Host institution: Aalborg University (AAU), Copenhagen 🇩🇰
Supervisors: Prof. Jannick Sørensen (AAU) and Prof. Tim Raats (VUB)
Academic secondment: Vrije Universiteit Brussel (VUB) 🇧🇪
Industrial secondment: European Broadcasting Union (EBU), Geneva 🇨ðŸ‡
PhD duration: 3 years
This PhD project is titled: Quality news both for Public Service Media and is part of WP4 Algorithms and value-based curation.
AI-powered chatbots have become a standard feature for all types of services but, when used in quality-oriented Public Interest Media, the correctness of the answers given by the chatbot is pivotal. The reputation of Public Interest Media is based on unbiased, quality-checked trustworthiness. The European Broadcasting Union (EBU) in Geneva has developed, for its Public Service Media members, a state-of-the-Art RAG-based conversational chatbot: NEO, which is based on four million news articles, growing daily by 3000. NEO can be used both by journalists and end-users.
NEO is a very relevant case for this PhD position not only as the quality of its replies must adhere to the highest journalistic standard, but also because it must integrate in the editorial profile of the news organisations where it is implemented. The current version of NEO only searches articles published by public media journalists but if a ‘deep search’ mode should be implemented – to provide better answers on more complex questions – external trusted sources must be carefully integrated and answers must be automatically quality-controlled, e.g., via a novel ‘agentic workflow’ to be developed in the PhD project where elements of information in the chatbot answer are examined by a network of independent software agents. How to prevent NEO from using AI-generated content? In short: How to ensure the highest journalistic quality in the output from NEO?
Another possible topic for the PhD candidate is designing NEO for different user needs. Journalists have different needs, so have end-users. Furthermore, the use context for NEO as a plug-in for social media is radically different from NEO implemented within a news website: How to speak to the user, which pictures to show? Should the style of NEO’s answers only satisfy user needs (e.g.: Entertain me!) or should NEO also try to nudge peoples’ fields of interest?
A third possible topic is performance improvement of using a graph-based analysis and/or infrastructure. Typical RAG systems use a semantic search based on embeddings. NEO uses a hybrid approach with both embeddings-based and keyword-based retrieval. While the hybrid approach has clearly shown its supremacy, retrieval could still be better. A graph-based storage of the article content (or a sample of it) could better model the complex links between people, facts, organisations, and concepts, to name a few, described in the articles. On simple questions like ‘what are the latest (major) news today?’ or ‘give me a timeline of the COVID pandemic’, NEO might struggle. A graph-based approach might help to identify the broad concepts first, and then move on to the details.
There are obviously more problems in developing a quality-focused public service chatbot. The applicant is thus not limited to choose from the topics above, but can develop a fourth topic, in collaboration with the supervisors.
The position requires relocation to Denmark as the candidate will be enrolled in the PhD programme of Aalborg University. The project is conducted under the supervision of Jannick Sørensen, Associate Professor at Aalborg University, and Tim Raats, Associate Professor at Vrije Universiteit Brussel. It will involve close collaboration with other Doctoral Candidates in the RePIM doctoral Network Project, and an academic secondment of approximately 2 months at Vrije Universiteit Brussel in Belgium. The candidate will also carry out 3-month internship at the European Broadcasting Union (EBU) in Geneva.
The PhD position is part of RePIM – Revisioning Public Interest Media, a four-year Marie Skłodowska-Curie (MSCA) Doctoral Network dedicated to reimagining the role and future of Public Interest Media in a data-driven, platform-dominated environment. RePIM brings together leading European universities, industry partners, and 12 Doctoral Candidates in an interdisciplinary, cross-sectoral training and research programme. The network investigates how Public Interest Media can remain relevant, sustainable, and impactful by transforming how content is produced, packaged, distributed, and supported organisationally and technologically. Through its focus on strategic innovation, organisational change, and media management, RePIM equips its doctoral researchers with advanced analytical and managerial skills to help reshape Public Interest Media across diverse European contexts.
Project-specific profile requirements
- A Master’s degree in either computer engineering or computer science/data science. A master’s degree of 120 ECTS points is an official requirement for enrolment as PhD at Aalborg University.
- Practical work experience with AI, Large Language Models, RAG, data science, embeddings and software agents is welcomed. The EBU-NEO tech-stack consists of: Python, LangChain, LangGraph, MongoDB, Milvus, Elastic Search.
- Knowledge from the fields of media science, user experience design, journalism or communication studies is welcome.
- Willingness to engage in international mobility in line with the MSCA-DN framework (meetings, training sessions, research stays and industry stays, etc.).
Requirements for competence in English
Applicants who are planning to complete a doctoral thesis in English and who do not have English as a first language or who have not completed an English language-based Master’s programme (or an equivalent educational achievement in English) shall provide documentation that they have passed one of the following official tests with the respective minimum score: IELTS (band score): 7, TOEFL (paper-based): 600, TOEFL (internet-based): 100. The language test must be no more than five years old at the time of the application.
English skills may also be documented in the following manner:
1) An English taught qualifying upper secondary school diploma, Bachelor’s degree or Master’s degree from USA, Canada, Australia, New Zealand, UK or Ireland.
2) A Nordic or German upper secondary school diploma, International Baccalaureate (from the IB diploma programme) or European Baccalaureate (from Schola Europaea) with an English level equivalent to a Danish B level in English with a minimum GPA of 3.0 (Danish grade scale).
3) A Danish Upper secondary school diploma – ‘English level B’ or 4) a Danish Upper secondary school diploma – ‘English level A’.