Naive Bayes Classifier for web text Analysis

Software Engineering

Social media allows the creation and interactions of user-created content. Social medium places include Facebook, Twitter etc. Student’s casual discussion on social media focused into their educational experience, mind-set, and worry about the learning procedure. Information from such instrumented environments can present valuable data to report student problem. Examining such data can be challenging. The problem of student’s experiences reveal from social media content need human analysis. It pays attention on engineering student’s Twitter posts to know problem and troubles in their educational practices. This paper proposes a workflow to put together both qualitative investigation and large-scale data mining scheme. First a sample is taken from student and then qualitative analysis conducted on that sample which is associated to engineering student’s educational life. It is found that engineering students encounter problems such as heavy learning load, lack of social meeting, and sleep deficiency. Based on this outcome, a multi-label classification algorithm that is Naive Bayes Multi-label Classifier algorithm and Decision tree algorithm is applied to categorize tweets presenting student’s problems. The algorithm prepares a detector of student problems. This study presents a tactic and outcome that demonstrate how casual social media data can present insight into student’s incident.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.