Making Sense of the Urban Future: Recommendation Systems in Smart Cities Dirk Ahlers NTNU – Norwegian University of Science and Technology Trondheim, Norway dirk.ahlers@ntnu.no ABSTRACT exciting systems on top of this new city infrastructures to generate A large variety of Recommender Systems today can help users to insights and provide new services and systems to people. understand and make sense of certain aspects of their cities, for Recommendation systems have already been implicitly or ex- example events, restaurants, government services, or transport. plicitly catering to users in cities, often through specific domains With the rise of the Smart Cities concept, more city operations and such as location-based recommenders [8, 13, 15] or citizen services services will be made available by integrating multiple information [11, 44]. Current and future work will continue this trend from both systems from all types of city systems. The development of Smart academic and industry perspectives. This is exemplified by work- Cities solutions will open up an exciting space for urban recom- shops such as RecSys workshops on Location-Aware Recommenda- mendations on a new and complex scale, which is the topic of this tions1 , Tourism Recommender Systems2 , the CitRec2017 workshop position paper. Most work today focuses on individual services, on urban recommender systems for citizens [44], as well as other such as recommendations for places, routes, or activities, but noth- work we discuss later, that continue to encourage researchers to ing yet makes use of the vast and complex available information identify challenges and opportunities in this area. and service space. Recommendations in smart cities can be a fruit- On the other hand, the concept of Smart Cities [6, 9, 35, 41] is ful area to explore in order to drive recommendations away from getting more traction in research, industry, and city development. single-item or single-domain systems and towards multi-source, For RecSys purposes, the Smart City concept can be understood multi-faceted, multi-stakeholder, multi-level, multi-dimensional, as a convergence of digital information and physical environment and integrated recommendations that explore and combine the along with social factors within a city. The ’smartness’ from the rich data and services that cities have to offer. Apart from giving ICT view is usually provided by information systems and concerns recommendations, suggestions, and decision support for daily life certain key areas: governance, people, living, mobility, economy, of citizens, such systems can also be a main building block towards environment. Thus, Smart Cities provide a new digital infrastruc- smart cities, making cities and their citizens more green, sustain- ture for cities. However, we take a broader view here to get to a able, climate-aware, and ultimately, more liveable. The ambition better understanding of the full potential. A Smart City should be we are sketching here shows integrated recommender systems in a city that not only provides smart data and services itself, but smart cities to be a highly complex and multidisciplinary challenge, should also be able to make smart use and allow its citizens to make with considerable input and output data and algorithmic complexity smart use of these and external data that is relevant and available within a complex domain. in open datasets, crowdsourced data, or social networks; to find new ways of operation, living, and creation. On the one side are CCS CONCEPTS city systems, such as energy, transportation, infrastructure, sustain- ability, housing, traffic, control systems, urban data analytics, and • Information systems → Recommender systems; • Human- additional sensors. On the other side are external services and data centered computing → Social recommendation. sources that can be used to make the city smarter. These include crowdsourced data, mapping, social networks, volunteered data, KEYWORDS external systems and services running within the city, news, and Smart City, Recommendation, Urban Environment, Urban Inter- also open data, both structured and unstructured. actions, Urban Computing, Information Access, Civic Tech, User The main innovations for a citizen are the availability of data, Interaction, Complex Systems easy access to data and services, and resulting, a higher number of options to use and participate in a city that turns into a con- nected smart urban environment. The research question we want 1 INTRODUCTION to explore in this context is, Cities are highly complex, dynamic, and interesting environments. ’What will change from a RecSys perspective once we Growing worldwide urbanisation puts cities under pressure to adapt have a Smart City surrounding us?’ to changing circumstances. There is not only a need for planning We see many challenges and opportunities that not only make and operation of cities and city systems, but also interest in the this an valuable and challenging application domain, but also a huge and growing amount of data that is produced continuously possible driver for further development of the recommender sys- 24/7 through cities and citizens for a variety of use cases, including tems field. These cover most important fields such as applications navigating these data sources and provide information access to citizens and stakeholders. Researchers should take the opportunity 1 https://recsys.acm.org/recsys15/localrec/ to use the growing infrastructure and data availability to build 2 https://recsys.acm.org/recsys19/rectour/ Copyright (c) 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). Dirk Ahlers domains, user scenarios and information needs, data integration, For our definition of a Smart City, we broaden the usual technical methods and algorithms, and the general applicability of recommen- definition of a computationally-augmented and sensor-enhanced dations in both reactive and proactive situations as well as decision to that of the sustainable participatory liveable smart city [2]. support and behaviour changes at multiple, complex levels. We On the infrastructure side, we acknowledge that a real-life smart especially see a necessary move away from single-domain single- city is build up of many separate systems that are not all centrally item recommendation towards more complex and cross-domain controlled by a municipality, as there are many separate services approaches. that can make a city smarter. As such, we see a smart city as an open To better support our case for integrated Smart Cities as a valu- ecosystem [3] that facilitates technical integration and collaborative able new research area for Recommendation Systems, we will first open innovation where necessary. In combination, this allows us to explore some related work to understand the current state of the also focus on inhabitants and participation/co-creation activities in art and then sketch a future path. addition to technology and infrastructure. The users can be citizens, defined as people living in the city, as well as travellers coming from elsewhere to visit the city physically or also use some city 2 RELATED WORK systems remotely, as well as a range of other stakeholders. Recommendation Systems are a way to filter through an abundance of data, add personalization, and create a valuable selection tailored to user preferences and context. With growing amounts of data and options in data-intensive Smart Cities, such tasks becomes 2.2 Related Recommenders increasingly important as a means to facilitate information access Longer discussed features for the evolution of recommendation to a vast range of options. Recommendation Systems assume a systems include extensions of older methods, mostly based on lim- choice of the user from a selection that usually is triggered by