Search

With businesses increasingly prioritizing data-driven decision making, the demand for business analysts is high and expected to grow. In response, many universities and institutions have developed courses and programs related to business analytics to prepare more graduates for careers in this field. Business analytics programs and educators consistently strive to achieve a high level of student learning success, ensuring competence in working in the business analytics field after graduation. In this study, we aim to examine key factors influencing student learning in business analytics, focusing on performance expectancy and satisfaction. We examined specific factors, including personal interest, career relevance expectancy, learning effort, and perceived course structure effectiveness, from perspectives related to both students and instructors. A research model was developed and empirically tested. The results showed that all factors significantly influenced both perceived academic performance and learning satisfaction. Additionally, personal interest and career relevance expectancy could significantly impact learning effort.

Recent studies claimed that the absence of a paradigm is a challenge to developing education for sustainable development and soft skills competencies. This integrative study examines stimulating these transferable and transversal competencies through constructivist approaches to teaching from the cognitive, social, radical, and critical perspectives. The study argues that the use of constructivist approaches to teaching can contribute to the achievement of education for sustainable development and soft skills competencies through the delegation of power from teachers/lecturers to students. This, in active and interactive classrooms, empowers students and builds their confidence to develop on the personal, academic, and professional levels. The use of the cognitive constructivist approach assists in developing competencies based on a clear understanding of the cognitive structures of students in a vibrant classroom environment. The use of the social constructivist approach assists in constructing individualized learning environment based on predetermined zones of proximal development in sociocultural contexts. The radical and critical constructivist approaches to teaching, through the rejection of conventional epistemologies, allow students the freedom to creatively address issues related to environmental, economic, and social sustainability. This becomes effective through the fostering of self and social awareness, challenging existing ideas, and provoking innovative thoughts that are necessary to shape a sustainable future.

Soft skills-based learning is very important to equip vocational high school students, one of which is entrepreneurship. This research aims to develop entrepreneurship learning through the "menara berkah" model. This research aims to develop entrepreneurship learning through the "menara berkah" model. This research is a type of development research including predevelopment stage of the model, model development, and validation or model testing stage. The research sample amounted to 25 people from two vocational high schools in Palembang and Yogyakarta. While data collection techniques using mixed methods and data analysis using statistical tests. Based on the construct of the model content assessment results obtained an average of 4.45, this score indicates that all aspects are components that are feasible to be used as material or content of entrepreneurship-based learning management models in the catering expertise competency. The "menara berkah" model is proven to be effective and applicable, with an average achievement of 4.76%, this indicates that this model can be used and can make it easier, especially in entrepreneurship-based learning. The results also show six competencies that must be possessed by students, namely: technical skills, decision making, organizational skills, marketing and financial management, risk taking, creativity, and innovation.

The capacity for mathematical reasoning, pivotal in grasping core math concepts, directly shapes a student's success in their mathematical studies. This study aimed to detail and analyzed how the search, solve, create, and share (SSCS) instructional framework impacts mathematical reasoning skills within the context of linear equations. We adopted a quasi-experimental research approach using a non-matching control group design. To gather data on mathematical reasoning proficiency, a validated and reliable essay-type test was employed. Data collection on mathematical reasoning abilities used an essay test instrument that has been valid and is reliable. This research involved 102 eighth grade students whereby they were selected by using a purposive sampling. To measure and describe the effect size, we utilized a specific method, yielding a result of 0.97. The t-test was employed to assess the influence of the SSCS learning model, and the significance value obtained was less than 0.05. The effect size, as determined, stands at 0.97, suggesting a substantial impact. The t-test results underscore a significant relationship between the SSCS learning model and the enhancement of mathematical reasoning abilities. This research delineates a framework for employing the SSCS model to enhance students' mathematical reasoning capabilities. It is evident that such reasoning abilities play a pivotal.

