Gray-box approach to narrative analysis

While Natural LanguageProcessing (NLP) is already a well-developed field, the problem of using NLP methods for narrative analysis has not yet been satisfactorily solved. In the spirit of the HumanE-AI project, in the current microproject we lay the groundwork for developing a new approach to narrative analysis providing a gray-box (at least partially explainable) NLP model tailored for facilitating work of qualitative text/narrative analysts. We conduct a proof-of-concept study combining existing standard NLP methods (e.g. topic modeling, entity recognition) with qualitative analysis of narratives about smart cities and related technologies and use this experience to conceptualize our approach to narrative analysis, in particular with respect to problems which are not easily solved with the existing tools. Crucially, the current initial research will be followed-up by a next microproject dedicated to formalizing our approach to narrative analysis and developing its open-source implementation (for Python).

Output

Submitted paper on narrative analysis of articles on smart cities and related technologies

Project Partners:

• Institut national de recherche en sciences et technologies du numérique (INRIA), James Crowley

Primary Contact: Andrzej Nowak, University of Warsaw