NORMA eResearch @NCI Library

Topic modelling: Location-based offline advertising using Twitter

Cool, Martijn (2018) Topic modelling: Location-based offline advertising using Twitter. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (914kB) | Preview


Targeting the desirable audience for offline advertisements may be challenging. Unlike online where user profiling is common practice, offline advertising can only target a broader, less appropriate audience. Offline is generally more expensive than online marketing, but your advertisements may be overshadowed with the greater amounts of online advertising content, therefore, offline advertising is still valuable. This study researches an alternative approach to offline advertising with the use of online publicly available information from Twitter. The aim of this research is to investigate to what extent interest topics can be identified from Twitter content in a geographical region. Tweets located in Dublin County were collected and used to identify specific interest zones across Dublin. The main method for topic modelling in this research is with a Latent Dirichlet Allocation algorithm. The algorithm runs into obstacles on smaller sized documents to produce consistent, coherent and non-subjective topic labels. It is evident from the research that topic modelling on tweets may not produce consistent topic categories, to represent the Dublin population and interest zoning adequately. The research provides a well-designed framework from which future work in interest zoning using topic modelling can be done. The paper proposes additional measures to improve on location-based offline
advertising using online content.

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 > HF Commerce > Marketing > Advertising
Z Bibliography. Library Science. Information Resources > ZA Information resources > ZA4150 Computer Network Resources > The Internet > World Wide Web > Websites > Online social networks
T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > The Internet > World Wide Web > Websites > Online social networks
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Caoimhe Ni Mhaicin
Date Deposited: 05 Nov 2018 11:46
Last Modified: 05 Nov 2018 11:46

Actions (login required)

View Item View Item