Early Detection of Poor Academic Performers Using Machine Learning Predictive Modeling

2021 ◽  
Vol 13 (3) ◽  
pp. 56-69
Author(s):  
Kaviyarasi Ramanathan ◽  
Balasubramanian Thangavel
Keyword(s):  
Academic Performance ◽  
Predictive Modeling ◽  
Academic Development ◽  
Attribute Selection ◽  
Educational Institutions ◽  
Key Factors ◽  
Attainment Gap ◽  
The Common ◽  
Low Performance ◽  
Academic Scores

The student's academic development, retention, and attainment gap are considered as the common key factors that influence the institutional academic performance. In this regard, educational institutions are focusing to reduce the attainment gap between good, average, and poor performing students. Two different datasets are taken for this study. Students' data is collected through questionnaire, and Dataset 1 (D1) is created. The second dataset (D2) is taken from the repository. Both the datasets have been preprocessed followed by attribute selection and predictive modeling. In this study, predictive models have been built, and the learners are classified as high, average, and low performers based on their academic scores as well as on their demographic characters. The three classifier models are applied on the datasets. Based on the evaluation measures, the best classifier is identified. This early identification of low performance students will help the educators as well as the learners to put a special care to enhance the learning process as well as to improve the academic performance.

Resilient Factors in Students with Disabilities

2018 ◽  
Vol 5 (2) ◽  
pp. 23 ◽  
Author(s):  
Gustavo Rafael Escobar Delgado ◽  
Anicia Katherine Tarazona Meza ◽  
Andy Einstein García García
Keyword(s):  
Academic Performance ◽  
Students With Disabilities ◽  
Latin American ◽  
Descriptive Study ◽  
The Other ◽  
Disabled Students ◽  
Low Performance ◽  
The Relationship ◽  
Latin American Population

The research analyzes the relationship between factors of resilience and academic performance in disabled students studying at the Technical University of Manabí. It is a correlational descriptive study conducted with a population of 88 disabled students, of which two groups were selected, one with high academic performance and the other with low performance. A questionnaire was designed and applied to determine the level of quality of life and risk factors of adolescents. Resilience was measured with the SV-RES scale created for the Latin American population.

scholarly journals Design and Optimization of a Fuzzy Logic System for Academic Performance Prediction

Symmetry ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 133
Author(s):  
Juan A. Rojas ◽  
Helbert E. Espitia ◽  
Lilian A. Bejarano
Keyword(s):  
Academic Performance ◽  
Performance Prediction ◽  
Teaching Methods ◽  
Continuous Monitoring ◽  
Educational Institution ◽  
Educational Institutions ◽  
Educational Support ◽  
Design And Optimization ◽  
Monitoring Process ◽  
Logic System

Currently, in Colombia, different problems in education exist; one of them is the inconvenience in tracing and controlling the learning trajectories that decide the topics taught in the country’s educational institutions. This work aims to implement a logic-based system that allows teachers and educational institutions to carry out a continuous monitoring process of students’ academic performance, facilitating early corrections of errors or failures in teaching methods, to promote educational support spaces within the educational institution.

Tied to the Common Core

2016 ◽  
Vol 52 (5) ◽  
pp. 793-840 ◽  
Author(s):  
Yi-Hwa Liou
Keyword(s):  
Common Core ◽  
Educational Leaders ◽  
State Standards ◽  
Leadership Team ◽  
Social Aspect ◽  
Key Factors ◽  
Core State ◽  
Social Network Modeling ◽  
Perception Gap ◽  
The Common

