TRAP@NCI

Market structure analysis for the restaurants serving Indian cuisine in Dublin using comparative opinions and clustering

Halladakoppalu Shivanna, Ravi Kiran (2018) Market structure analysis for the restaurants serving Indian cuisine in Dublin using comparative opinions and clustering. Masters thesis, Dublin, National College of Ireland.

[img]
Preview
PDF (Master of Science)
Download (1MB) | Preview

Abstract

The restaurant industry is a very competitive one, everyone wants to be ahead of the others, but how? online reviews is the answer, they have abundant information from various people who visit these restaurants frequently comparing the services and giving out their opinions. So a method of identifying the comparative sentences using the restaurant names was used. A single line graph network was used to check for the direction and number of the comparisons for each restaurant. The market structure could be easily determined and visualized by this single line graph. The importance values were calculated based on the sentiment scores present in each restaurant, from which the focal restaurant could be easily identified using the cluster analysis. Also, this gives us the top restaurants in the market. Managers of the restaurants will get to know the direct and indirect competition from the other restaurants. They can keep an eye on the competitors and devise their course of action to be ahead of them.

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 > Food Industry
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: 05 Nov 2018 13:40
Last Modified: 05 Nov 2018 13:40
URI: http://trap.ncirl.ie/id/eprint/3431

Actions (login required)

View Item View Item