During attempts to prevent and control the COVID-19 pandemic in China, higher education programs shifted their traditional educational models to online models. This paper aimed to explore how Chinese universities organized online teaching and learning during the pandemic. It investigated the factors affecting the implementation of online teaching and provided policy recommendations for improving the quality of education in the post-pandemic period. The primary data for this study came from in-depth interviews with nine students and five teaching and administrative staff at eight major universities in mainland China. Literature was obtained in both English and Chinese from January 2020 to September 2021. Peer-reviewed journals, policy reports, and university documents regarding online education in Chinese universities were reviewed, and their challenges and countermeasures were investigated. The paper found that the implementation of online education was affected by various sources, including technologies, teachers' teaching skills, network information literacy, and students' learning motivations and self-directed learning skills. Based on the insiders' views, the paper suggested that to promote the quality of online education in the post-COVID-19 pandemic, higher education institutes and programs could develop their infrastructure construction, improve teachers' quality of teaching, and focus on students' learning motivations.

The main purpose of this study is to investigate the impact of English as a Foreign Language (EFL) teachers' instructional innovativeness on student engagement, with specific reference to behavioral and emotional aspects of engagement as perceived by the teachers. Given the ever-changing demands of contemporary education, this study underscores the importance of innovativeness and its influence on student engagement in L2 learning and teaching. The study adopted a cross-sectional design, utilizing a predictive moderated model, also assessing whether various teacher background variables such as educational status, gender, and field of graduation moderate the relationship between instructional innovativeness and student engagement. Data from 144 EFL teachers across Turkiye underwent analysis through partial least squares structural equation modeling (PLS-SEM). It was shown that instructional innovativeness significantly predicts both behavioral and emotional student engagement. However, only educational status, particularly differences between BA and PhD degrees, was found to moderate the impact on behavioral engagement, with no significant moderating effects identified for emotional engagement. In conclusion, this study highlights the merit of cultivating and fostering a culture of innovation among ELT practitioners to benefit students.

The limitations of traditional education models and the advancement of technology have revealed the need to transform the learning experience. The "Flipped Learning" approach, born out of this need, is a model where students study learning materials in advance and participate in more interactive and hands-on activities in the classroom. This research discusses how the Flipped Learning model can be combined with ChatGPT. ChatGPT is a language model developed by OpenAI, and it can interact with students thanks to its natural language processing capability. In this way, combined with the Flipped Learning model, it can provide students with a more individualized and interactive learning experience. From this viewpoint, in this research, a model called "ChatGPT Aided Flipped Learning Model (CAFLM)" has been developed, which enables ChatGPT to be used in the "Flipped Learning" learning environment. CAFLM has three main phases: 1) Preparation, 2) Outside classroom teaching, and 3) inside classroom teaching. At these phases, the tasks of the student and the teacher are explained in detail. Sample activities and use cases are provided on how ChatGPT can be integrated into the Flipped Learning model and help students. To experience the model, activities developed for mathematics and science lessons were carried out using ChatGPT. The experiences have shown that the Flipped Learning model can be combined with Chatbots such as ChatGPT to provide students with a more effective and personalized learning experience. CAFLM can enable students to be more active in the learning process and contribute to innovative approaches in education.

Grit, the passion for achieving long-term goals, has been conceived as a two-dimensional construct (Consistency of interest and Perseverance of effort). The construct is well known for its easy measurement and its relationship with performance, including academic performance. However, there have been different criticisms, such as the overlap of grit with other personality characteristics, the variability in the psychometric structure of the Grit-O and Grit-S tests, and the fact that some work reports a weak influence of grit on academic performance. Within this framework, this study contrasts different psychometric structures of the Grit-S scale and its relationship with the academic performance of higher education students. So, with this purpose, a dichotomous model of high and low grit, a K-medias clustering model, and three structural equation models have been tested. The results indicate that (a) there is a statistically significant relationship between grit--mainly determined by the consistency dimension--and academic performance, although it decreases when controlling for contextual variables, and (b) Consistency mediates the relationship between Perseverance and academic performance. The instability of grit to predict performance is discussed, and the thesis of a two-sub-dimensional structure is supported.

