Student behavior patterns in vocational education big data based on clustering algorithm

The study investigated the characteristic differences among student learning behavior patterns in an online learning situation. Sixty students participated in the work and undertook four months online learning in an e-learning system. The two-stage cluster analysis was designed to explore the identification and classification of student learning behavior patterns. The results found three distinct patterns: Active Participants, Enthusiastic Participants, and Lower Participants. In addition, we found that the preliminary influences of the learning activities and the parent-child learning interaction in online learning situations might be the factors which affect studentpsilas behavior. Finally, this study found no significant difference of learning performance among the various student behavior patterns.

Apartment is a room or several rooms (rooms) that are functioned or designated as a place to live, located in a building that usually has other rooms or rooms and the like. This study attempts to explore and analyze the relationship between residential space patterns and student behavior patterns in Jakarta. The behavioral patterns of students that affect the pattern of vertical residential spaces not only have an impact on the behavior and form of space but also see how student behavior shapes architecture in residential space patterns and architecture shapes student behavior. The purpose of this study is to understand the theory related to the relationship between vertical residential space patterns and student behavior patterns, to understand the characteristics of the relationship between residential space patterns and student behavior, to understand environmental factors for student behavior. The research method taken on the research approach uses a qualitative descriptive method. The data studied and obtained are physical and non-physical data obtained from interviews, observations, and mapping of student behavior patterns in residential spaces of Jakarta apartments. The approach that will be used is the Human Behavior approach to students in apartment housing. From the analysis of behavior patterns carried out, student activities are quite dense, causing the use of furniture according to needs and has ergonomic characteristics.

Campus data is increasingly gaining the attention of college student management staff; they hope that through the use of machine learning and big data technology theory, analysis of students during the period of school data finds students growth law, timely find hidden dangers and properly handle, for students to develop more scientific and humanized management plan, truly in accordance with their individual aptitude. For Grade 13 students, the course management optimization success rates were 62.90% for Algorithm 1 and 69.35% for Algorithm 2. For grade 15 students, the success rate of course management optimization was 64.41% for algorithm 1 and 89.83% for algorithm 2. By studying the relevant techniques of student group behavior pattern analysis, we explore how to classify the behavior patterns of college students by combining machine learning K-means algorithm and NMF algorithm. Using the emotion polarity classification algorithm based on dependence, we paper how to classify the emotion polarity of student network comments and classify some real student comments in a university forum. The paper also completed the analysis of student group behavior patterns based on machine learning K-means algorithm and NMF algorithm, and obtained the classification results and characteristics of group behavior patterns, classified the real comments of some students based on the forum based on dependency, and determined the related theory based on support vector machine (SVM) algorithm. The characteristics of students’ behavior in school were analyzed from three aspects, and the K-means algorithm in the cluster analysis was used to mine the data of these three aspects, which obtained the distribution of students’ behavior characteristics of five types of consumption habits, three types of living habits and four types of learning habits. Students’ long Internet time, low number of books borrowing, and provide targeted management for teachers and schools according to the characteristics of these problems propose.

This manuscript delineates a normative structure for community college students, outlines how this structure varies by student characteristics, and compares this structure to that of a previously established normative structure identified at a 4-year institution. A total of 512 student survey responses on the College Student Behaviors Inventory were collected at a comprehensive community college in the rural Southeast. A series of factor analyses using varimax rotation was applied to identify 23 inviolable norms, 20 admonitory norms, and four laudatory norms, with little variation across student characteristics. Specifically, gender is the only characteristic that yields a significant difference across all patterns of student behavior. We also find the normative structure at a community college to have many similarities to that of a 4-year institution, yet also some differences. The strong number of similarities, however, appears to dispel the suggestion that the diversity in mission and student body characteristics between 2- and 4-year colleges and universities would result in significantly different peer environments. Implications are offered as to how knowledge of such a normative structure may influence policymaking on community college campuses.

Abstract. As one spatio-temporal data mining task, clustering helps the exploration of patterns in the data by grouping similar elements together. However, previous studies on spatial or temporal clustering are incapable of analysing complex patterns in spatio-temporal data. For instance, concurrent spatio-temporal patterns in 2D or 3D datasets. In this study we present two clustering algorithms for complex pattern analysis: (1) the Bregman block average co-clustering algorithm with I-divergence (BBAC_I) which enables the concurrent analysis of spatio-temporal patterns in 2D data matrix, and (2) the Bregman cube average tri-clustering algorithm with I-divergence (BCAT_I) which enables the complete partitional analysis in 3D data cube. Here the use of the two clustering algorithms is illustrated by Dutch daily average temperature dataset from 28 weather stations from 1992 to 2011. For BBAC_I, it is applied to the averaged yearly dataset to identify station-year co-clusters which contain similar temperatures along stations and years, thus revealing patterns along both spatial and temporal dimensions. For BCAT_I, it is applied to the temperature dataset organized in a data cube with one spatial (stations) and two nested temporal dimensions (years and days). By partitioning the whole dataset into clusters of stations and years with similar within-year temperature similarity, BCAT_I explores the spatio-temporal patterns of intra-annual variability in the daily temperature dataset. As such, both BBAC_I and BCAT_I algorithms, combined with suitable geovisualization techniques, allow the exploration of complex spatial and temporal patterns, which contributes to a better understanding of complex patterns in spatio-temporal data.

