Analysis Of Student Performance Research Articles

Towards a Technological Ecosystem to Provide Information Dashboards as a Service: A Dynamic Proposal for Supplying Dashboards Adapted to Specific Scenarios

Data are crucial to improve decision-making and obtain greater benefits in any type of activity. However, the large amount of information generated by new technologies has made data analysis and knowledge generation a complex task. Numerous tools have emerged to facilitate this generation of knowledge, such as dashboards. Although dashboards are useful tools, their effectiveness can be affected by poor design or by not taking into account the context in which they are placed. Therefore, it is necessary to design and create custom dashboards according to the audience and data domain. This paper presents an application of the software product line paradigm and the integration of this approach into a web service to allow users to request source code for customized information dashboards. The main goal is to introduce the idea of creating a holistic ecosystem of different services to craft and integrate information visualizations in a variety of contexts. One of the contexts that can be especially favored by this approach is the educational context, where learning analytics, data analysis of student performance, and didactic tools are becoming very relevant. Three different use cases of this approach are presented to illustrate the benefits of the developed generative service.

Investigating Alignment in a Quantitative Literacy Course for Social Sciences Students

The Numeracy Centre at the University of Cape Town has taught a one-semester quantitative literacy course for social sciences students since 1999. This study aims to provide an example for how the design of such a course can be assessed for alignment with quantitative reasoning goals. We propose a framework of learning outcomes for the course and use that framework to analyse the assessments and student performance on them. We find that just under half of the overall mark for the course was devoted to the interpretation and communication of quantitative information (our “main” outcomes), and about a quarter was devoted to the performing of calculations. The analysis revealed that statistics outcomes were under-represented in the make-up of the overall course mark, and assessment of these outcomes was restricted almost entirely to the two final examinations. The results of the analysis of the alignment between outcomes and assessment are useful to inform discussions about changes to the course curriculum. The analysis of student performance on the different outcomes provides insights which are useful for informing improvements to our teaching approach. The analysis demonstrates a relatively straightforward procedure that can be used or adapted by researchers in other institutions for ongoing monitoring of alignment between course outcomes, teaching, and assessment.

Using benchtop experiments to teach dimensional analysis and analogue modeling to graduate geoscience students

The need for geoscience students to develop a quantitative skillset is ever increasing. However, this can be difficult to implement in university-style lecture courses in a way that is both manageable for the instructor and does not involve lengthy, potentially repetitive, question sheets for the students. Here, a method for teaching dimensional analysis, basic fluid dynamics, and the interpretation and scaling of experimental data is presented for a graduate student audience. The proposed method utilizes simple fluid dynamic benchtop experiments that require a small amount of teaching space and use readily available, low cost materials. Our analysis of student performance through pre- and post-tests demonstrates that students have a better knowledge of dimensional analysis, data interpretation and experimental design after the series of practical sessions compared to instruction through a single, passive lecture. We therefore show that simple benchtop experiments can be an effective way to improve and integrate quantitative learning into a graduate geoscience class.

Improving performance in a large flipped barrier mathematics course: a longitudinal case study

Flipped classrooms are increasingly popular due to improvements in online technology and expected benefits in student engagement and learning. Although research has increased dramatically in the last 10 years, few studies have assessed the effectiveness of flipping large enrollment, barrier mathematics courses. Creating a comprehensive flipped classroom learning experience that includes high quality in-class activities can be particularly challenging in large classrooms, especially when implemented for the first time. However, improving engagement and learning in these courses would be particularly helpful in improving STEM graduation rates. This paper describes a longitudinal analysis of student performance and opinions in a differential equations course over three years with three different instructional strategies: traditional lecture, initial flipped, and revised flipped. We found that flipping the course reduced withdrawal rates and improved pass rates, but the initial iteration reduced exam performance. We then observed a positive change in exam performance and student opinion from the initial to the revised flipped course. We conclude that the flipped classroom can be effective in large mathematics courses required for STEM degrees, although it may not be possible to see all benefits in an initial implementation.

Extreme Poverty, Violence and Inclusive education in Haiti: Student Performance Analysis from the Multifactorial Approach

The objective of this work is to analyze the impact of violence, crime, kidnapping and extreme poverty on the academic performance and mental health of high school and undergraduate students in public schools and colleges located in Port-au-Prince, Haiti. It is a qualitative research of a deductive type and a semi-structured interview to collect the data and draw the pertinent conclusions. The results show a proportion of undergraduate students in very difficult socioeconomic situations, and with fear of being kidnapped when going to school, due to violent acts. Likewise, high school students have expressed their fear of being violated, which causes various psychological disorders. It was concluded that poverty and violent events harm inclusive and continuous education, school performance, collective well-being and the tranquility of students, and the general population

Comparative analysis of student performance in collaborative problem solving: What does it tell us?

