TRAP@NCI

Studying the Studies: An analysis of Twitter to investigate the volume, topics, sentiment and contradictions of the latest “New Study”

Kennedy, Rachel (2014) Studying the Studies: An analysis of Twitter to investigate the volume, topics, sentiment and contradictions of the latest “New Study”. Diploma thesis, Dublin, National College of Ireland.

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

Abstract

This project is based on data pertaining to new studies collected from Twitter. The textual data was gathered using code developed in Java, and was cleaned and parsed into a format where further analysis could take place.

The analysis involved topic analysis, sentiment analysis, identification of contradictions, identification of factors that increase tweet longevity and a brief look at the use of language.

Topic analysis found that health is the most common subject discussed in the tweets (40.21%), followed by conversational and humorous tweets (34.45%) and followed by technology at 3.75%.

Sentiment analysis was carried out using the AlchemyAPI tool and showed a negative sentiment overall, with only three topics (marketing, entertainment and business) having a positive sentiment score.

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: 16 Dec 2014 14:37
Last Modified: 16 Dec 2014 14:37
URI: http://trap.ncirl.ie/id/eprint/1891

Actions (login required)

View Item View Item