their environment and peers. The study employed an interpretivist qualitative research methods to explore the transformative potential of dramatic arts, emphasising the impact on critical thinking, problem-solving, and proficient communication. Data from 117 students in Grade 12 who were part of a purposive sample were gathered using open-ended questionnaires, interviews, and classroom observations. The data was analysed through thematic analysis. The findings highlighted the positive impact of dramatic arts integration on academic performance, student engagement, empathy development, and communication skills. Participants reported enhanced critical thinking skills, deeper subject understanding, and a more meaningful relationship with academic subjects. The study also offered recommendations for educational institutions, including developing comprehensive programs incorporating dramatic arts, continual professional development for teachers, building robust assessment and evaluation systems, and collaboration with local theatre organisations and cultural institutions to enhance students’ understanding of dramatic arts.

Revolutionizing construction: A cutting-edge decision-making model for artificial intelligence implementation in sustainable building projects

This study examines how certain artificial intelligence (AI) drivers affect the industry's adoption of this technology in the construction industry. The research methods comprised a comprehensive analysis of previous studies to pinpoint the primary factors influencing AI adoption in the construction industry. Data collection was carried out through a well-structured survey involving relevant stakeholders in the building construction sector. The three main constructs of technological devices, advancement, and knowledge were found from the set of drivers with the technique of exploratory factor analysis. The deployment of AI in construction has the potential to improve health and safety and expedite project completion, as this research has evaluated. To figure out how these factors relate to the adoption of AI in the construction industry, partial least squares structural equation modeling was used. The study's conclusions showed that the influence of AI installation in the construction industry is reasonably significant thanks to the technology, advancement, and knowledge, contributing around 15 % of the effects that have been directly witnessed. The practical implications of AI for policy makers, engineers, and construction stakeholders are extensive and provide valuable insights for customized strategies aimed at using AI's potential to improve projects, promote sustainability, and elevate health and safety standards.

Examining workplace affordances within work-study programmes for becoming an engineer

PurposeWork-study programmes aim to support young adults transitioning from tertiary education to work and contribute to enhancing their employability. The purpose of this study is to provide a detailed analysis of the learning experiences of trainees in work-study programmes within the broad field of engineering.Design/methodology/approachThe data gathering procedures used interviews with participants of a specific work-study programme and conducting thematic analyses to identify and understand the motivations of these adults for enrolling in work-study programmes and their associated workplace learning experiences. Fifty-two alumni of electrical and logistics engineering programmes completed 12 months of a separate work-study programme and consented to participate in an hour-long interview. They elaborated upon their work-learn experiences to explicate their work-learn needs and challenges in those interviews.FindingsFindings include workplaces facilitated skills development through providing combinations of work tasks comprising both routine and novel work assignments; challenging circumstances at the workplace provided trainees with opportunities to develop adaptive capacities; and engaging in non-routine work processes fosters integration into the engineering workplace community.Originality/valueThe findings contribute to the existing literature by exemplifying how routine engineering activities are practical affordances through which engineering trainees construct knowledge and dispositions for engaging in challenging, non-routine engineering work. Such experiences are crucial in preparing trainees for advanced roles in logistics or electronic sectors.

Local community's engagement and enactment of social value from hydropower infrastructure

PurposeSocial needs of local community are highly essential in the context of public infrastructure and have an impact on their performance. This paper explores the local community subjectivity in interaction with primary stakeholders to deepen our understanding of social value and this category of misunderstood stakeholders.Design/methodology/approachThe paper presents a partnership framework that aims to help stakeholders be reflexive and construct knowledge about social value of the infrastructure. The empirical material includes an extensive review of the public infrastructure documents published between 1981 and 2021 and 13 interviews with key members of local community.FindingsThe main contribution of this study is an integrated model to study the social value of an infrastructure and a dynamic approach to study how a local community engages and enacts social value. The dynamic approach highlights three plans of stakeholder’s subjectivity, which are relational, representational and operational plans to promote inclusive stakeholder’s management (“of” and “for”).Originality/valueThe study combines an analytical and a theoretical framework to investigate the enactment of social value.

How do constructions with modal verbs develop in second language learners of English?

Abstract The study reported on in this paper uses data from a large, pseudolongitudinal corpus of second language (L2) learner writing to investigate how L2 knowledge of verb-argument constructions (VACs) develops from low-beginner to upper-intermediate proficiency levels. The focus is on learners from two L1 backgrounds (L1 German and L1 Spanish) and on a subset of VACs that contain modal auxiliaries in combination with lexical verbs (e.g., subject-modal-verb, as in I can cook). For each VAC, L1, and proficiency level, frequency lists of verbs were created and compared across datasets. Reference data on the same constructions was extracted from a corpus of L1 writing. Results suggest that modal VACs become more frequent, less predictable, more productive, and more aligned with L1 production as learner proficiency increases. The findings of this study help to expand our understanding of the processes that underlie L2 construction acquisition.

Embedding Building Information Modelling in the Construction Area: A Case within an Undergraduate Civil Engineering Program

Undergraduate programs face the challenge of staying up-to-date by responding to globalization, internationalization, and regionalization processes. Civil engineering programs should meet the requirements of the Architecture, Engineering, Construction, and Operation (AECO) industry. Building Information Modelling (BIM) is a methodology that involves shared digital representations of built assets to facilitate design, construction, and operation processes within the construction knowledge field. The present research describes a methodology with six mechanisms to develop and consolidate BIM-related competencies within the construction area from an undergraduate civil engineering program. It also explores students’ perceptions about the subjects within this area and their relationship with the training and reinforcement of the competencies. The study follows a descriptive scope with an action research design. The principal result is the methodology, which has six mechanisms: (1) BIM implementation into topics and syllabi; (2) use of collaborative platforms; (3) professor training programs; (4) establishment of student organizations; (5) development of a BIM application project; and (6) area and subject meetings. The validation process, which included professors, enrollment, employability and research rates, and the curricular proposal and students’ perceptions, revealed that the mechanisms could effectively support the development and reinforcement of BIM-related competencies.

The Impact of a Digital Game-Based AI Chatbot on Students’ Academic Performance, Higher-Order Thinking, and Behavioral Patterns in an Information Technology Curriculum

In the age of intelligence, information technology (IT) education has become the focus of attention in the education sector. However, traditional teaching methods fall short in motivating students and fostering higher-order thinking and have difficulty providing a personalized learning experience. Although AI chatbots can provide instant feedback as an innovative teaching tool, it is still challenging to fully enhance learner engagement. Based on this, this study developed a digital game-based AI chatbot system to enhance students’ learning experience through digital game-based learning strategies. This study utilized a quasi-experimental design with the experimental group using a digital game-based AI chatbot and the control group using a traditional AI chatbot. A comparison was made between the two groups concerning student learning performance in IT courses, higher-order thinking (including problem-solving, computational thinking, and creativity), learning motivation, and flow experience. In addition, the behavioral patterns of high-achieving and low-achieving students in the experimental group were analyzed. The results showed that the experimental group was significantly better than the control group in academic performance, problem-solving, computational thinking, learning motivation, and flow experience, but there was no significant difference in creativity tendency. Behavioral pattern analysis showed that high-achieving students in the experimental group showed more systematic learning strategies, while low-achieving students relied more on immediate feedback and external help, but both high- and low-achieving groups were able to actively talk to the AI chatbot and actively explore problem-solving strategies in the digital game. Therefore, AI chatbots based on digital games can be effectively used in IT courses to help students construct knowledge and develop higher-order thinking.