Student Profile Modeling Using Boosting Algorithms

The student profile has become an important component of education systems. Many systems objectives, as e-recommendation, e-orientation, e-recruitment and dropout prediction are essentially based on the profile for decision support. Machine learning plays an important role in this context and several studies have been carried out either for classification, prediction or clustering purpose. In this paper, the authors present a comparative study between different boosting algorithms which have been used successfully in many fields and for many purposes. In addition, the authors applied feature selection methods Fisher Score, Information Gain combined with Recursive Feature Elimination to enhance the preprocessing task and models’ performances. Using multi-label dataset predict the class of the student performance in mathematics, this article results show that the Light Gradient Boosting Machine (LightGBM) algorithm achieved the best performance when using Information gain with Recursive Feature Elimination method compared to the other boosting algorithms.

Effects of Generic and Subject-Didactic Teaching Characteristics on Student Performance in Mathematics in Secondary School: A Scoping Review

<p style="text-align: justify;">Research on instructional quality has been of great interest for several decades, leading to an immense and diverse body of literature. However, due to different definitions and operationalisations, the picture of what characteristics are important for instructional quality is not entirely clear. Therefore, in this paper, a scoping review was performed to provide an overview of existing evidence of both generic and subject-didactic characteristics with regard to student performance. More precisely, this paper aims to (a) identify both generic and subject-didactic characteristics affecting student performance in mathematics in secondary school, (b) cluster these characteristics into categories to show areas for quality teaching, and (c) analyse and assess the effects of these characteristics on student performance to rate the scientific evidence in the context of the articles considered. The results reveal that teaching characteristics, and not just the instruments for recording the quality of teaching as described in previous research, can be placed on a continuum ranging from generic to subject-didactic. Moreover, on account of the inconsistent definition of subject-didactic characteristics, the category of ‘subject-didactic specifics’ needs further development to establish it as a separate category in empirical research. Finally, this study represents a further step toward understanding the effects of teaching characteristics on student performance by providing an overview of teaching characteristics and their effects and evidence.</p>

Observed Quality of Formative Peer and Self-Assessment in Everyday Mathematics Teaching and its Effects on Student Performance

<p style="text-align: justify;">The positive effect of peer assessment and self-assessment strategies on learners' performance has been widely confirmed in experimental or quasi-experimental studies. However, whether peer and self-assessment within everyday mathematics teaching affect student learning and achievement, has rarely been studied. This study aimed to determine with what quality peer and self-assessment occur in everyday mathematics instruction and whether and which students benefit from it in terms of achievement and the learning process. Two lessons on division were video-recorded and rated to determine the quality of peer and self-assessment. Six hundred thirty-four students of fourth-grade primary school classes in German-speaking Switzerland participated in the study and completed a performance test on division. Multilevel analyses showed no general effect of the quality of peer or self-assessment on performance. However, high-quality self-assessment was beneficial for lower-performing students, who used a larger repertoire of calculation strategies, which helped them perform better. In conclusion, peer and self-assessment in real-life settings only have a small effect on the student performance in this Swiss study.</p>

Student Performance on the BDSI for Basic Data Structures

A Concept Inventory (CI) is an assessment to measure student conceptual understanding of a particular topic. This article presents the results of a CI for basic data structures (BDSI) that has been previously shown to have strong evidence for validity. The goal of this work is to help researchers or instructors who administer the BDSI in their own courses to better understand their results. In support of this goal, we discuss our findings for each question of the CI using data gathered from 1,963 students across seven institutions.

Optimization of Ideological and Political Education under the Epidemic via Mobile Learning Auxiliary Platform in the Era of Digitization

In the digitized era, life has become simpler with the increased information technology. The Education Department in the whole world is facing a tremendous revolution with the development. The traditional classroom study is converted to a modernized and digitized classroom with visualization. This modernization has increased the learning capability of the students with an increase in student and teacher interaction. From this teaching and learning process, most colleges and universities have improved performance in preparing course materials, effective teaching, and independent learning among the students in the theoretical courses. Ideological and political education (IPE) is a theoretical subject that is taught and understood at higher education institutions, such as colleges and universities. A hybrid hierarchical K -means clustering for optimizing clustering with unsupervised machine learning is proposed to analyze the student performance and concluded that the proposed algorithm shows improved performance than the K -means algorithm.