Purpose: Researchers and scholars have called for greater attention to collaboration among and between educational leaders in districtwide reform. This work underlines the important social aspect of such collaboration and further investigates the type of professional interaction among/between district and school leaders particularly around the Common Core State Standards (CCSS) and characterizes such interaction by key factors. Research Method: The work takes place in one school district of more than 30 schools serving students from traditionally marginalized backgrounds. Descriptive statistics, multilevel social network modeling, and network sociograms are used to understand the characteristics of professional interactions around CCSS implementation among district and site leaders. Findings: The findings indicate similarities and differences in characteristics of leaders who likely seek CCSS advice and leaders who likely provide that CCSS advice. Leader self-efficacy in implementing the CCSS positively explains the likelihood of both seeking and providing advice behaviors, and yet other factors (organizational learning, leadership, job satisfaction, and CCSS beliefs) each makes different contributions to the likelihood of seeking and/or providing the CCSS advice. Conclusion and Implications: This work suggests a discrepancy of leaders’ perceptions between advice seekers and providers, signaling a need for closing the perception gap between advice seekers and providers such that the leadership team could better craft coherent norms of collaboration in instructional improvement. Understanding the “why” of CCSS advice ties may help guide leaders toward the “how” to align professional and social aspects of change.

Apathy and Academic Failure among Students: Results of a Pilot Longitudinal Study

2021 ◽  
pp. 187-200
Author(s):  
A.A. Zolotareva ◽  
Keyword(s):  
Risk Factor ◽  
Academic Performance ◽  
University Students ◽  
Perceived Stress ◽  
Academic Motivation ◽  
Academic Failure ◽  
Educational Institutions ◽  
Boredom Proneness ◽  
Academic Control ◽  
Study Engagement

The current study was aimed to examine the impact of psychological adjustment / maladjustment on the academic performance of Russian university students. Previous studies have shown that academic performance is closely related to alienation from study, study engagement, academic motivation, perceived stress, academic control, and boredom proneness. Some researchers also have suggested that adolescent apathy may be the risk factor for academic failure among university students. In turn, the American psychologist R. Handelman defined adolescent apathy as a specific state of lack of goal-setting, energy and interest, indifference to changes and experience of difficulties in making decisions in young adults [27]. In September 2019, 103 students (73 females and 30 males) aged 16 to 21 years from several Moscow universities filled out instruments assessing adolescent apathy, alienation from study, study engagement, academic motivation, perceived stress, academic control, and boredom proneness. The study was conducted at seminars in psychological disciplines. All study participants received bonus points in these disciplines. In January 2019, based on the results of the examination session, an average score was calculated for each study participant. This score became a criterion for academic performance of university students. There were no statistically significant age and gender differences in the scores of psychological adjustment / maladjustment. The one-way analysis of variance (ANOVA) revealed that adolescent apathy was the single indicator that affects the academic performance of university students. Thus, the higher scores of adolescent apathy university students showed at the beginning of the academic year, the lower the average scores they received for the first exam session. Based on these data, it was concluded that adolescent apathy is a risk factor for academic failure and can serve as a target for preventive and interventional measures related to academic failure among Russian university students. Currently, in foreign practice, programs and recommendations are being developed and implemented for teachers of higher educational institutions who are faced with the adolescent apathy outcomes. Perhaps this study, which has proved the importance of adolescent apathy in the context of academic failure among university students, will be the first step towards the development and implementation of similar programs and recommendations for Russian educational institutions.

scholarly journals Institutional Collaboration on MOOCs in Education—A Literature Review

2017 ◽  
Vol 18 (6) ◽  
Author(s):  
Anne-Mette Nortvig ◽  
René B Christiansen
Keyword(s):  
Literature Review ◽  
Online Courses ◽  
Massive Open Online Courses ◽  
Educational Institutions ◽  
Passive Resistance ◽  
Institutional Collaboration ◽  
The Us ◽  
E Learning ◽  
The Common ◽  
Common Learning

<p class="3">This literature review seeks to outline the state of the art regarding collaboration between educational institutions on Massive Open Online Courses (MOOCs) launched in Europe and in the US for the past 10 years. The review explores enablers and barriers that influence national institutional MOOC collaboration, and looks into how existing knowledge about institutional collaboration on e-learning can be used in MOOC collaboration. The review is based on a literature search in databases and on snowballing techniques. It concludes that collaboration on MOOCs can be advantageous in terms of ensuring quality and innovation in the common learning designs, and that—in order to succeed—such projects need strategic and institutional support from all partners involved. Moreover, the review points out barriers concerning the reluctance of individual institutions to engage in national collaboration due to fear of potential loss of their own national branding and the teachers’ hesitancy or passive resistance to new educational platforms and formats.</p>

scholarly journals Statistically, Does peer assisted learning make a difference on a UK engineering degree programme? HETL Scotland 2017