Collaboration is a complex skill, comprised of multiple subskills, that is of growing interest to policy makers, educators and researchers. Several definitions and frameworks have been described in the literature to support assessment of collaboration; however, the inherent structure of the construct still needs better definition. In 2015, the Organisation for Economic Cooperation and Development, in their Programme for International Student Assessment assessed 15-year-old students’ collaborative problem solving achievement, with the use of computer-simulated agents, aiming to address the lack of internationally comparable data in this field. This paper explores what the data from this assessment tell us about the skill, and how these data compare with data from two other assessments of collaboration. Analyses enable comment on the extent to which the three assessments are measuring the same construct, and the extent to which the construct can be covered using computer-based assessments. These investigations generate better understanding of this complex and innovative domain.

Mapping Student Performance With Employment Using Fuzzy C-Means

Technical organisations are ranked based on performance indicators like resources, students' intake, global reputation, and research activities. Student performance and placement are important factors in deciding the ranking of a university. Student performance analysis is a recent and widely researched domain aimed at reforming the education system. The analysis assists institutions to understand and improve their performance and educational outcomes. Admissions, academics, and placement are the three most significant processes during which the large amount of data is gathered within a university and there is a requirement of analysis. The data mining techniques are used for data analysis processes and it encompasses data understanding, pre-processing, modelling, and implementation. In this research work, fuzzy c-means clustering technique is used to understand fuzziness of student performance, classify and map the student performance to employability. To understand this objective, the dataset has been collected from universities, pre-processed, and analysed.

Prediction and Analysis of Student Performance in Secondary Education Based on Data Mining and Machine Learning Techniques

<p>According to modern era education is the key to achieve success in the future; it develops a human personality, thoughts, and social skills. The purpose of this research work is to focus on educational data mining (EDM) through machine learning algorithms. EDM means to discover hidden knowledge and pattern about student's performance. Machine learning can be useful to predict the learning outcomes of students. From last few years, several tools have been used to judge the student's performance from different points of view like the student's level, objectives, techniques, algorithms, and different methods. In this paper, predicting and analyzing student performance in secondary school is conducted using data mining techniques and machine learning algorithms such as Naive Bayes, Decision Tree algorithm J48, and Logistic Regression. For this the collection of dataset from "Secondary School" and then filtration is applying on desired values using WEKA, tool.</p>

Rutgers Robert Wood Johnson Medical School.

Rutgers Robert Wood Johnson Medical School.

Quantum computing inspired framework of student performance assessment in smart classroom

SummaryInternet of Things (IoT) technology, merged with fog‐cloud computing, has provided efficient services in the education industry. Inspired by this aspect, this paper presents an effective framework of the smart classroom for optimal evaluation of the performance of students and teachers based on quantum game‐theoretic (QGT) decision making. Specifically, IoT technology is incorporated inside the classroom to acquire data about students and teachers for determining the academic enhancement of students. The acquired data is evaluated over the fog‐cloud computing platform to estimate a quantifiable measure of probability of performance using the Bayesian modeling technique. Moreover, to analyze the student and teacher performance over the temporal scale, student performance indicator and teacher performance indicator are calculated. Finally, student‐teacher performance is assessed using the effective two‐player quantum gametic decision‐making. The experimental simulation on four challenging datasets namely student performance (7029 instances), student academic performance (3585 instances), student performance prediction (2120 instances), and student performance analysis (6507 instances) shows the effectiveness of the proposed framework. The simulation results are contrasted with various state‐of‐the‐art techniques to estimate the overall efficiency of the proposed system. Moreover, mathematical analysis has been carried out to depict the performance of the proposed framework.

Analysis and Prediction of Student Performance Using Data Mining Classification Algorithms

Analysis and Prediction of Student Performance Using Data Mining Classification Algorithms

Regression analysis of student academic performance using deep learning

Educational data mining helps the educational institutions to perform effectively and efficiently by exploiting the data related to all its stakeholders. It can help the at-risk students, develop recommendation systems and alert the students at different levels. It is beneficial to the students, educators and authorities as a whole. Deep learning has gained momentum in various domains especially image processing with a large dataset. We devise a regression model for analyzing the academic performance of the students using deep learning. We have applied regression using deep learning and linear regression on the dataset. For such models with smaller datasets, to tackle the issue of overfitting is critical. Hence, the parameters can be tuned to deal with such issues. The deep learning model records a mean absolute score (mae) of 1.61 and loss 4.7 with the value of k = 3. While the linear regression model yields a loss of 6.7 and mae score of 1.97. The deep learning model outperforms the linear regression model. The model may be successfully extended to other programmes to mine and predict the performance of the learners.