Teachers' learning leadership is one of important facets to students' quality of independent learning. This should be well constructed by sustainable action and transformational of change. The aims of this research are: 1) to measure how valid and reliable both sustainable action and transformation of change are in the construction of learning leadership model and 2) how learning leadership correlates to independent learning. This is a case study which applies quantitative descriptive method. The data were collected by using a 5-Likert scale questionnaire comprises the indicators of sustainable action, transformation of change and independent learning. This questionnaire was distributed to 59 Elementary teachers of three areas in West Jakarta, Indonesia. The data were analyzed by using SEM PLS and statistical analysis of regression. The findings revealed that both sustainable action and transformational of change were valid and reliable in the construction of learning leadership model. Besides, the analysis of regression showed that learning leadership was significantly correlated to independent learning.

Sports and Physical Education (SPE), like any other discipline, contributes to students' education. These students, for a good acquisition of teaching content, should be invited to take notes of the theoretical and technological knowledge conveyed by Physical and Sport Activities (PSA), subject of teaching. This quantitative and qualitative study aims to identify the usefulness of the implementation of theoretical knowledge and note-taking of the information taught in the training of students in Physical Education classes at the secondary school level. To achieve this objective, certain key concepts from "The Anthropological Theory of Didactics" by Chevallard were employed. In accordance with this theoretical framework, a methodological approach was adopted that focuses on administering questionnaires to students in the second cycle. These students meet the criterion of regular attendance at physical education courses in two secondary colleges. This approach includes recording three sessions of physical education courses and conducting interviews with each teacher at the course's conclusion. The results indicated that the students do not have a favorable relationship with the theoretical knowledge transmitted in PE during the practice of the different Physical and Sports Activities (PSA). This is due to the fact that the teacher does not focus the student's attention on what he or she has really learned and what he must retain in order to facilitate the practice of the different Physical and Sports Activities. To summarize, the essential finding derived from this study was that students in PE would greatly benefit from an introduction of theoretical courses combined with written documentation of the pedagogical information provided. The integration of both elements could foster the development of citizens who are proficient both physically and intellectually.

Learning is an integral part of being human. How people learn has long been discussed, revealed in many learning theories, investigated in numerous studies, and demonstrated in extensive practices. The goal of this article is to rethink how people learn from four fundamental perspectives, that is, learning by interaction with content (C), learning by interaction with other people (O), learning by interaction with self (S), and learning by interaction with tasks or practices (T), so-called COST model. This framework offers a high-level view of human learning and the role of technology in human learning. Moreover, it serves as a guide for effective design of learning experiences, learning environments, and learning approaches, where technology has become a crucial component.

The global pandemic caused by the SARS-CoV-2 virus brought about a true revolution in the predominant teaching-learning processes (i.e., face-to-face environment) that had been implemented up to that point. In this regard, virtual teaching-learning environments (VTLEs) have gained unprecedented significance. The main objectives of our research were to define an explanatory theoretical model and to test a multiple serial mediation model with four variables in series (one independent variable plus three mediators) to relate perceived utility (independent variable) in the use of a VTLE and perceived learning (dependent or criterion variable) in such contexts, taking into account the mediation of subjective norm (mediator 1), ease of use (mediator 2), and intention to use behavior (mediator 3), and using the extended technology acceptance model as the theoretical framework. Additionally, we aimed to analyze the direct and indirect relationships and effects among the variables that constituted the proposed model. Methodologically, the research can be classified as a cross-sectional causal ex post facto design. A representative sample of students enrolled in higher education institutions in the Dominican Republic was used as the research population, and a standardized Likert scale was administered to measure the five dimensions of the proposed model. Finally, it is worth noting that the obtained results indicate that all direct and indirect effects considered in the model were statistically significant, except for the indirect effect, where the four predictor variables were arranged in series to verify their influence on the criterion variable: perceived learning.