Examining the Factors Influencing Applicants’ Placement on One General Surgery Program’s Rank Order List

Purpose Surgery residency applications include variables that determine an individual’s rank on a program’s match list. We performed this study to determine which residency application variables are the most impactful in creating our program’s rank order list. Methods We completed a retrospective examination of all interviewed applicants for the 2019 match. We recorded United States Medical Licensing Examinations (USMLE) step I and II scores, class quartile rank from the Medical Student Performance Evaluation (MSPE), Alpha Omega Alpha (AOA) membership, geographic region, surgery clerkship grade, and grades on other clerkships. The MSPE and letters of recommendation were reviewed by two of the authors and assigned a score of 1 to 3, where 1 was weak and 3 was strong. The same two authors reviewed the assessments from each applicant’s interview and assigned a score from 1-5, where 1 was poor and 5 was excellent. Univariate analysis was performed, and the significant variables were used to construct an adjusted multivariate model with significance measured at P < .05. Results Univariate analysis for all 92 interviewed applicants demonstrated that USMLE step 2 scores ( P = .002), class quartile rank ( P = .004), AOA status ( P = .014), geographic location ( P < .001), letters of recommendation ( P < .001), and interview rating ( P < .001) were significant in predicting an applicant’s position on the rank list. On multivariate analysis only USMLE step 2 ( P = .018) and interview ( P < .001) remained significant. Conclusion USMLE step 2 and an excellent interview were the most important factors in constructing our rank order list. Applicants with a demonstrated strong clinical fund of knowledge that develop a rapport with our faculty and residents receive the highest level of consideration for our program.

Measuring the effectiveness of online problem solving for improving academic performance in a probability course

Research on impact in student achievement of online homework systems compared to traditional methods is ambivalent. Methodological issues in the study design, besides of technological diversity, can account for this uncertainty. Hypothesis This study aims to estimate the effect size of homework practice with exercises automatically provided by the ‘e-status’ platform, in students from five Engineering programs. Instead of comparing students using the platform with others not using it, we distributed the subject topics into two blocks, and created nine probability problems for each block. After that, the students were randomly assigned to one block and could solve the related exercises through e-status. Teachers and evaluators were masked to the assignation. Five weeks after the assignment, all students answered a written test with questions regarding all topics. The study outcome was the difference between both blocks’ scores obtained from the test. The two groups comprised 163 and 166 students. Of these, 103 and 107 respectively attended the test, while the remainder were imputed with 0. Those assigned to the first block obtained an average outcome of −1.85, while the average in the second block was −3.29 (95% confidence interval of difference, −2.46 to −0.43). During the period in which they had access to the platform before the test, the average total time spent solving problems was less than three hours. Our findings provide evidence that a small amount of active online work can positively impact on student performance.

The effects of course format, sex, semester, and institution on student performance in an undergraduate animal science course

The transition of courses from in-person to an online format due to the COVID-19 pandemic could have potentially affected overall student performance in lecture-based courses. The objective of this case study was to determine the impact of course format, as well as the effects of student sex, time of year at which the course was taken, and the institution it was taken at on student performance in an undergraduate animal science course. The course used for this study was taught at two institutions (University of Florida; UF and University of Nevada, Reno; UNR) over seven years (2014-2017 at UNR and 2018-2021 at UF). Student performance (n = 911) was evaluated using both quizzes and exams from 2014 through the spring semester 2020 and only exams were used for summer and fall semesters of 2020 and the spring and summer semesters of 2021. The final score (out of 100%) for each student was used to evaluate student performance. In addition, students were classified as high performing students if they scored ≥ 95% and low performing students if they scored ≤ 70%. The variables that were evaluated were the effects of semester (spring, summer, or fall), institution (UF or UNR), sex (male or female), number of teaching assistants (TAs; 0 to 13), and course format (online or in-person). The course was taught in-person at UNR and in-person and online at UF. The spring semester of 2020 was taught in-person until March but was switched to online approximately nine weeks after the semester started and was considered an online semester for this analysis. As the course was only taught online at UF, the variable course format was assessed using UF records only. Data was analyzed using both linear models and logistic regressions. The probability that students were high performing was not affected by sex or institution. Interestingly, both fall semester, and the online format had a positive, desirable effect on the probability that students were high performing. The probability that students were low performing was not affected by sex. However, if a student performed poorly in the class, they were more likely to have taken the course at UNR, or at UF with many TAs. Thus, student performance was impacted by changing the course format, as well as institution, the number of TAs, and the semester in which the course was taken.