UMP Institutional Repository

The English language multilingual processing for sentiment analysis in social media by using Python NLTK Text Classification, Miopia and MeaningCloud sentiment analysis techniques

Allen, Lee Wei Kiat (2019) The English language multilingual processing for sentiment analysis in social media by using Python NLTK Text Classification, Miopia and MeaningCloud sentiment analysis techniques. Faculty of Computer System & Software Engineering, Universiti Malaysia Pahang.

[img]
Preview
Pdf
The English language multilingual processing for sentiment analysis.pdf - Accepted Version

Download (340kB) | Preview

Abstract

Nowadays, numerous numbers of companies have utilized the web to offer their services and products. Web customers dependably look through the comments of other customers towards a product or service before they chose to buy the things or viewed the films. The company needs to analyse their customers’ sentiment and feeling based on their comments. The outcome of the sentiment analysis makes the companies easily to discover the expression of their users is more to positive or negative. The sentiment analysis is utilized in data mining. The accuracy of the output is the issue of the sentiment analysis. The objective of this research is to explore and evaluate English language using 3 different sentiment analysis techniques which are the Python NLTK Text Classification, Miopia and MeaningCloud tools in term of their text classification (positive or negative). 3 sentiment analysis techniques have been used in this research to analyse the sentiment analysis of the reviews and comments from English language in social media. There are 8 phases in the research flow which are problem statement. objective, literature reviews, framework understanding, sentiment data understand, propose the framework, measurement the sentiment data and evaluation of the results phases. The accuracy of the output for the sentiment analysis techniques (Python NLTK Text Classification, Miopia and MeaningCloud) in English language will be compared. The exactness of the Python NLTK Text Classification (Corpus-based approach), Miopia (Lexicon-based approach) and MeaningCloud (Hybrid approach) are 74.5%, 73% and 82.13%. The accuracy of MeaningCloud is the highest among the 3 sentiment analysis techniques. This is because this technique hybrids the characteristics of corpus based and lexicon- based approach and achieve the maximum classification accuracy. Therefore, hybrid machine interpretation method is considered the best among these three models.

Item Type: Undergraduates Project Papers
Additional Information: Project Paper (Bachelors of Computer Science (Computer Systems & Networking)) -- Universiti Malaysia Pahang – 2019, SV: DR. NOR SARADATUL AKMAR BINTI ZULKIFLI, e-Thesis
Uncontrolled Keywords: Sentiment analysis techniques; Python NLTK Text Classification; Miopia; MeaningCloud
Subjects: Q Science > QA Mathematics > QA76 Computer software
Faculty/Division: Faculty of Computer System And Software Engineering
Depositing User: Mrs. Sufarini Mohd Sudin
Date Deposited: 05 Dec 2019 02:02
Last Modified: 05 Dec 2019 02:02
URI: http://umpir.ump.edu.my/id/eprint/26734
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item