This is a PhD position available at MAPIX technologies, UK & Utrecht University, The Netherlands, through the EU European Training Network SAF21. The candidate should have an MSc in Computational Linguistics, Data Science, Artificial Intelligence, Information Science, or Computer Science.

Research domain: To uncover the potential wealth within unstructured and semi-structured textual data relevant to the multi-stakeholder fisheries market, this PhD research topic investigates the effectiveness and efficiency of a range of text analytics techniques—from NLP-based to ML-based and combinations thereof—to help improve our understanding of the stakeholder opinions and perceptions for better social marketing and management strategies within the fisheries domain. This research is positioned within a design science research context from a meta-algorithmic modelling perspective. Following knowledge discovery processes such as CRISP-DM, the PhD candidate will employ and unify feature engineering, algorithm selection and parameter optimization techniques, among others, to uncover relevant social aspects and stakeholder perceptions as well as their relationships from publicly available textual data sources (such as the Web) within the fisheries application domain. In particular, the PhD candidate will investigate the optimal balance between applying ensembles of symbolic NLP approaches on the one hand and probabilistic text analytics techniques on the other hand. The main research artifact in this PhD research is envisioned as a unified meta-algorithmic model that provides custom “recipes” to match domain-specific analytical information needs— regarding e.g. social marketing—with proven text analytics techniques (both symbolic and probabilistic) and software tooling configurations. The research will be evaluated in an action research setting resulting in a Text Analytics for 21st century Fisheries web based application to be developed by the candidate.