This project will employ natural language processing methods to extract information from social media postings in the context of disasters and emergency situations. When natural disasters such as earthquakes, hurricanes and fires happen, there is a need for very localized information about the impacts of the events to enable first responders to act quickly. Among the various means of communication to raise awareness in emergency response, social media have come to play a significant role in sending text, photos and videos that can record information about the nature of an event, including for example the location, people injured, or damage to buildings, roads or bridges. There is a challenge therefore to find automated methods to detect such information within these messages.
The potential of social media to assist in emergency response has been widely acknowledged and there is a considerable body of literature on the subject. Much of the work to date has been concerned with determining relevance and informativeness, and classifying and clustering the posts according to the nature of the event or information communicated, and the sentiments expressed in them. There has also been a considerable body of work on determining the locations referred to (georeferencing). This is motivated by the fact that only a small proportion of media such as Twitter have GPS coordinates of the sending device, and furthermore that location could be different from the described event. Only very limited progress has however been made on extracting fine grained information that might link a specific impact with a particular location. In natural language processing this is a problem of relation extraction, where in this case the relation is between an impact that could be described by a phase such as ‘collapsed building’, ‘people injured’, or ‘power lines down’, and a location that could also be an expression such as ‘west side of Leicester Square’, or ‘the intersection of Wade Road and Juniper Crescent’.
The project will apply and develop deep learning methods, such as for named entity recognition, dependency parsing and relation extraction, to identify impacts and locations and the relations between them within messages that have been previously classified as potentially relevant. We will collaborate with the QuakeCore centre of excellence in New Zealand (http://www.quakecore.nz), that specialises in earthquake resilience, and with related projects on georeferencing natural language descriptions of location.
Keywords: social media, natural language processing, emergency response, machine learning
Contact for information on the project: [Email Address Removed]
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.
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
Please submit your application before the application deadline 29th April 2022 via Computer Science and Informatics - Study - Cardiff University
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
- In the funding field of your application, insert “I am applying for 2022 PhD Scholarship in Computer Science and Informatics”, and specify the project title and supervisors of this project in the text box provided.
- Qualification certificates and Transcripts
- References x 2
- Proof of English language (if applicable)
Interview - If the application meets the entrance requirements, you will be invited to an interview
If you have any questions or need more information, please contact [Email Address Removed]
Continue with Facebook