Conflict is an integral part of school management and its existence must not be shunned as it stimulates creative and innovative ways of thinking which enhance organisational growth and performance. The purpose of the study reported on here was to investigate how education managers executed Thomas and Kilmann's model in managing and resolving conflicts in schools to avert chaos and anarchy with the ultimate intention of enhancing productivity. A constructivist, inductive grounded theory utilising a qualitative approach was employed. Qualitative data were generated using a semi-structured interview protocol from 4 information-rich education managers who were purposively selected. The inclusion criteria for the participants were age, experience, professional qualifications and the sample was determined by theoretical saturation. Data generated were thematically analysed. The study revealed that the conflict management and resolution model used by education managers in schools was contingent to their environment and perception. It also revealed that conflict was innovative and stimulated thought processes. As a result, schools must recruit education managers who are transformative, democratic and equipped with the appropriate strategies for managing and resolving conflict if teachers' morale is to be boosted and productivity enhanced.

Artificial intelligence (AI) has recently been gaining ground, particularly since November 2022, with the introduction of generative tools based on natural language processing and neural network algorithms. These kinds of tools have great potential for creators and users of Open Educational Resources (OER) and the Open Movement itself but they also represent risks. The International Council for Open and Distance Education OER Advocacy Committee (OERAC) developed two workshops to present the role of AI in OER at two international conferences in the fall of 2023. The workshops presented the features, benefits, key challenges, and practical issues related to using AI technologies from professional, ethical, sustainable, and equitable perspectives, while also focusing on the five areas of the UNESCO OER Recommendation. Participants were dynamically engaged in discussions, and documented their ideas in formats that could be used as OER in themselves. The OERAC noted and categorized the results, and developed short summaries and drafts for further work. Finally, drawing on the findings from the workshops, we asked ChatPDF for a second opinion on further suggestions for AI in connection with OER, which in turn related to the five areas of the recommendation. We conclude that, while there is great potential for the use of AI in the context of the Open Movement, there is also a need for professional ethics, equity, and sustainable capacity building, access, inclusion, policy, models, and international collaboration.

While scholars have found that undergraduate involvement in research is beneficial, the lack of such experiences in the social sciences and humanities is glaring. This paper analyzes how an emphasis on community through cohort models impacts undergraduate student experience in research, taking from the Emerging Scholars Program, an interdisciplinary research program where cohorts of undergraduates are matched with faculty and attend meetings, workshops, and presentations together. We find that the cohort model created a robust community that fosters positive relationships that develop professional skills and emotional support, allowing students to collaborate and aim more toward their professional goals. The results from this study offer valuable insights into how universities can ensure that students have meaningful research experience beyond the classroom.

Learning the periodic table of elements can pose a challenge for students due to the complex organization and relationships between the different elements. Game-based interventions have been shown in past studies to be one of the feasible ways to overcome this challenge. In this research, a tabletop game, called "Little Periodic" was developed to improve students' chemical representation and conceptual understanding. Following the five phases of the ADDIE model - Analysis, Design, Development, Implementation, and Evaluation - the study first analyzed students' needs and identified key concepts for mastery. Additionally, an overview of the five phases is discussed in detail within this study, providing insight into the systematic process to develop and evaluate the tabletop game. Three teachers were interviewed to see the appropriate content that will be included in the tabletop game based on the "Dokumen Standard Kurikulum dan Pentaksiran (DSKP)." A tabletop game was designed and developed that could be used in physical learning environments. To evaluate the effectiveness of the developed tabletop game, validation forms and questionnaires were administered to three validator experts. The results indicated that the tabletop game was valid and effective, with high scores for content suitability, potential effectiveness, and overall satisfaction. The feedback received from chemistry teachers indicated a significant level of satisfaction with the tabletop game. The developed tabletop games can be employed in various learning situations, including in-person learning, and the effects of tabletop games need to further be investigated to ensure and enhance students to achieve deeper learning outcomes.