Student performance analysis and prediction in classroom learning: A review of educational data mining studies

Student performance modelling is one of the challenging and popular research topics in educational data mining (EDM). Multiple factors influence the performance in non-linear ways; thus making this field more attractive to the researchers. The widespread availability of e ducational datasets further catalyse this interestingness, especially in online learning. Although several EDM surveys are available in the literature, we could find only a few specific surveys on student performance analysis and prediction. These specific surveys are limited in nature and primarily focus on studies that try to identify possible predictor or model student performance. However, the previous works do not address the temporal aspect of prediction. Moreover, we could not find any such specific survey which focuses only on classroom-based education. In this paper, we present a systematic review of EDM studies on student performance in classroom learning. It focuses on identifying the predictors, methods used for such identification, time and aim of prediction. It is significantly the first systematic survey of EDM studies that consider only classroom learning and focuses on the temporal aspect as well. This paper presents a review of 140 studies in this area. The meta-analysis indicates that the researchers achieve significant prediction efficiency during the tenure of the course. However, performance prediction before course commencement needs special attention.

Capacitación: Evaluación áulica y desarrollo de habilidades docentes

The objective of this article was to show the training needs in classroom evaluation that affect teaching skills. The methodology used was quantitative and qualitative, observational, cross-cutting and descriptive and correlation. The collection of information was through a questionnaire with reagents in relation to training needs in classroom evaluation and teaching skills. The sample consisted of 435 Basic Education teachers working in 31 municipalities of the State of Coahuila de Zaragoza, the sample method was non-probabilistic for convenience, according to the diagnosis of the teacher training necessities, performed by the Secretary of Education of the State of Coahuila. The techniques used were descriptive statistics, multivariate and analysis of textual data. According to statistical empirical evidence, it is stated that if training courses provide teachers with strategies that develop the skill of creative thinking; through practical elements such as observation techniques and student performance analysis will impact their classroom evaluation.

Recommendation system to improve students performance using machine learning

For any educational institutes, students are a crucial asset so as to supply graduates of great quality. To achieve this, it is becoming essential for every college, school or any other scholastic institute to examine the performance of students. Due to the unbelievabledevelopment in recent technology like social media, it’s going to prevent the students from their concrete track, and this is often one among the explanations for the students to accomplish poor in academic accomplishments and it even results in course drop outs. Predicting student’s performance will attentive the learner to know about their performance and it provides as a gamble to increase their performance in future. However academic performance may differ from student to student as every student has diverse level of performance. It becomes difficult to research student data by relating statistical techniques or other outdated management tools. Hence there’s a requirement to develop an automatic machine learning tool for student performance analysis that might analyze student performance and can guide them by displaying the suggestions where they need improvement.

A comparative analysis of two computer science degree offerings

This article presents an in-depth analysis and comparison of two computer science degree offerings, viz., the Bologna BSc in Information Systems and Computer Engineering, offered by the Instituto Superior Técnico of the University of Lisbon, Portugal, and the BSc in Computer Science offered by the Pontifical Catholic University of Rio de Janeiro, Brazil. The analysis is based on the student transcripts collected from the academic systems of both institutions over circa one decade. The article starts with a description of the degrees and global statistics of the student population considered. Then, it presents a comparative analysis of the curricula, which focuses on how close students follow the recommended curricula, based on data visualization techniques and academic performance indexes. The indexes indicated a mismatch between the semesters that the curricula recommend for the courses and the semesters that students enroll in those courses. Furthermore, a visualization of course advances and delays indicated that a significant fraction of the students failed in the semester that the curricula recommend for the courses. The article moves on to present a comparative analysis of student performance in individual courses, and then applies a technique borrowed from Market Basket Analysis to investigate student performance in multiple courses that are taken in the same semester. The analysis pointed out sets of courses, at both degrees, that students are struggling with, when they take the courses in the same semester. Finally, the article summarizes the lessons learned, which invite academic administrators to reflect on the weaknesses and strengths of each degree analyzed. Specifically, the analysis suggests that the curricula should be reorganized to avoid that students take certain courses together, not because of conceptual reasons, but because students frequently fail if they do so. Some of these patterns are common to both degrees.

