IJARP
SJIF(2020): 5.702

International Journal of Advanced Research and Publications

High Quality Publications & World Wide Indexing!

Mining Of Tweets For Possible Investment In Lipa City Using Natural Language Processing And Naive Bayes Classifier

Volume 2 - Issue 12, December 2018 Edition
[Download Full Paper]

Author(s)
Francis G. Balazon, Myrna A. Coliat
Keywords
tweets, sentiment, investing, social media, naïve bayes
Abstract
Investing is one of the most popular businesses to make money grow. With that, one cannot have a mistake of just investing into something. The use of social media nowadays is fast and widespread all over the world. It could help a lot in gathering the information that an investor needed. With the use of a social media site, surveying will be easy and there will be no cost in surveying on what do people like or need these days. The study focused on the development of a website which collects all the tweets about Lipa City and then analyzes the sentiments of the tweets if it is positive or negative. It then categorizes the sentiments and displays the percentage of the tweets from different parameters. The researchers started the website application through data gathering, planning, and designing the functional features of the website. The processes involved in the sentiment analysis of the website are Naive Bayes Classifier to analyze the tweets and Natural Language Processing to properly categorize the parameters of the tweets. To see the errors of the website, the researchers evaluated the system by a series of testing and it was proven to be a functional and helpful website.
References
[1]. About Public and Protected Tweets, 2017. Available from Twitter Help Center: https://support.twitter.com/articles/14016; accessed June 7, 2017.

[2]. Haddi, E., Liu, X., Shi, Y. The Role of Text Pre-Processing in Sentiment Analysis. Available from Procedia Computer Science 17 ( 2013 ) 26 – 32: https://ac.els-cdn.com/S1877050913001385/1-s2.0-S187705091300 1385-main.pdf?_tid=8a9824be-c997-11e7-9f96-00000aab0f6c&acdnat=1510704016_b44a-f4d238db021be498a2cdcfea8192; accessed November 2, 2017.

[3]. Machine Learning General Concepts, 2016. Available from http://emma.memect.com/t/4734751241f61c53ff2194e4d3c59bea3412894005afd064799a4de96e13659c/Machine%20Learning%20General%20Concepts.pdf; accessed Nov. 2, 2017.

[4]. Ishwar, R.R. 10 Steps to Begin Sentiment Analysis to Glean Customer Insight, 2016. Available from https://www.infogix.com/blog/10-steps-to-begin- sentiment-analysis-to-glean-customer-insight/; accessed November 2, 2017.

[5]. Text Tokenization and Multiwords, 2017. Available from Meaning Cloud: https://www.meaningcloud.com/developer/resources/doc/models/models/text-tokenization-multiwords; accessed November 13, 2017.

[6]. Liu, B. Sentiment Analysis and Opinion Mining, Morgan & Claypool Publishers, 2012. Available from https://www.cs.uic.edu/~liub/FBS/Sentiment-Analysis-and-OpinionMining.pdf; accessed June 7, 2017.

[7]. Kanber, B. Machine Learning: Naïve Bayes Document Classification Algorithm in Javascript, 2012. Available from https://burakkanber.com/blog/machine-learning-naive-bayes-1/; accessed June 7, 2017.

[8]. Machine Learning General Concepts, 2016. Available from http://emma.memect.com/t/4734751241f61c53ff2194e4d3c59bea3412894005afd064799a4de96e13659c/Machine%20Learning%20General%20Concepts.pdf; accessed June 7, 2017.

[9]. AI-Natural Language Processing, 2017. Available from tutorialspoint: https://www.tutorialspoint.com/artificial_intelligence/artificial_intelligence_natural_language_processing.htm; accessed November 2, 2017.