This action research aimed to study the use the Gamification-Incentive-Feedback (GIF) Model in enhancing the classroom learning experience of Grade 9 students in a private school in Cagayan de Oro, Philippines. The research used convenience sampling and used a combination of Likert scale pre-intervention and post-intervention survey questionnaires as well as focus group discussion (FGD) to gather data and responses. The results were analyzed through the Wilcoxon Signed Rank Test and interview responses from the FGD through thematic analysis. Results reveal a significant difference in students' classroom learning experience in terms of motivation. Further, the participants' responses to the FGD revealed that the GIF Model encourages participation and teamwork; that it promotes competition; that it is motivating, fun, exciting, and interesting; that it encourages learning retention; and that the GIF Model should be implemented face to face; among others. It is concluded that the use of GIF Model is a promising approach for the students in the classroom to create an engaging, motivating, and rewarding experience. Educators are encouraged to adapt the GIF Model in their teaching practice but should make sure that it is properly and fairly organized to avoid student frustration.

This study aims to examine the self- confidence and self-efficacy levels of soccer referees. It was conducted with relational using survey model quantitative research method. The sample of the study consisted of 100 people working as football referees in Nicosia, Famagusta, Kyrenia, Güzelyurt and Iskele districts in TRNC. As data collection tools, a form containing personal information of the participants, the Self-Confidence Scale developed by Akin (2007) and the Referee Self-Efficacy Scale developed by Myers, Feltz, Gullien, and Dithurbide (2012) and the Turkish validity oath reliability study conducted by Karaçam and Pulur (2017) were used. According to the data obtained, it is seen that soccer referees generally have a high level of self-confidence and self-efficacy. Of particular, it is noteworthy that the average values of general self-confidence and general self-efficacy are quite high. However, there are lower means values in some areas in the subscales, indicating that there is potential for improvement in certain areas. Moreover, a positive oath significant relationship was found between self-efficacy levels of soccer referees oath internal self-confidence. Similar to a positive oath significant relationship was found between external self-confidence and self-efficacy levels (Sertel, Gökbörü & Yinal, 2023). Similar results were obtained by examining self-efficacy in general, and positive oath significant relationships were found between physical self-efficacy, game knowledge, decision making, pressure oath communication and self-efficacy. However, the relationship between external self-confidence and self-efficacy was not statistically significant the effect of general self-confidence on self-efficacy levels are statistically uncertain As a result, it is seen that external self-confidence does not have a significant role in explaining self-efficacy levels, but the The effect of general self-confidence is uncertain. Others variables may need to be taken into consideration to further explain this model.

The relationship between time preference and high school students' career choices was analyzed using the cross-lagged effects model. A significant relationship was found between time preference in the first year of high school and educational expectations in April of the third year. Furthermore, time preference in the first year of high school was influenced by academic performance in the third year of junior high school. The hypothesis that educational expectations in the first year affect time preference in the third year was not supported. The fact that time preferences determine educational expectations indicates that high school students' career choices are based on certain sets of values. However, it is conceivable that time preference in the first year of high school reflects the degree of adaptation to education up through junior high school. "Career choices based on one's values" may in fact mean that those who have adapted to schooling expect to continue their education for a longer period.