The aim of this paper is to describe the consumer behaviour and everyday lifestyle patterns of Hungarian university and college students. The results are gained from an international survey, carried out by the Department of Environmental Economics and Technology at the Corvinus University of Budapest, supported by the Norwegian Financial Mechanism. As background literature, characteristics of the consumer society and the development of sustainable consumption as a concept are interpreted in the paper. The empirical analysis aims to describe the most important clusters of students, based on the factors of their consumer behaviour, environmental activism and pro-environmental everyday habits. Our results identify two extreme clusters which most significantly differ from each other: the environmental activists and the indifferent group. However, a third cluster has the most modest consumer behaviour, namely the group which considers product features, energy consumption and the behaviour of producers. They sp...

Data mining (DM) approaches have been applied in the field of Educational Data Mining (EDM) to obtain the important insights about student preferences and behaviors. By using a variety of strategies to increase the effectiveness of e-learning environments, the design aims to enhance learning processes by forecasting the traits of students. Academic data can be used to study trends in student behavior using a selection of DM, such as grouping, classification, and forecasting. This study presents a novel approach to learning behaviors prediction in the Chaotic-Tuned Shuffled Frog Leaping Optimized Random Forest (CSFLO-RF). The CSFLO technique, which accelerates the global convergence of the traditional SFLO technique, improves the accuracy of RF categorization in the suggested methodology. The K-Means Clustering (KMC) methodology uses the student behavior patterns recorded in the log record to group learners into specific categories based on their e-learning system usage. The generated clusters were allocated multiple learning styles based on the framework for learning styles. Following that, the specified behaviors were employed as input for the proposed CSFLO-RF classification to evaluate the degree to predict the students’ learning behavior. According to the results of the suggested technique, which is implemented to utilize the Weka platform, the CSFLO-RF approach yielded more successful outcomes than other existing strategies.

When observing behaviors of special-needs students, on average, typical behaviors of common propensity are observed along with unspecific behaviors. Unlike behaviors that are generally known, information regarding unspecific behaviors is insufficient. For an education or guidance regarding the unspecific behaviors, collection and management of data regarding the unspecific behaviors of special-needs students are needed. In this paper, a consultation management model based on behavior classification of special-needs students using machine learning is proposed. It is a model that provides data to a user by collecting, classifying and managing the behavior data by letting the machine learn the data regarding the unspecific behaviors of special-needs students that are not typical and well known. Since it requires data regarding various behaviors of special-needs students, the data set shall be organized using the behavior pattern data of special-needs students that currently exists, and the data shall be learned by the proposed model. Web-based machine learning model that collects behaviors of special-needs students in real-time is proposed in order to collect the behavior pattern data regarding the unspecific behaviors of special-needs students. The data can be input using the proposed model, and the user can use it through web-browser. The data can be easily input and revised using the proposed model in any environment that the internet can be accessed. The utilization of data analysis result can be enhanced through the use of data list and tools such as a graph through a web-browser, and the accuracy can be enhanced by learning the result that has been acquired by comparing it with previous data by connecting to the database. The test has been performed by arbitrarily applying unspecific behaviors that are not stored in the database, and the forecast model has accurately classified and grouped the input data. Also, it has been verified that it is possible to accurately distinguish and classify the behaviors through the feature data of the behaviors even if there are some errors in the input process. In future, the research of real-time data collection and tailored education index data: the common items need to be organized as a data by recording a class time of special schools or special classes and analyzing the behavior patterns of multiple special-needs students in real-time.

Predicting student performance and understanding behavioral patterns have become central themes in modern educational research, particularly with the rise of digital and blended learning environments. The growing availability of data from Learning Management Systems (LMS) and online learning platforms has led to a wide array of data-driven and AI-based approaches for analyzing academic outcomes and learner behaviors. This paper presents a comprehensive comparative review of existing intelligent learning models, examining how various studies utilize behavioral indicators, such as engagement, interaction patterns, and study habits, to predict student performance. By synthesizing findings across diverse methodologies and datasets, the review highlights current trends, strengths, limitations, and research gaps, offering educators and researchers valuable insights for developing more effective, data-informed student support strategies.

During the last few years, learning analytics (LA) has gained the interest of researchers in the field of education. Generally, LA is related with the development of methods that use educational data sets to support the learning process. Therefore, there is a need understanding how learners, educators, and institutions can best support this process. Thus, a framework is presented that tries to extend the collaborative three-dimensional virtual environments for educational by integrating a LA tool. The aim is to help the teacher to monitor and evaluate the students' learning process in these types of environments. It is the intention include a (1) comprehensive analysis of the currently available LA tools for educational, (2) design of a user-centered framework based the requirements gathered from the analysis, and (3) thorough evaluation of framework to allow identify possible behavior patterns of students within the environment, related to your preferences for materials and expertise.

