This paper analyzes the odd-even formula in Delhi using tweets posted on Twitter from December 2015 to August 2016. Twitter is a social network where users post their feelings, opinions and sentiments for any event using hashtags and mentions. The tweets posted publicly can be viewed by anyone interested. This paper transforms the unstructured tweets into structured information using open source libraries. Further objective is to build a model using Support Vector Machines (SVM) to classify unseen tweets on the same context. This paper collects tweets on this event under the hashtag-#oddeven formula‖. This study explores four freely available resources in the form of Application Programming Interfaces (APIs)/Packages for labeling tweets for academic research. Four machine learning models using SVM multi-class classifier were built using the labels provided by the APIs/Packages. The performances of these four models are evaluated through standard evaluation metrics. The experimental results reveal that TextBlob and Pattern python packages outperformed Vivekn and Meaning Cloud APIs. This study may also help in decision making of this event to some extent.

No abstract

No abstract

This paper analyzes the odd-even policy in Delhi using tweets posted on Twitter from December 2015 to August 2016. Twitter is a social network where users post their feelings, opinions and sentiments for any event. This paper transforms the unstructured tweets into structured information using open source libraries. Further objective is to build a model using Deep Belief Networks classification (DBN) to classify unseen tweets on the same context. This paper collects tweets on this event under six hashtags. This study explores three freely available resources / Application Programming Interfaces (APIs) for labeling of tweets for academic research. This paper proposes three sentiment prediction models using the sentiment predictions provided by three APIs. DBN classifier is used to build six models. The performances of these six models are evaluated through standard evaluation metrics. The experimental results reveal that the TextBlob API and proposed Preference Model outperformed than the other four sentiment prediction models.