TY  - JOUR
TI  - Sentiment Analysis of Top Colleges in India Using Twitter Data
AU  - Pallavi. S
AU  -  Ramya K.V
AU  -  Rachana C
AU  -  Vidyashree
AU  -  Gangadhar Immadi
JO  - International Journal of Scientific Research in Computer Science, Engineering and Information Technology
PB  - Technoscience Academy
DA  - 2017/06/30
PY  - 2017
DO  - https://doi.org/10.32628/IJSRCSEIT
UR  - https://ijsrcseit.com/CSEIT172340
VL  - 2
IS  - 3
SP  - 689	
EP  - 693
AB  - Sentiment analysis is used for identifying and classifying opinions or sentiments expressed in source text. Social media is generating a vast amount of sentiment rich data in the form of tweets, status updates, blog posts etc. Sentiment analysis of this user generated data is very useful in knowing the opinion of the crowd [6]. Due to the presence of slang words and misspellings, twitter sentiment analysis is difficult compared to general sentiment analysis. Sentiments from the source text will be analyzed by using a machine learning approach. Mining opinions and analyzing sentiments from social network data which will help in several fields such as even prediction, analyzing overall mood of public on a particular social issue. The accuracy of classification can be increased by using Natural Language Processing (NLP) Techniques. We present a new feature vector for classifying the tweets as positive, negative, neutral and undefined. The mined text information is subjected to Ensemble classification to analyze the sentiment. Ensemble classification involves combining the effect of various independent classifiers on a particular classification problem [1].  Multi-Layer Perceptron (MLP) is used to classify the features extracted from the reviews. A Decision Tree-based Feature Ranking is used for feature selection. Based on Manhattan Hierarchical Cluster Criterion the ranking will be done [5].