Gupta, Neha (2018) Exploring happiness indicators in cities and industrial sectors using Twitter and Urban GIS data. PhD thesis, University of Warwick.

Preview

PDF WRAP_Theses_Gupta_2018.pdf - Submitted Version - Requires a PDF viewer. Download (11Mb) | Preview

Request Changes to record.

Abstract

The changing demographics and landscape of cities emphasises to better understand the factors which influence citizen happiness. Inferring happiness (sentiment analysis) indicators from Twitter text and Urban GIS data offers a scalable solution. The current research is an exploratory study conducted to apply Natural Language Processing (NLP) and GIS techniques to geo-tagged Tweets in the Greater London area in order to investigate the underlying socioeconomic and urban geography features that potentially could influence happiness. Specifically, the present research devise a methodology to explore the aggregated sentiment of people engaged in various industrial sectors by joining diverse datasets (Twitter, INSPIRE polygons, Ordanance Survey AddressBase and UK Land Registry) which so far has existed in silos in order to monitor the working patterns and sentiment trends in industrial areas in urban space. Furthermore, the proposed methodology seek insights about the Brexit related Twitter sentiment trends in targetted industrial sectors. The results of this study could enable urban planners to move beyond planning services using traditional cost benefit analyses by incorporating openly available data sources. The novel data-driven approach developed in this work has an application in analysing the mood prevalent in various economic sectors and provides an evidence to incorporate social media analytics in organisational studies, thereby offering a mechanism to monitor working patterns in near real-time using tweet intensities. The procedure outlined can be used to extend more traditional survey and sample based methods in behavioural studies and also could be an enabler for policy makers to perceive the sentiment of a targeted sector of society in light of an existing social phenomenon.

Item Type:	Thesis or Dissertation (PhD)
Subjects:	Q Science > QA Mathematics > QA76 Electronic computers. Computer science. Computer software
Library of Congress Subject Headings (LCSH):	Happiness, Geographic information systems, Natural language processing (Computer science), Online social networks
Official Date:	September 2018
Dates:	Date Event September 2018 UNSPECIFIED
Institution:	University of Warwick
Theses Department:	Department of Computer Science
Thesis Type:	PhD
Publication Status:	Unpublished
Supervisor(s)/Advisor:	Jarvis, Stephen A., 1970-
Sponsors:	University of Warwick. Centre for Competitive Advantage in the Global Economy ; Engineering and Physical Sciences Research Council
Format of File:	pdf
Extent:	xiv, 108 leaves : illustrations, charts
Language:	eng

Request changes or add full text files to a record

Repository staff actions (login required)

View Item

Downloads