2019 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Anne Louise Nortcliffe ◽  
Sajhda Parveen ◽  
Cathy Pink-Keech
Keyword(s):  
Academic Performance ◽  
Statistical Analysis ◽  
Positive Impact ◽  
Data Sets ◽  
Social Categories ◽  
Peer Assisted Learning ◽  
Student Records ◽  
Content Type ◽  
Attainment Gap ◽  
The Impact

Purpose Black British minority ethnics (BME) students are nationally underachieving in comparison to their Ethnic Chinese and White peers, showing typically a 16 per cent graduate attainment gap in the UK. Previous research has suggested that the attainment gap could be explained by BME student disengagement, as the students typically commute from family home to University, and they work part time. However, peer-assisted learning (PAL) has been shown to have a positive impact on addressing and resolving student alienation and disengagement. However, a question still remains regarding whether student perceptions hold up to statistical analysis when scrutinised in comparison to similar cohorts without PAL interventions. The paper aims to discuss these issues. Design/methodology/approach This paper presents the results of a statistical study for two cohorts of students on engineering courses with a disproportionately high representation of BME students. The research method involved a statistical analysis of student records for the two cohorts to ascertain any effect of correlation between: PAL; student ethnicity; and student parental employment on student academic performance and placement attainment. Findings The results indicate that PAL has no significant impact on the academic performance; however, PAL has a positive impact on the placement/internship attainment for BME students and students from parental households with parents in non-managerial/professional employment. Research limitations/implications The research limitations are that the cohorts are small, but more equal diverse mix of different social categories than any other courses. However, as the cohorts are less than 30 students, comparing social categories the data sets are small to have absolute confidence in the statistical results of academic performance. Even the t-test has its limitations as the subjects are human, and there are multiple personal factors that can impact an individual academic performance; therefore, the data sets are heterostatic. Practical implications The results highlight that there is need for pedagogy interventions to support: ideally all BME students from all social categery to secure placements; BME students who are unable to go on placement to gain supplementary learning that has the same impact on their personal development and learning as placement/internship experience; and White students from managerial/professional family households to engage more in their studies. Social implications Not addressing and providing appropriate pedagogy interventions, in the wider context not addressing/resolving the BME academic and placement attainment gap, a set of students are being disadvantaged to their peers through no fault of their own, and compounding their academic attainment. As academics we have a duty to provide every opportunity to develop our student attainment, and as student entry is generally homogeneous, all students should attain it. Originality/value Previous research evaluation of PAL programmes has focused on quantitative students surveys and qualitative semi-structured research interviews with students on their student engagement and learning experience. On the other hand, this paper evaluates the intervention through conducting a quantitative statistical analysis of the student records to evaluate the impact of PAL on a cohort’s performance on different social categories (classifications) and compares the results to a cohort of another group with a similar student profile, but without PAL intervention implementation.

scholarly journals Geo-gebra como herramienta didáctica en el proceso de enseñanza-aprendizaje de la matemática, y su incidencia en el rendimiento académico en los estudiantes de la carrera de ingeniería agronómica

2019 ◽  
Vol 3 (3.1) ◽  
pp. 204-223
Author(s):  
Juan Manuel Martínez Nogales ◽  
Jorge Cachuput Gusñay ◽  
Hernan Eriberto Chamarro Sevilla ◽  
Jorge Rigoberto López Ortega
Keyword(s):  
Academic Performance ◽  
Learning Process ◽  
Work Experience ◽  
Educational Software ◽  
High Rate ◽  
First Semester ◽  
Culture Of Learning ◽  
Low Performance ◽  
Teaching Learning ◽  
Engineering Career

