Student Stress Prediction Using Machine Learning Algorithms And Comprehensive Analysis

Student performance is most often hampered by mental health difficulties. Students' motivation, attention, and social ties can all be impacted by mental illness, all of which are key factors in their academic achievement. Due to the novel coronavirus pandemic, many institutions and colleges throughout the world have resorted to online learning. Despite widespread use of emergency remote learning (ERL) in higher education during the COVID-19 pandemic, little is known about the elements that influence student satisfaction and stress levels in this innovative learning environment in a crisis. Our research intends to provide a timely assessment of the COVID-19 pandemic's impact on college students' mental stress level employing machine learning algorithms to predict the stress faced by students based on their academic routines. Data collected through student surveys relating to a lot of factors such as time spent on studying, social media, health and fitness etc. provide a strong basis to determine students stress levels and via supervised machine learning algorithms predictions are done on the academic stress by analyzing the prime factors affecting the issue at hand. Various ML models such as Naive Bayes, Random Forest, Artificial Neural Networks (ANN) etc. have been employed and a comprehensive comparison is performed with the proposal of the most optimum algorithm for the prediction of stress level. Copyright © 2022, Anka Publishers. All rights reserved.

Comparative analysis of identifying accuracy of online misinformation of COVID-19 using SVM algorithm with decision tree classification

Aim: To improve the accuracy percentage of predicting misinformation about COVID-19 using SVM algorithm. Materials and methods: Support Vector Machine (SVM) with sample size = 20 and Decision Tree classification with sample size = 20 was iterated at different times for predicting the accuracy percentage of misinformation about COVID19. The Novel Poly kernel function used in SVM maps the dataset into higher dimensional space which helps to improve accuracy percentage. Results and Discussion: SVM has significantly better accuracy (94.48%) compared to Decision Tree accuracy (93%). There was a statistical significance between SVM and the Decision Tree (p=0.000) (p < 0.05 Independent Sample T-test).