PhD Studentship Available Predicting News and News Impact: From Social Media to News and back again

Contact details: Dr Katja Markert

44 (0)113 343 5777

One PhD studentship is available in the area Natural Language Processing and Social Media. The studentship is co-funded by an EPSRC Doctoral Training Grant at the School of Computing at the University of Leeds ( and the company 365 Media (

The main purpose of the project is to explore the links between social media and more traditional news outlets, using Natural Language Processing as well as general data aggregation/data mining methods.

Social media (such as Twitter, Facebook etc.) is by now often faster in spreading events and information than traditional news outlets.  On the other hand, social media react to news, and particular news will cause (sometimes quite unexpected) substantial ripples on social media sites.

In particular, the project aims at one or both of the following:

  1. Predicting today’s news from yesterday’s tweets (or equivalents).
  2. Predicting today’s tweets from yesterday’s news, therefore predicting news impact.

Although concerned with the general case of how to capture and model the interplay between these media, the studentship will concentrate on one or two case studies, which will provide a direct application link in interplay with interests at 365 Media.

These might encompass the business sector (e.g. mergers and acquisition), political events (e.g. elections, protests, coups), entertainment (e.g. film reviews, celebrity scandals), or other things of high public interest (e.g epidemics, severe weather).

The studentship is funded for 3.5 years and covers Home/EU fees and maintenance at the standard EPSRC rate (currently £13,736 per annum). Please note, due to funding restrictions this studentship is open only to UK/EU students who have been resident in the UK for a minimum of three years prior to starting their PhD studies.

The PhD candidate should have or expect to obtain a first class or good 2.1 honours degree or an Msc with at least Merit in computer science or a related field. Experience in data mining and/or natural language processing recommended.

The studentship will start from 1 October 2013 or as soon as possible thereafter. The successful candidate must fulfil the eligibility criteria for EPSRC funding through UK/EU nationality and residency status (See and is therefore only open to UK and EU students. EU students who do not fulfil the EPSRC UK residency requirements are only eligible for a fees-only award.

The School of Computing is among the 10 best Computing departments in the UK according to the 2008 Research Assessment Exercise (RAE).  An impressive 80% of staff is rated internationally excellent or world leading. This clearly confirms the School’s position as one of the leading computing departments in the UK and a leader in the field internationally.

365 Media is a US company whose UK subsidiary is the project partner. 365 Media provides data mining, cleansing and enriching services to all kinds of content consumers. Their UK R&D operation is focused on the intelligent automation of these services, particularly where natural language is concerned.

In addition to mentoring and opportunities for direct collaboration, 365 Media will be able to provide substantial support to the student in the form of specialized software tools, high quality datasets, and data processing (e.g. harvesting and annotation) services relevant to the research area.

Formal applications for research degree study should be on line through the University website. Detailed information of how to apply online can be found via the ‘Apply’ button below.

For informal enquiries and discussion prior or concurrent to application please contact Dr. Katja Markert, NLP group leader, Victoria Masters, Graduate School Office, Faculty of Engineering, University of Leeds, Leeds, LS2 9JT. tel +44 (0) 113 34 38000

Follow us on Facebook:

Also Read  PhD Studentship Available CFD in Energy

Leave a Reply

Your email address will not be published. Required fields are marked *