The Geo-Gebra software as a didactic tool in the teaching-learning process of mathematics and its impact on academic performance in the first semester students of the Faculty of Natural Resources, Agronomic engineering career of ESPOCH. The problem that has been detected in the students of the first semester, a high rate of low performance in the learning of mathematics, in the race because there is a culture of learning on the part of the students, it is determined that we must make profound changes in educational paradigms, the proposal for this process is to use the Geo-Gebra software didactic tool of mathematics, for the research was based on a questionnaire of questions applied with respect to the use of Goe-Gebra software, as a teaching resource in teaching- learning of mathematics, then with the use of this tool a form of satisfaction was applied to students and teachers, to later make the didactic guide using the Geo - Gebra educational software, hence the importance of making striking designs according to the level or semester and with contents attached to the current geometry plans and programs in which  educational. According to the work experience, a didactic guide was designed for the use of educational software specifically for inequations. It is concluded the research carried out that 72% of the students surveyed consider, using the ICTs it would improve the learning of the geometry and its academic performance; Therefore, it is recommended to train the teachers of the area and promote the proposal in the institution for the application in the teaching-learning process.

scholarly journals Academic Performance, Self Efficacy and Perceived Social Support of Visually Impaired Students

2016 ◽  
Vol 22 (1) ◽  
pp. 72
Author(s):  
Sarah Shahed ◽  
Zahida Ilyas ◽  
Ali Madeeh Hashmi
Keyword(s):  
Social Support ◽  
Academic Performance ◽  
Self Efficacy ◽  
Visually Impaired ◽  
Perceived Social Support ◽  
Educational Institutions ◽  
Social Support Scale ◽  
Visually Impaired Students ◽  
Set Up ◽  
Medical University

AbstractObjective:The present study investigated the relationship between academic performance, self efficacy and perceived social support of visually impaired students.Sample:A purposive sample consisting of 60 visually impaired students was selected from three institutions in Lahore, comprising boys and girls in equal number.Instruments: Translated versions of Multidimensional Perceived Social Support Scale by Zimet, Dehlam and Farley and Generalized Self Efficacy Scale by Jerusalem were used for the purpose of data collection.Results:Significant correlation was found between academic performance, self efficacy, and perceived social support. Gender differences were found in academic achievement. Girls secured a higher percentage of marks than boys.Conclusion:Visually impaired students can make King Edward Medical University/ Mayo Hospital, Lahore significant educational attainments if they are provided support. This in turn will add to their self efficacy which may lead to even greater achievement. Educational institutions need to design and set up support networks by involving faculty and students for promoting higher achievement and selfreliance in visually impaired students.

scholarly journals KoGuN: Accelerating Deep Reinforcement Learning via Integrating Human Suboptimal Knowledge

2020 ◽  
Author(s):  
Peng Zhang ◽  
Jianye Hao ◽  
Weixun Wang ◽  
Hongyao Tang ◽  
Yi Ma ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Prior Knowledge ◽  
Learning Process ◽  
Learning Algorithm ◽  
Fuzzy Rule ◽  
Policy Network ◽  
Human Knowledge ◽  
Learning Agents ◽  
The Common ◽  
Low Performance

Reinforcement learning agents usually learn from scratch, which requires a large number of interactions with the environment. This is quite different from the learning process of human. When faced with a new task, human naturally have the common sense and use the prior knowledge to derive an initial policy and guide the learning process afterwards. Although the prior knowledge may be not fully applicable to the new task, the learning process is significantly sped up since the initial policy ensures a quick-start of learning and intermediate guidance allows to avoid unnecessary exploration. Taking this inspiration, we propose knowledge guided policy network (KoGuN), a novel framework that combines human prior suboptimal knowledge with reinforcement learning. Our framework consists of a fuzzy rule controller to represent human knowledge and a refine module to finetune suboptimal prior knowledge. The proposed framework is end-to-end and can be combined with existing policy-based reinforcement learning algorithm. We conduct experiments on several control tasks. The empirical results show that our approach, which combines suboptimal human knowledge and RL, achieves significant improvement on learning efficiency of flat RL algorithms, even with very low-performance human prior knowledge.

Sign in / Sign up

Export Citation Format

Share Document