Using Text Analytics for Monitoring and Evaluation

This PhD research will develop methods for modelling textual data, social media data, etc., and to use this date to predict traditional Monitoring and Evaluation data that is generated through a research hub.

Eligibility
Candidates are required to have:
• An excellent undergraduate degree with Honours in an analytical subject, e.g. mathematics, statistics, management science, computing science, etc.,
• A Masters degree (or equivalent) will be strongly preferred
• Students may also have other relevant experience or skills which are relevant to this project
• Candidates who are not native English speakers will be required to provide evidence for their English skills (such as by IELTS or similar tests that are approved by UKVI, or a degree completed in an English speaking country).

Project Details
This is an exciting opportunity to join the One Ocean Hub, a new, £20M global hub for interdisciplinary research funded through the UKRI Global Challenges Research Fund. The Hub seeks to address intractable challenges faced by developing countries in relation to ocean management. Through this 5-year initiative, researchers from the UK will work with colleagues across the world to address the challenges of South Africa, Namibia, Ghana, Fiji and Solomon Islands in realising the economic, socio-cultural and environmental benefits from the ocean. The Hub will weave learning from the ocean, ranging from the traditional knowledge of the peoples who rely upon it to marine sciences, innovative legal approaches and artistic methods. Our aim is to bridge the disconnections in law, science and society across all levels from the local to the international. This PhD position will directly feed into supporting some of the challenges facing the Hub.

There has been a recent increase in the volume of documents generated during projects and large-scale programmes that may contain useful information, but is at risk of being lost due to sufficient time for review. During the life of Ocean Hub, it is expected that substantial textual data will be generated by the different partners and stakeholders. This data could be internal reports and external reports produced by the partners, social media data produced by the partners and others, and other data, e.g. media reports. Recent research has illustrated the challenge in not only developing appropriate text mining algorithms,. but in the interplay between the outputs of these algorithms and the mental models used by decision makers. The aim of this PhD will be to develop models and algorithms to analyse textual data that is generated during the life of the Hub that it is hoped will capture nuances that we may be unable to measure and act as leading indicators to predict the lagging indicators that are part of traditional Monitoring and Evaluation.

Much of the research on text mining assumes, at least partially, that the user has an implicit or explicit understanding of the items they are searching for and a clear evaluation criteria for knowing when they have found what they are looking for. This research will seek to take a broader approach of exploratory text mining, underpinned by a collaborative approach with end-users who can contextualise the emerging patterns and give meaning to the analysis.

The objectives of this PhD
• To review the text mining literature to identify appropriate
• To develop methods for modelling textual data, social media data, etc.
• To develop methods for linking textual data with the traditional M&E data generated in the hub.
• To model the data temporally to begin to make predictions on future text documents and lagging indicators.

Supervisor
Dr Matthew Revie - https://www.strath.ac.uk/staff/reviematthewdr/
Professor John Quigley - https://www.strath.ac.uk/staff/quigleyjohnprof/

Contact Us
For more information, please contact Matthew Revie on [Email Address Removed]