Undergraduate Summer Projects in Data Mining and Analytics

The Data 2 Knowledge (D2K) research group has two undergraduate summer research placements in data mining and analytics within the Publications Metadata Augmentation (PMA) project.

The Project

The PMA project aims to create a generalised datamining tool to extract publication metadata related to individual UK cohort studies. It will create a dataset of enhanced publications metadata that can then be analysed for a range of purposes including social studies of health sciences and measuring the impact of cohort studies.

Successful students will conduct a range of duties to assist on the PMA project, tailoring to candidate strengths and research interests. This is likely to include:

• data discovery, data entry and data cleaning

• developing analytics and visualisations (including real-time) e.g. network analysis, temporal trends, mapping

• web interface for data discovery e.g. to search the publications metadata and view the analytics.

Person specification:

• Experience writing in a range of languages e.g. python, javascript

• Knowledge of data structures used in bibliographic settings e.g. json, bibtex

• Linux experience would be an advantage

Placements will be situated in School of Social and Community Medicine at Oakfield House for 6-10 weeks between June and September 2016. Flexibility can be taken into account with term start/end dates. Students will be paid on a monthly basis at a rate of £275 a week, working standard research hours.