The export of Russian education is linked to promoting universities internationally. Following ethical standards when promoting a brand strengthens its image, reputation, and attractiveness to foreign students. This chapter identifies issues with marketing communications between Russian universities and international students. It proposes a model for managing ethical brand promotion conceptually and practically. Desk research methods were used, including synthesis, traditional content analysis, and interdisciplinary assessment. The conceptual level manages ethical promotion through social/ethical marketing from three perspectives: caring for current and future students, applying values to educational services, and legal brand responsibility. The practical level uses social/ethical tools like PR and integrated communications ethically. Recommendations were expressed by (1) in detailing approaches to social and ethical marketing based on segmentation of foreign students according to priority individual and cultural values, and behavior patterns of students from different generations Y and Z when choosing a university, based on differentiated brand positioning for target segments; (2) in the systematization of international and Russian regulatory documents establishing the rules of ethical marketing communications; (3) in systematizing the ethical principles of brand promotion via the Internet and digital channels; and (4) in developing activities that allow universities to ensure confidentiality in marketing communications with the brand’s target audience.

The application of data mining methods to identify key factors of academic performance based on students' digital footprints is discussed in the paper. Using the OULAD dataset as an example, a predictive logistic regression model was constructed, and behavioral patterns of students were clustered. The results demonstrate that the key factors for success are regularity of study activities and discipline in meeting deadlines, while the “storming” tactic is a significant predictor of risk. Cluster analysis allowed us to identify five stable behavioral types of students, which justifies the need for a differentiated pedagogical approach. The research conducted provides a basis for developing early warning systems for academic performance problems and personalized support for students.

In traditional dance teaching, teachers’ demonstration generally takes up most of the in‐class time, which reduces the opportunities for students to practice. Therefore, researchers have started to adopt flipped learning to increase the in‐class time for students’ practice and teachers’ guidance. However, there are some problems associated with the conventional approach to flipped learning; these problems include students’ lack of preparation before class which affects their engagement in the in‐class activity; lack of guidance when self‐learning; no instant assistance when encountering problems; and lack of reflection. To address these problems, the current study proposes a reflective thinking promoting approach to instruct the students to understand the pre‐class materials and to strengthen their reflection and the interflow among peers in flipped learning. A total of 129 university students were recruited in the present study. They were divided into the experimental group which adopted the annotation, reflection, questioning and interflow (ARQI) approach and the control group which adopted the previous flipped learning approach. The results revealed that ARQI could significantly enhance the students’ dance performance. The interview also revealed that ARQI promoted the students’ reflection. Moreover, the higher self‐efficacy students tended to gain more benefits from the flipped learning approach than those with lower self‐efficacy. Lastly, following the ARQI steps to finish the pre‐class learning, students were aware that they were required to put more mental and temporal efforts into the class. Practitioner NotesWhat is already known about this topic Educators have questioned the quality of dance teaching that mainly adopts a directive teaching approach in which students just do as they are told or mirror the teacher, rather than a dialogical or student‐centered approach which allows students to dance based on their understanding and interpretation of the theme (Sims & Erwin, 2012). Flipped learning enables students to have more time to practice and interact with the teacher and peers by shifting the in‐class lectures to pre‐class self‐learning. Researchers have pointed out that insufficient preparation in the pre‐class learning stage could significantly affect students’ in‐class learning performance, which is a big challenge of implementing flipped learning. What this paper adds A reflective thinking‐promoting mechanism is proposed for implementing flipped dance to instruct students to understand the pre‐class materials and to strengthen their reflection and the interflow among peers. The experimental results showed that the proposed approach promoted the students’ reflective thinking as well as their dance performance. Implications for practice and/or policy Self‐efficacy plays an important role in flipped learning. When teachers implement relevant strategies, more focus should be placed on students with low self‐efficacy. Forming the reflective thinking skill is important, but attainable; it needs students’ increased mental and temporal efforts. Further investigations on the effects of employing the approach in other performing arts courses from different aspects, such as the interactive and behavioral patterns of students in the pre‐class and in‐class stages, are needed.

Technology advancements have always helped to constantly multitask and take more and more work and targets due to which people are under stern time pressures and are constantly moving which leads to stress. Increasing number of people seems to be overcharged and overburdened. People are finding it difficult to keep up their energy levels up and live a normal, peaceful life; instead most of their useful time gets wasted in coping from stress.This paper focuses on finding the stress level of management students who are working under immense pressure by meeting day to day deadlines, studying a number of subjects at a time, doing to many assignments and submitting the term projects on deadlines. Apart from fulfilling their course requirement, students also have to deal with different other pressures and fulfill their parent‟s expectations. This study is done with the objective of discovering the causes of stress in the lives of students, the effects of stress, identifying the various variables associated with it and establishing definite relationships between these variables. The study also tries to identify the prominent underlying variables responsible for causing stress. For this a comprehensive survey via an online questionnaire has been conducted. This paper uses a descriptive methodology and focuses to find the effect of different causes on the stress levels and hence is an insight into the behavioral patterns of students when they experience the same.

Black carbon concentration and health impact in urban school buildings in South Korea: Focus on student behavior patterns