This project will use data mining and machine learning methods to categorise and then map geographic locations according to their distinguishing characteristics. At present when looking at the map of a city it can be difficult to get a feel of the local character of different neighbourhoods. Most online maps are confined to indicating the presence of general types of features such as buildings, streets and parks, sometimes accompanied by the brands of shops or cafes, and perhaps a few prominent landmarks. When looking at these maps, we often have little idea of, for example, the main types of retail or industrial activity; whether it is a modern or historic place; cultural associations such as who lived there; whether it can be a calm, convivial or an overcrowded place; is it safe, good for music, or cinema or art; what are the crime levels; what is the air quality; is it ethnically diverse or ethnically distinctive; is there much green space?
There have been some previous studies that have used topic modelling to identify some place characteristics as reflected in social media, but these studies are very limited compared to the multiple facets of place that might be of interest to people, according to their personal intentions or preferences. This project will exploit a much wider range of relevant data sources than has previously been used in studies of sense of place, and will include national and local government surveys on socio-economic characteristics of resident population, employment levels, house age, the natural environment, air quality, and crime levels; cultural and historic aspects (e.g. from Wikipedia/DBpedia); topographic data such as OpenStreetMap and Ordnance Survey; and social media perceptions from Twitter, Google Places, TripAdvisor and Flickr.
In order to characterise locations, we will use a mix of unsupervised machine learning methods that identify distinguishing characteristics of places given the multiple data sources, along with human subject studies in which people introduce their own categories. Supervised deep learning methods will be used to create classifiers that exploit the multiple data sources to attached appropriate labels or categories. A range of cartographic techniques based on the use of colours, patterns, text and icons will be used to create maps that distinguish between the different aspects of place.
Keywords: sense of place, cartography, data mining, machine learning, online mapping
Please address enquiries to Prof. Chris Jones: jonescb2@cardiff.ac.uk
Entry requirements
Academic criteria:
A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject. Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas.
Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component.
This application is open to students worldwide.
How to apply:
Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below
This project is accepting applications all year round, for self-funded candidates via https://www.cardiff.ac.uk/study/postgraduate/research/programmes/programme/computer-science-and-informatics
In order to be considered candidates must submit the following information:
- Supporting statement
- CV
- In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD
- Qualification certificates and Transcripts
- Proof of Funding. For example, a letter of intent from your sponsor or confirmation of self-funded status (In the funding field of your application, insert Self-Funded)
- References x 2
- Proof of English language (if applicable)
If you have any questions or need more information, please contact COMSC-PGR@cardiff.ac.uk
Continue with Facebook