DOIONLINE 
DOIONLINE Publish In |
International Journal of Advances in Electronics and Computer Science-IJAECS |
 Journal Home Volume Issue |
||||||||
Issue |
Volume-3,Issue-12 ( Dec, 2016 ) | |||||||||
Paper Title |
Analyzing Student’s Learning Experiences Through Social Media Data Using Machine Learning Tool | |||||||||
Author Name |
Ajinkya .A. Londhe, Jamgekar R.S, Solunke B. R | |||||||||
Affilition |
M.E (Computer) M.E (Computer), Assistant Professor, M.TECH (Computer), Assistant Professor, Department of Computer Science & Engineering, N B Navale Sinhgad College of Engineering, Solapur 413255 | |||||||||
Pages |
105-108 | |||||||||
Abstract |
Social media which can be stated as online media supporting social interaction & user contribution is playing a crucial role in social networking and sharing of data. School, Colleges and universities are beginning to accept social media as a source of mean for enhancement of education system. Student’s comfortable and accidental talk’s on social media shade light into their educational experience, mind-set, and worries about their learning procedure. Social media sites such as twitter, Facebook, and you-tube provides grand platform to large amount of user without any restrictions to share their opinions, educational learning experience and concerns via their posts Assessment of such data in social network is quite a challenging process. In the proposed system, there will be advancement to mine the data which constitute both qualitative analysis and extensive data mining technique. Tweets will be categorized into different categories considering various striking themes. We use WEKA a data mining/machine learning tool to integrate Naive Bayes classifier and support vector machine (SVM)on mined data for qualitative analysis purpose to get the deeper understanding of the data and obtain more accurate results out of the data-set using label based measure to analyze the results. This scheme, presents an approach that show how unconstrained social media data can provide awareness and insights into students’ learning experiences. Keywords— Computers and education, Social networking, Social media data, WEKA, Naive Bayes, SVM and Data mining. | |||||||||
| View Paper | ||||||||||
