• Vishal Avacha
• Omkar Bhosale
• Pravin Khot
• Pradnya Bramhane
• Riyazahmed Jamadar

More range of users shares their opinions on Twitter, creating it a valuable platform for trailing and analyzing public sentiment. Such trailing and analysis will offer important data for higher cognitive process in numerous domains. Thus it's attracted attention in each academe and trade. Previous analysis chiefly targeted on modeling and trailing public sentiment. During this work, we have a tendency to move one step any to interpret sentiment variations. We have a tendency to discovered that rising topics (named foreground topics) inside the sentiment variation periods area unit extremely associated with the real reasons behind the variations. supported this observation, we have a tendency to propose a Latent Dirichlet Allocation (LDA) based mostly model, Foreground and Background LDA (FB-LDA), to distil foreground topics and strain long background topics. These foreground topics will provide potential interpretations of the sentiment variations. To any enhance the readability of the well-mined reasons, we have a tendency to choose the foremost representative tweets for foreground topics and develop another generative model referred to as Reason Candidate and Background LDA (RCB-LDA) to rank them with reference to their “popularity” inside the variation amount. Experimental results show that our ways will effectively notice foreground topics and rank reason candidates. The projected models may also be applied to alternative tasks like finding topic variations between 2 sets of documents.

Latent Dirichlet Allocation (LDA), Sentiment Analysis, Tweets, Opinion mining

"SURVEY ON INTERPRETING THE PUBLIC SENTIMENT VARIATIONS ON TWITTER ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.3, Issue 5, page no.287-289, May-2016, Available :http://www.jetir.org/papers/JETIR1605049.pdf

"SURVEY ON INTERPRETING THE PUBLIC SENTIMENT VARIATIONS ON TWITTER ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.3, Issue 5, page no. pp287-289, May-2016, Available at : http://www.jetir.org/papers/JETIR1605049.pdf