Your browser doesn't support javascript.
Performance Comparison of Machine Learning Algorithms for Prediction of Students' Social Engagement
5th International Conference on Computing Methodologies and Communication, ICCMC 2021 ; : 947-951, 2021.
Article in English | Scopus | ID: covidwho-1247042
ABSTRACT
The various techniques and algorithms of ML DL are becoming popular for prediction with different level of accuracy. This paper includes performance comparison of few machine learning algorithms in the reference of student social engagement during covid-19 pandemic period. In this study, the comparison of Naïve Bayes, J48 tree, REPTree and Random forest algorithm is carried on structured dataset of 1200+ instance. In this paper, study proposes scrutinizes commonly used social app platform. Further, it compares them with the various ML approach. The objective of this study is to foreseeing the correlation between student social engagement for one the most popular social engagement platform during covid-19 pandemic. This paper focusses on accuracy, F-measure and time to summarize comparison result. The findings of the study and dynamic analysis indicate ML/Deep learning algorithm can lead better accuracy and other factor for preprocessed student social engagement dataset. The finding can predict engagement of students for most popular social media platform with performance comparison of ML algorithm. © 2021 IEEE.

Full text: Available Collection: Databases of international organizations Database: Scopus Type of study: Prognostic study / Randomized controlled trials Language: English Journal: 5th International Conference on Computing Methodologies and Communication, ICCMC 2021 Year: 2021 Document Type: Article

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: Databases of international organizations Database: Scopus Type of study: Prognostic study / Randomized controlled trials Language: English Journal: 5th International Conference on Computing Methodologies and Communication, ICCMC 2021 Year: 2021 Document Type: Article