As a result of hardware miniaturization and ubiquitous internet access, there is a wealth of user- and sensor-generated geographic content already available, from social media activity to private weather stations. Due to this, citizen science projects have many channels to communicate with and collect data from participants. However, handling the data is already a critical issue for many citizen science projects, which struggle to utilize fully the potentials of these new data. A key challenge is the assessment of the data quality and its fitness-for-purpose. Existing crowdsourcing approaches to curate the incoming content face problems of sustainability, scalability, and reproducibility of results. Previous research has shown that taking the geographic context of the content into account, and using data mining and machine learning techniques to structure and classify the content can support the quality assessment decisively. However, this approach requires human supervision to prevent statistically significant but meaningless results, and to train classifiers and regression models for new contexts and use cases. This work presents an approach to combine human and machine processing of geographic content, with the objective to use the local knowledge of citizens and the computational power of modern algorithms to address the respective weaknesses of each. A prototype and small case study on urban imaginaries will demonstrate how citizens could contribute beyond data collection, and formulate research questions, supervise machine learning and data mining, and validate results. These would be first steps towards citizen data scientists. Dr. Frank O. Ostermann<http://www.linkedin.com/in/foost> | Assistant Professor<http://www.itc.nl/resumes/ostermann> University of Twente<http://www.utwente.nl/> | Faculty ITC<http://www.itc.nl/> | Department Geo-Information Processing (GIP)<https://www.itc.nl/GIP> ITC Building, room 2-056 | T: +31 (0)53 - 487 4492 | f.o.ostermann@utwente.nl<mailto:f.o.ostermann@utwente.nl> Study Geoinformatics: www.itc.nl/geoinformatics<http://www.itc.nl/geoinformatics>