Abstract Now a day’s most of students communicate with each other using various social media networks such as Twitter, Facebook, YouTube and what’s app. Students shares their opinions, concerns and emotions about the learning process. From these social sites there are large size of unstructured data are generated which consists students important data. To manage this unstructured data are too difficult task, so we use various techniques to solve this problem. In this paper we collect all Engineering students communication from twitter to analyse various problems like heavy study load, negative emotions, lack of social engagement and sleepy problems. Students’ comments from twitter are classified into various above problem using Naive Bayes algorithm. Also we used various algorithms for processing data like stemming, TF-IDF algorithm and cosine similarity. This paper shows that how students share their opinions through twitter and which comments are in which category. Using Memetic algorithm we got the more accurate results.
[1]
Mihaela Vorvoreanu,et al.
Managing identity across social networks
,
2011
.
[2]
Devin Gaffney.
#iranElection: quantifying online activism
,
2010
.
[3]
Mary J. Culnan,et al.
How Large U.S. Companies Can Use Twitter and Other Social Media to Gain Business Value
,
2010,
MIS Q. Executive.
[4]
M. Vorvoreanu,et al.
Online Identity Management Literacy for Engineering and Technology Students
,
2012
.
[5]
Patricia G. Lange,et al.
Living and Learning with New Media: Summary of Findings from the Digital Youth Project
,
2009
.
[6]
Xin Chen,et al.
Mining Social Media Data for Understanding Students’ Learning Experiences
,
2014,
IEEE Transactions on Learning Technologies.