Developing a privacy-aware map-based cross-platform social media dashboard for municipal decision-making # Developing a privacy-aware map-based cross-platform social media dashboard for municipal decision-making ## Introduction Users of location-based social media networks (LBSN), such as Instagram, Flickr, or Twitter, have produced an unprecedented base of data over the past decade. According to ILIEVA & MCPHEARSON (2018: 553), "the enormous scale and timely observation are unique advantages of [social media data]" and therefore hold enormous potential for various application purposes such as urban planning, among others. Most notably for Instagram, as one of the largest LBSN, encouraging the sharing of locations when creating content, offers completely new and promising application purposes, through the combination of the spatial component with timestamps and the actual content (image & text). Public social media (SM) data have shown their potential examining the increasingly relevant social problems of Spatial (In-) Justice, spatial (in-) equality and spatial (in-) equity (Cf. SOJA 2013: 47). However, few research attempts were made to make these results available broader in practice and accessible to laypersons in an understandable way. LBSN data could contribute significantly to creating a better information base for municipal decision-making processes, reaching especially younger target groups. Until now, specifically these groups were difficult to reach in common participation processes (Cf. SELLE 2004), while bearing consequences of municipal policies for the longest period of time. Our stated research goal is therefore to provide citizens, laypersons and municipal decision-makers with an unprecedented LBSN Dashboard, as a simple open-source platform for spatial multi-purpose LBSN analysis. ## Problem Statement Such an undertaking raises certain ethical and legal questions, since the user data belong to the users themselves, including the right to self-determination over their data, on the one hand, and the right to privacy on the other. The far too short-sighted (but frequently used) argument that posts have been deliberately published, with all the consequences of their public nature in mind (e.g., BURTON et al. 2012: 2), is simply not sufficient for an in-depth discussion of privacy. This further violates the most important aspects of privacy (Cf. BOYD & CRAWFORD 2012: 672). In fact, most users are not or only partially aware of what can actually be inferred from what they share or disclose about themselves (KESSLER & MCKENZIE 2018: 6f). Yet, privacy is rarely addressed in LBSN research and, worse, often negligently ignored. In this context, many negative examples can be found where data was analyzed and high-resolution results were published, clearly violating users' privacy, for example, in scientific publications (Cf. KOUNADI & LEITNER 2014: 140). ## Research Interest Given the increasing socio-spatial inequality, the rapid growth of SM, and the growing interest of municipalities in SM knowledge, we see a significant need for such a privacy-aware LBSN dashboard, which is entirely new to the geospatial community. We develop a privacy-aware LBSN dashboard prototype and propose a data processing pipeline based on the HyperLogLog (HLL) algorithm by FLAJOLET et al. (2007). The dashboard is geared towards easy information retrieval and making use of the data richness of LBSN -- without compromising user privacy and the need for extensive data retention. Instead, we provide a unique, customizable, GDPR-compliant privacy approach. The combination of different open-source tools for structuring multi-platform LBSN data, leveraging the capabilities of HyperLogLog and simple Python integration ensure easy reproducibility and active community development (Cf. DUNKEL et al. 2021; DUNKEL & LÖCHNER 2021a & b). The dashboard prototype is tailored for use in municipalities and its citizens, but offers high scalability for other purposes or other spatial levels. A limited interactive demo and its GitHub repository are permanently publicly available as a result of a Master's thesis and an IoT Design Thinking Workshop (Cf. WECKMÜLLER 2021; BUNDESSTADT BONN 2022). We plan on finishing and automatizing the data processing pipeline, enabling more sophisticated queries and adding further visualization methods. In the long run, the dashboard is thought to serve as a participation and open data hub for all citizens and for any city in the world. So far, the city of Bonn and Chemnitz (Germany) are pilot partners of this research project.