Open AccessA Novel Adaptable Approach for Sentiment Analysis
Author(s) -
R. Aishwarya,
C Ashwatha,
A.Pavana Deepthi,
Beschi Raja J
Publication year - 2019
Publication title -
international journal of scientific research in computer science, engineering and information technology
Language(s) - English
Resource type - Journals
ISSN - 2456-3307
DOI - 10.32628/cseit195263
Subject(s) - sentiment analysis , computer science , boosting (machine learning) , the internet , process (computing) , data science , artificial intelligence , machine learning , data mining , world wide web , operating system
The internet has provided many novel ways for people to express their ideas and views about different topics, ideas and trends. The contents generated by the users which are present on various mediums like internet blogs, discussion forums, and groups paves a strong base for decision making in diverse fields such as digital advertising, election polls, scientific predictions, market surveys and business zones etc. Sentiment analysis is the process of mining the sentiments from the data that are available in online platforms and categorizing the opinion towards a particular entity that falls on three different categories which are positive, neutral and negative. In this paper, the problem of sentiment classification of election dataset in twitter has been addressed. This paper summarizes the ensemble method, the best way to achieve classification. And also about the ada boosting algorithm and artificial neural networks by which the optimized prediction accuracy is achieved.