NB: This topic is intentially open and less defined than others to encourage students who have their own ideas to use it as a starting point.

As a result of hardware miniaturization and ubiquitous internet access, there is a wealth of user- and sensor-generated geographic content available, from social media activity to private weather stations to embedded sensor technology for managing public transport or optimizing energy consumption. In an urban context, these developments have become an essential part of the Smart Cities concept.

However, citizens and governments are still far away from fully exploiting the potentials of these new data sources for improved decision-making, participation, and service provision. A focus on technology leads to a focus on resource efficiency, with the objective to increase the quality of life for citizens becoming secondary [1]. While a lot of research takes the perspective of commercial or administrative actors, this project aims to support citizens of Smart Cities to become Smart Citizens, exploiting the potential of new technologies and platforms for engaging them in participatory planning processes [2], challenging authoritative knowledge production [3], and improving their spatial decision-making.

A key challenge is to keep citizens "in the loop" of scientific research (which is increasingly used to support evidence-based policy making) and daily data processing in Smart Cities. The specific local knowledge of citizens has the potential to provide location-based services that are relevant and useful for them. This topic aims to investigate how to let citizens participate in the processing and analysis of urban data, e.g. to make automated approaches at filtering and analysing geo-social media and other information smarter. While data mining and machine learning techniques provide a great opportunity to master the modern information deluge, without human training and supervision, they run the risk of discovering spurious patterns or correlations, become biased, or perform worse with new or changing data [4]. The output of this research should be a proof-of-concept that allows citizens to contribute their local knowledge to geospatial analysis and citizen science through a flexible, usable interface.

The topic is best investigated with a concrete problem in mind, e.g. littering, air pollution, noise, traffic jams, perceived or actual crime, etc. If required, there are several georeferenced social media data sets from Enschede and London available.

A successful thesis will have contributed to enabling Citizen Science and Smart Citizens for Smart Cities: “If we increasingly want to use data as a mirror of society, then people need to be able to see themselves in its reflection” [5]. Any case study can be loosely based on recent work by potential supervisors [4, 6], while transferring the approach to a smart city context [7].

Useful skills include the willingness to look beyond GIScience disciplinary boundaries (e.g. concepts from social network analysis), the ability to use scripting languages (e.g. Python) to collect data from APIs (e.g. Flickr), pre-process the data (e.g. NLTK, GDAL), and analyze the geographic distribution (e.g. R or sci-kit learn). For a student with proven advanced technical skills and interests, there are limited funds available to use cutting-edge NLP such as BERT [8] on an AWS cluster.

[1] http://www.cityofsound.com/blog/2013/02/on-the-smart-city-a-call-for-sma...
[2] P. Mooney, P. Corcoran, and B. Ciepluch, “The potential for using volunteered geo-graphic information in pervasive health computing applications,” J. Ambient Intell. Humaniz. Comput., vol. 4, no. 6, pp. 731–745, Dec. 2013
[3] M. Dodge and R. Kitchin, “Crowdsourced cartography: mapping experience and knowledge,” Environ. Plan. A, vol. 45, no. 1, pp. 19–36, 2013.
[4] Ostermann, F.O., Garcia-Chapeton, G.A., Kraak, M.-J., Zurita-Milla, R., 2017. Mining user-generated geographic content: An interactive, crowdsourced approach to validation and supervision, in: Bregt, A., Sarjakoski, T., van Lammeren, R., Rip, F. (Eds.), Societal Geo-Innovation : Short Papers, Posters and Poster Abstracts of the 20th AGILE Conference on Geographic Information Science. Presented at the 20th AGILE Conference on Geographic Information Science., Wageningen University & Research, Wageningen, The Netherlands.
[5] L. Dodds, “People like you are in this dataset,” Lost Boy, 15-Sep-2016.
[6] F. O. Ostermann, H. Huang, G. Andrienko, N. Andrienko, C. Capineri, and K. Farkas, “Extracting and comparing places using geo - social media,” in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, La Grande Motte, France, 2015, pp. 311–316.
[7] J. Morales and M. Garcia, “GeoSmart cities: Event-driven geoprocessing as enabler of smart cities,” 2015, pp. 1–6
[8] https://arxiv.org/pdf/1810.04805.pdf