An Analysis of Students' Makeup-Exam Results and Performance in Undergraduate Biology Courses

A consistent challenge for undergraduate instructors is how to properly and objectively assess students who cannot attend regularly scheduled exams. Though many alternatives exist, perhaps the most common strategy is to allow students to take a makeup exam at a different time. Many instructors avoid this option for fear of the students gaining an unfair advantage in their exam preparations. I assessed student performance on makeup exams in relation to their typical performance on other exams throughout the course, to determine if there was any signal of score improvement or decline on makeup exams. I analyzed the data in regard to when students took the makeup exam, what their excuse for missing the regularly scheduled exam was, and the type of course in which they took the makeup. Students' makeup-exam scores were not significantly different from their regular-exam scores, though students who took a makeup due to a school-sponsored activity scored worse than students taking a makeup due to family emergencies or illness. While this research cannot definitively state that makeup exams do not provide some sort of advantage to student scores, it suggests that if students are trying to “game the system,” at the very least, they aren't winning.

Applicability of Traditional Classification Techniques on Educational Data

Student performance prediction and analysis is an essential part of higher educational institutions, which helps in overall betterment of the educational system. Various traditional Data Mining (DM) techniques like Regression, Classification, etc. are prominently utilized for analyzing the data coming from educational settings. The usage of DM in the area of academics is called Educational Data Mining (EDM). The current pilot study aims to determine the applicability of these standalone classification techniques namely; Decision Tree, BayesNet, Nearest Neighbor, Rule-Based, and Random Forest (RF). The present pilot study uses the WEKA tool to implement traditional classification techniques on a standard dataset containing student academic information and background. The paper also implements feature selection to identify the high influential features from the dataset. It helps in reducing the dimensionality of the dataset as well as enhancing the accuracy of the classifier. The results of classifiers are compared on basis of standard statistical measures like Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Kappa, etc. The results show the applicability of classification algorithms for student performance prediction which will help under-achievers and struggling students to improve. It is found the output that, J48 algorithm of the Decision tree gave the best results. Further, it is deduced from the comparative analysis that individual classifiers give different accuracy on the same dataset due to class imbalance in a multiclass dataset.

Analysis of Student Academic Performance Using Human-in-the-Loop Cyber-Physical Systems

Is it possible to analyze student academic performance using Human-in-the-Loop Cyber-Physical Systems (HiLCPS) and offering personalized learning methodologies? Taking advantage of the Internet of Things (IoT) and mobile phone sensors, this article presents a system that can be used to adapt pedagogical methodologies and to improve academic performance. Thus, in this domain, the present work shows a system capable of analyzing student behavior and the correlation with their academic performance. Our system is composed of an IoT application named ISABELA and a set of open-source technologies provided by the FIWARE Project. The analysis of student performance was done through the collection of data, during 30 days, from a group of Ecuadorian university students at “Escuela Politécnica Nacional” in Quito, Ecuador. Data gathering was carried out during the first period of classes using the students’ smartphones. In this analysis, we found a significant correlation between the students’ lifestyle and their academic performance according to certain parameters, such as the time spent on the university campus, the students’ sociability, and physical activity, etc.

Blended learning in teaching higher mathematics to students with disabilities

A stable trend in modern education is the transition from traditional or face-to-face learning to blended learning by introducing new online tools into the educational process. The complexity of converting traditional academic disciplines into a blended learning format arises from the need to simultaneously develop two interconnected and at the same time qualitatively different components (traditional and online). A correct balancing of the traditional and online components of blended learning allows making the educational process more comfortable and adaptable to the needs of every individual student. The solution of this problem largely depends on specific features of different academic disciplines. In this paper we propose a solution for basic mathematical disciplines taught to students with disabilities at Bauman Moscow State Technical University. The purpose of the study is to find the optimal organization of the process of studying higher mathematics by students with disabilities at Bauman Moscow State Technical University in the framework of blended learning, combining elements of the traditional teaching in the classroom and elements of online learning. Materials and research methods include the analysis of scientific and methodological literature on blended learning, the preparation and implementation of electronic training materials and teaching aids, the analysis of student performance and feedback, as well as the subsequent educational process adjustment based on the data received. The result of the study is the creation of a balanced two-component structure of the educational process in the framework of blended learning. The traditional component includes lectures, seminars and classroom consultations, and the online component consists of electronic training materials and communication tools via the Internet (email and a means of online consultations). Special hardware and software make online consultations similar in effectiveness to traditional classroom consultations. Every student at any place with access to the Internet is able not only to see and hear other participants of the online consultations, but also to see their notes and, in turn, show them his/her own notes made by hand on a regular sheet paper. The introduction of the online component into the educational process allows reducing the high learning rate typical for traditional learning and making it more acceptable for students experiencing certain health problems. Conclusion: the results of the study are used during classes in four mathematical disciplines: mathematical analysis, analytical geometry, linear algebra and integrals with differential equations, which are taught to students with disabilities in the first and second years of study at Bauman Moscow State Technical University.