• Sandeep Kaur
• Dr. Vinay Chopra

With the widespread usage of social media, forums and blogs, customer reviews and opinions emerged as critical factor for decision making in various areas. A lot of researchers focused on automatically categorizing reviews on the basis of polarity such as positive, negative and neutral called as sentiment analysis. In this paper, framework for analysing emotions of users in social media text such as twitter using emotion theories has been presented. However, data collected from twitter contains lot of irrelevant and redundant features. Hence, it is important to select only those features which contribute best to the accuracy of the classifier. To tackle with such problem, a hybrid algorithm using Ant Colony Optimization variant Max-Min Ant system and Support Vector Machines has been introduced through this paper. It has been found that accuracy of classifier enhances when optimal features are selected using feature selection algorithm.

Support Vector Machines, Feature Selection, Ant Colony Optimization, Max-Min Ant System.

"Emotion Analysis of Twitter Data using Hybrid Support Vector Machines and Ant Colony Optimization Variant ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 12, page no.573-577, December-2018, Available :http://www.jetir.org/papers/JETIR1812774.pdf

"Emotion Analysis of Twitter Data using Hybrid Support Vector Machines and Ant Colony Optimization Variant ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 12, page no. pp573-577, December-2018, Available at : http://www.jetir.org/papers/JETIR1812774.pdf