Sentiment Analysis for Tweets using Patterns and Strategies to Detect the Genuineness of Tweets
Deepti Kulkarni1, Nagaraju Bogiri2

1Deepti Kulkarni, Computer Engineering Department, K. J.College of Engineering & Management, Savitribai Phule Pune University, Pune, India
2Nagaraju Bogiri, Computer Engineering Department, K. J.College of Engineering & Management, Savitribai Phule Pune University, Pune, India

Manuscript received on 02 July 2019 | Revised Manuscript received on 05 July 2019 | Manuscript published on 30 August 2019 | PP: 198-202 | Volume-8 Issue-10, August 2019 | Retrieval Number: H7397068819/2019©BEIESP | DOI: 10.35940/ijitee.H7397.0881019
Open Access | Ethics and  Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: Sentiment analysis related with distinguishing and classifying opinions or sentiments expressed in given text. Social media is completing a colossal quality of wealthy knowledge within the type of tweets, standing updates, diary posts etc. Sentiment analysis of this user generated knowledge is incredibly helpful in knowing the opinion of the gang. Twitter sentiment analysis is troublesome compared to general sentiment analysis thanks to the presence of slang words and misspellings. Knowledge base approach and Machine learning approach square measure the 2 methods used for analyzing sentiments from the text. Public and private opinion a few wide range of subjects’ square measure expressed and unfold frequently via numerous social media. Twitter offers organizations quick and effective thanks to analyze customers’ view toward the crucial to success within the market place. Developing a program for sentiment analysis is an approach to be accustomed computationally live customers’ perceptions. This project cognitive content together with varied patterns for tweets along a side multiple strategies to discover the sentiment class expressed in a very tweet and if a tweet is real or not. We proposed work to classify sentiments of tweets from people to determine if people are happy, sad, angry, etc. about particular topic. Also the purpose of the work is to check genuineness of tweets so that rumors about any topics can be detected and mitigated. This approach can be used in various fields further as like detecting people sentiment about particular social issues. Also fake tweets and rumors which may further exploit to social issues like riots, religion complexities can be removed. To achieve these goals and fetch tweets we used Twit4j API and various techniques such as NLP, TF-IDF, and Sentiment Classifications are applied to get results accordingly. We had maintained our own database of words for dictionary purpose as well as have been used Open Apache NLP with their predefined dictionaries. 
Keywords: NLP Sentiment Analysis, Machine Learning, Influence of tweets, POS
Scope of the Article: Machine Learning