TRAP@NCI

Apple Inc. : Social Media Sentiment Analysis using Data Mining Techniques

Cashill, David (2014) Apple Inc. : Social Media Sentiment Analysis using Data Mining Techniques. Diploma thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Diploma)
Download (2MB) | Preview

Abstract

Sentiment analysis, which can also be known as opinion mining, is an increasingly popular form of research used by businesses, companies and marketers, it used mostly for qualitative research. Technologies in data mining are so powerful at that this moment in time that data scientists have a vast amount of tools available in order to conduct analysis. The idea of sentiment analysis is to elicit the opinions and attitudes of social media users from sources such as blogs, microblogs and social media networks. These opinions and attitudes, or the “Sentiment” of the social media users can then be combined in order to set out a measurement of the communal sentiment in regard to the, business or company, person or topic being analysed.

Twitter is a social media microblogging platform that allows its users to post messages of up to 140 characters about anything they wish to discuss or comment on, users can also follow other users and receive their posts, this can create conversations about likes and dislikes etc. Twitter has become one of the major social media communication platforms in recent years due to its millions of users worldwide from all social backgrounds, it has also become a valuable source of data. This is because of the way in which these worldwide users share their opinions, likes, dislikes and emotions with each other on a daily basis.

This project will focus on ascertaining the sentiment in regard to a major brand of electronics manufacturer, Apple Inc. Machine learning algorithms are used in order to elicit sentiment from the collected data (tweets) and to then classify the data into “positive” and “negative” sentiment. For this purpose a total of 23,428 tweets were collected from 29th June 2014 to 21st July 2014. This data was analysed using machine learning algorithms and was classified successfully.

Item Type: Thesis (Diploma)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Divisions: School of Computing > Higher Diploma in Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 15 Dec 2014 10:38
Last Modified: 15 Dec 2014 10:38
URI: http://trap.ncirl.ie/id/eprint/1857

Actions (login required)

View Item View Item