This mixed methods research was applied and divided into two phases. Phase one: was to study the creative communication skills of school administrators according to the perspective of teachers in the Bangkok Metropolitan Administration (BMA). Multi-stage random sampling was used to select teachers from the BMA as participants in this research. The research instrument for phase one was a five-point Likert scale, consisting of 50 items, validating content with a range of 0.80 to 1.00, discriminant power between 0.30 to 0.80, and reliability of 0.986. Statistical analyses included mean, standard deviation, and the modified priority needs index (PNImodified). Phase two: focused on qualitative research to identify approaches to creative communication skills development of school administrators in schools under the BMA. The participant has three groups comprising seven individuals: academic experts in educational management at the directorial level or equivalent, representatives from the education department, and educational counselors affiliated with the BMA. Participants were selected using purposive sampling. The research employed a semi-structured interview as the instrument and conducted content analysis. The results of the research found that: 1) the degree of success, and importance of state requirements for creative communication skills of school administrators under the BMA were at high and highest levels respectively. The most crucial priority needs were encouragement, followed by active listening, fostering positive relationships, and reflective thinking, in that order; and 2) approaches for developing creative communication skills of school administrators under the BMA including engagement, approachability, optimism, and reinforcement, the EAOR model.

This paper explores recent advancements and implications of artificial intelligence (AI) technology, with a specific focus on Large Language Models (LLMs) like ChatGPT 3.5, within the realm of higher education. Through a comprehensive review of the academic literature, this paper highlights the unprecedented growth of these models and their widereaching impact across various sectors. The discussion sheds light on the complex issues and potential benefits presented by LLMs, providing a comprehensive overview of the field's current state. In the context of higher education, the paper explores the challenges and opportunities posed by LLMs. These include issues related to educational assessment, potential threats to academic integrity, privacy concerns, the propagation of misinformation, Equity, Diversity, and Inclusion (EDI) aspects, copyright concerns and inherent biases within the models. While these challenges are multifaceted and significant, the paper emphasises the availability of strategies to address them effectively and facilitate the successful adoption of LLMs in educational settings. Furthermore, the paper recognises the potential opportunities to transform higher education. It emphasises the need to update assessment policies, develop guidelines for staff and students, scaffold AI skills development, and find ways to leverage technology in the classroom. By proactively pursuing these steps, higher education institutions (HEIs) can harness the full potential of LLMs while managing their adoption responsibly. In conclusion, the paper urges HEIs to allocate appropriate resources to handle the adoption of LLMs effectively. This includes ensuring staff AI readiness and taking steps to modify their study programmes to align with the evolving educational landscape influenced by emerging technologies.

Student's critical thinking skills that are currently still low are important to develop because they affect the way students think in solving problems. The problem-based learning model with the inquiry method used to help improve student's critical thinking skills. The iSpring learning media used can help students understand the material. The research results were obtained from the output of the paired sample t-test, a significance value < 0.05, so it was concluded that there was a difference between before applying the learning model and after applying the learning model. The results of the questionnaire responses to the media also resulted in positive responses from students.

The use of learner modelling approaches is critical for providing adaptive support in educational computer games, with predictive learner modelling being among the key approaches. While adaptive supports have been shown to improve the effectiveness of educational games, improperly customized support can have negative effects on learning outcomes. To tackle these challenges, we present a novel approach, called DeepLM, that considers a series of time windows representing both sequences of learners' actions during gameplay and estimation of their current competencies (using stealth assessment) to model learners and accordingly predict their future performance. The approach employs a variant of deep neural networks to early predict learners' midterm and final scores simultaneously. The results show that using 20-50% of learners' action sequences can early predict their final scores, with a cross-validated convolutional neural network (CNN) achieving an area under the curve (AUC) and accuracy of 0.879 and 85.3%, respectively. The same model can also achieve high accuracy in predicting midterm and final scores at the same time, with an AUC and accuracy of 0.848 and 77.9%. Overall, the CNN model outperforms recurrent neural network, long short-term memory, and baseline multilayer perceptron (MLP) models in predicting learners' final performance and performs better than the baseline MLP model in predicting learners' midterm and final performance using both cross-validation and independent datasets. These findings show the potential of the proposed approach in accurately early predicting learners' performance, allowing educators and game designers to tailor interventions and support mechanisms that could lead to optimized learning outcomes.

