چکیده:
World of technology provides everyone with a great outlet to give their opinion, using social media like Twitter and other platforms. This paper employs machine learning methods for text analysis to obtain sentiments of reviews by the people on twitter. Sentiment analysis of the text uses Natural language processing, a machine learning technique to tell the orientation of opinion of a piece of text. This system extracts attributes from the piece of writing such as a) The polarity of text, whether the speaker is criticizing or appreciating, b) The topic of discussion, subject of the text. A comparison of the work done so far on sentiment analysis on tweets has been shown. A detailed discussion on feature extraction and feature representation is provided. Comparison of six classifiers: Naïve Bayes, Decision Tree, Logistic Regression, Support Vector Machine, XGBoost and Random Forest, based on their accuracy depending upon type of feature, is shown. Moreover, this paper also provides sentiment analysis of political views and public opinion on lockdown in India. Tweets with ‘#lockdown’ are analysed for their sentiment categorically and a schematic analysis is shown.
خلاصه ماشینی:
Sentiment Analysis of Tweets Using Supervised Machine Learning Techniques Based on Term Frequency Deepti Aggarwal* *Corresponding Author, Assistant Professor, JSS Academy of Technical Education, Noida.
This paper employs machine learning methods for text analysis to obtain sentiments of reviews by the people on twitter.
Comparison of six classifiers: Naïve Bayes, Decision Tree, Logistic Regression, Support Vector Machine, XGBoost and Random Forest, based on their accuracy depending upon type of feature, is shown.
(2016) introduces a paper having a title Apply Word Vectors for Sentiment Analysis of APP Reviews using techniques like Stanford Tokenizer, for tokenization of given corpus dataset with 85% Accuracy.
Alsaeedi & Khan (2019) introduces a paper with a title A Study on Sentiment Analysis Techniques of Twitter Data using techniques Supervised Machine Learning approach, Ensemble Approaches, Lexicon-Based Methods with 80% Accuracy using Machine learning algorithms and with 85% Ensemble and hybrid-based algorithms.
Naïve Bayes machine learning method to increase the performance of sentiment analysis Domain-specific analogy, express positive opinion about Oman tourism.
Giachanou & Crestani (2016) reviews all the methods available for text classification for classifying tweets for their sentiments.
Other classifiers such as tree based were not considered which might perform better, the comparison is not complete for context of supervised machine learning algorithms as all classification models are not compared (Kumar & Jaiswal, 2020).
Frequencies of top 20 bigrams / Feature Representation To feed data to machine learning models which are statistical models we cannot directly use textual words.
Sentiment Analysis of Tweets Using Supervised Machine Learning Techniques Based on Term Frequency.