TRAP@NCI

How can Google Trends and sentiment analysis of TripAdvisor and Facebook predict visitor numbers to the United Kingdom and Canada from 2010 - 2015?

Hutchin, Emmet (2016) How can Google Trends and sentiment analysis of TripAdvisor and Facebook predict visitor numbers to the United Kingdom and Canada from 2010 - 2015? Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview
[img]
Preview
PDF (Configuration File)
Download (842kB) | Preview

Abstract

Internet search data and sentiment analysis are becoming standard prediction methodologies and have been used to predict everything from the stock market to cinema box office revenues, they have been seen as separate tools to carry out analysis. This paper attempts to bridge the gap in the existing research by using search and sentiment analysis to predict future visitor numbers to the UK and
Canada. Sentiment analysis using the OL and HGI lexicons will be performed on hotel reviews for the UK and Canada scraped from TripAdvisor and comments extracted from hotel Facebook pages over a five-year period. This data will be matched with Google Trends data. It also aims to establish the best way to combine the data and using regression analysis. Some promising results are achieved by using multiple regression with Google TripAdvisor and Facebook data achieving over twice the correlation with visitor numbers than the highest scoring individual
variable.

Item Type: Thesis (Masters)
Subjects: Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science

H Social Sciences > HD Industries. Land use. Labor > Specific Industries > Hospitality Industry
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: CAOIMHE NI MHAICIN
Date Deposited: 03 Dec 2016 11:49
Last Modified: 03 Dec 2016 14:50
URI: http://trap.ncirl.ie/id/eprint/2489

Actions (login required)

View Item View Item