Research on higher education community engagement (HECE) rarely places university or institutional voices in conversation with the community partners' voices. Boundary-spanning frameworks such as Weerts and Sandmann's (2010) for universities and Adams's (2014) for community partners help boundary spanners, but such models draw boundaries between community and university spanners and the beneficiaries of their work. Contrary to a resource-based view of value creation, which posits that organizations with more resources create more value, beneficiary-centric views see the beneficiary as central to value creation (Lepak et al., 2007). In this essay we incorporate a beneficiary-centric lens into HECE boundary-spanning practices to advance a critical theory of value creation that considers for whom, for what, and to what effect beneficiaries may create value (Le Ber & Branzei, 2010). We advocate for an integrated framework that unites university and community partners and places the beneficiary at the center of all engagement efforts.

The prediction of student performance and the analysis of students' learning behaviour play an important role in enhancing online courses. By analysing a massive amount of clickstream data that captures student behaviour, educators can gain valuable insights into the factors that influence students' academic outcomes and identify areas of improvement in courses. In this study, we developed ClickTree, a tree-based methodology, to predict student performance in mathematical problems in end-unit assignments based on students' clickstream data. Utilising extensive clickstream data, we extracted a novel set of features at three levels, including problem-level, assignment-level and student-level, and we trained a CatBoost tree to predict whether a student will successfully answer a problem in an end-unit assignment or not. The developed method achieved an Area under the ROC Curve (AUC) of approximately 79% in the Educational Data Mining Cup 2023 and ranked second in the competition. Our results indicate that students who performed well in end-unit assignment problems engaged more with in-unit assignments and answered more problems correctly, while those who struggled had higher tutoring request rates. We also found that students face more difficulties with "check all that apply" types of problems. Moreover, Algebra II was the most difficult subject for students. The proposed method can be utilised to improve students' learning experiences, and the insights from this study can be integrated into mathematics courses to enhance students' learning outcomes.

Knowledge tracing aims to model and predict students' knowledge states during learning activities. Traditional methods like Bayesian Knowledge Tracing (BKT) and logistic regression have limitations in granularity and performance, while deep knowledge tracing (DKT) models often suffer from lacking transparency. This paper proposes a Transformer-based framework that emphasizes both accuracy and interpretability. It captures the relationship between student behaviors and learning outcomes considering the associations between exam and exercise problems. We participated in the EDM Cup 2023 Contest using the proposed framework and achieved first place on the task of predicting students' performance on end-of-unit test problems using clickstream data from previous assignments. Furthermore, the framework provides meaningful insights by analyzing user actions and visualizing attention weight matrices. These insights enable targeted interventions and personalized support, enhancing online learning experiences. We have uploaded our code, saved models, and predictions to an OSF repository: https://osf.io/mdpzc/.

We propose a novel model, Wide & Deep Item Response Theory (Wide & Deep IRT), to predict the correctness of students' responses to questions using historical clickstream data. This model combines the strengths of conventional Item Response Theory (IRT) models and Wide & Deep Learning for Recommender Systems. By leveraging clickstream data, Wide & Deep IRT provides precise predictions of answer correctness while enabling the exploration of behavioral patterns among different ability groups. Our experimental results based on a real-world dataset (EDM Cup 2023) demonstrate that Wide & Deep IRT outperforms conventional IRT models and state-of-the-art knowledge tracing models while maintaining the ease of interpretation associated with IRT models. Our model performed very well in the EDM Cup 2023 competition, placing second on the public leaderboard and third on the private leaderboard. Additionally, Wide & Deep IRT identifies distinct behavioral patterns across ability groups. In the EDMCup2023dataset, low-ability students were more likely to directly request an answer to a question before attempting to respond, which can negatively impact their learning outcomes and potentially indicates attempts to game the system. Lastly, the Wide & Deep IRT model consists of significantly fewer parameters compared to traditional IRT models and deep knowledge tracing models, making it easier to deploy in practice. The source code is available via Open Science Framework.