Social Media Content Analysis and Classification Using Data Mining and ML
Students' natural conversations on social media such as Twitter and Whatsapp are useful to understand their learning experiences feelings. Collecting and analyzing data from such media can be a difficult task. However, the large scale of data is required for automatic data analysis techniques to classify Twitter data. The proposed new system is a combination of qualitative analysis and large-scale data mining and ML techniques. This system focuses on engineering students' Twitter posts, which are collected from engineering colleges, to understand issues and problems in their learning. The authors first conduct a qualitative analysis using ML studio on tweets collected from engineering colleges using term #DStudentsproblems, engineeringProblem, Aluminisuggestions, and ladyEngineer. Collected tweets are related to engineering students' college lives. In the proposed system, a multi-label classification algorithm to classify tweets reflecting students' problems such as soft skill issues, heavy study load, lack of social engagement, and sleep problems is used.