Assorted Sentiment Model for Publically Available Page of Facebook
Saurabh Dhyani1, G. S. Thakur2

1Saurabh Dhyani*, PhD Degree, Department of Computer Applications, Maulana Azad National Institute of Technology, Bhopal (Madhya Pradesh) India.
2Ghanshyam Singh Thakur, Assistant Professor, Department of Computer Applications, Maulana Azad National Institute of Technology. Bhopal (Madhya Pradesh) India.
Manuscript received on December 18, 2019. | Revised Manuscript received on December 26, 2019. | Manuscript published on January 10, 2020. | PP: 1160-1167 | Volume-9 Issue-3, January 2020. | Retrieval Number: B7739129219/2020©BEIESP | DOI: 10.35940/ijitee.B7739.019320
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Ecommerce industries expose public page in the social network site (Facebook, twitter etc) for the intention of improving of business strategy. They extract public mood about the social network page in the forms of total likes, the total share of the page and sentiment of all comments to the social network page similar way celebrities expose public page in the social network sites for the intention of improving its fame. We have developed an assorted model for publicly available page of Facebook. This assorted model is the combination of data extractor model, language convertor and cleaned model, and sentiment analyzer model. Our data extractor model extract comments on all the posts of publicly expose Facebook page in the less span of time. Language convertor and cleaned model would work for conversion of text written in different Indian language to the English language and after that English written text would be cleaned through cleaned model. Language convertor is made after implementing CILTEL model. CILTEL model converts comments written in the Indian languages in the English language. Cleaning model will clean all the comments of all the posts on the Facebook page. Finally, sentiment extraction model will extract sentiments of all the comments of the Facebook page. We have implemented classification using three machine learning algorithm, namely naïve bayes algorithm, perceptron algorithm and rocchio algorithm for checking the performance of our sentiment analysis model. Our assorted sentiment analysis model is beneficial to users like marketing industry, election parties and celebrities. 
Keywords: Sentiment Analysis, Social media mining, Classification, Facebook, Content Mining, Machine learning algorithm
Scope of the Article: Classification