itations of content-based, collaborative, and hybrid approaches. context or activities. It is different from pure control systems or Suggestions [1] include an improvement of the understanding of on-demand search. These other fields will also need to adapt to users and items, the integration of context, multicriteria ratings, the new Smart City urban environments, but in this paper, we are more flexible and less intrusive recommendations, and broader especially interested in the ramifications for recommenders. evaluations based on usefulness or quality. Further discussions [16] Research related to recommendation systems in the overall and include the use of knowledge-based and group-based approaches integrated Smart City context is still in very early stages. It is note- and the exploration of additional applications domains, such as soft- worthy that we could not find any papers that deal with the Smart ware engineering, knowledge engineering, product configuration, City concept as a whole. The closest would be the workshop ap- and, especially important here, persuasive technologies and smart proach of citizen recommendation [44], though not necessarily the homes (both for design and for control to improve quality of life). individual contributions. Other available theoretical and practical The latter show a stronger relation to our topic, but still stay within papers usually address rather limited and focused aspects with- smaller niche tasks. out discussing the role of recommenders in the overall smart city Understanding recommender limitations from a human point context. of view can help to look at recommenders untied from current technology [36]. This view is close to our ambition here, to look into what would be an ideal system from a human life perspective, 2.1 A Definition of Smart Cities and what options for future work can be derived. A city as an organism comprises the buildings, roads, sub- ways, The area that currently has the strongest city relation is location- and other built environment, its natural environment in terms of aware recommendation systems [13] and recommendations in LB- topology, water, flora (and some fauna) together with machinery SNs [8], often with a focus on venues and places [15]. LBSNs with and finally, citizens and inhabitants. Seen on this level, a city is their locations and user interactions can also be used to get insights a highly complex organism with a multitude of dimensions that into a city’s internal life and processes [12]. can be understood from a variety of viewpoints [2, 6, 9, 24]. This is Aspects of venue and event recommendation can be used to show reflected in recent literature that is understanding cities not only the research opportunities that can arise with the use of the digital in terms of place and space, but also in terms of systems, structure, infrastructure of a Smart City [14]. To get around limitations with networks, flows, and processes [9]. Work from a more computa- only using location-based social networks (LBSN), that work ex- tional perspective [33] understands cities as sites of ubiquitous plores the use of social and physical sensors, for example analysing information and communication technology and data that people CCTV footage to detect interesting events. This is also described use to connect to people, places, and services. For example, cities as a way to bridge different silos of closed LBSNs. Similarly, sensor have previously been ideally designed to be legible [32], and to metadata can be used for city event detection [4] or Twitter can be give people the ability to form a mental model and mental map, used as a set of social sensors to understand and summarise city and that this is now changing towards cities being transparent or events [34] in preparation for recommender steps. understandable also from a data side [22]. This need is based on A promising approach is to use parts of the sensor infrastructure the observation that media interfaces are becoming the dominant of a smart city to improve quality of life, focusing on the features interfaces to the city. Additional work concerns sustainable [27], of personal health conditions coupled with real-time sensor-based liveable [35], or [5] hackable cities and ways to engage citizens [24] route information [10]. Citizen services as a general topic [44] and or communities [20]. e-government in particular [11] are further relevant domains. Making Sense of the Urban Future: Recommendation Systems in Smart Cities For the sensor integration of the Internet of Things (IoT), some user support. This will also mean to re-examine and re-assess the approaches deliver recommendation for analyses of data streams purpose of these systems towards user needs [26]. [42], while others already approach a smart home scenario [45] that To understand and utilise all services in and around the Smart recommends things based on relationship of users and RFID-tagged City and to integrate them, Recommenders have to work at differ- things, to for example support cooking or similar tasks. ent levels and scales. A possible goal would be to move the city Abstracting from individual locations, transportation and navi- experience into a Smart City Experience that combines exploration gation can be considered an area where integration of recommen- of the city, service discovery, proactive recommendations, and more dations is a bit further developed, either as multi-modality in the into a personal assistant to enable a personal sustainable liveable routing or in the data sources. Examples include trip recommen- city (cf. [7]). Some of the identified challenges are: dation [31] that includes places and events based on a rule- and Data integration: Recommendations spanning multiple data sources preference-based approach or transportation systems that recom- and systems, user scenarios, and user information needs. Integra- mend both taxis and passengers to each other [46]. Other systems tion into an open ecosystem of smart cities [3] to access for example recommend routes specially adapted to electric vehicles [17]. A municipal, local or national public and private, and worldwide sys- very different approach recommends beautiful or happy routes tems, ranging from social media over vertical collections, down to through a city based on maps and picture analysis of street-level individual municipal or local citizen services. photographs that derive additional dimensions for the city [38]. Improved context-awareness: approaches need to draw from more An interesting survey on smart communities [43] observes rec- complex user and city environment context and need increased ommendations used for mobile social learning, event guides, and adaptability [23]. context-aware services. Similar to smart cities, it further makes Scenario-based approaches: more complex, real-life oriented sce- the important definition of a smart community arising out of three narios, including ensemble-based, task-based, or exploration-based factors: physical world, online world, and social world. A similar recommendations, curated [29] from multiple streams. Complemen- work examines the applications for context-aware recommenders tary domains may be location, events, people, products, services, in smart urban environments [21] and describes scenario contexts routes, transportation, schedules, fitness, jobs, or news. of restaurants, public transportation, shopping, being at home, or Increased complexity: Complexity has to be handled inside the on a trip. system, on the UI side, and also will require better explanations for There are obvious differences in interest and needs for citizens on users into how the system works and why certain recommendations the one hand and city planners or operators on the other. Only a few are made [40]. Complexity occurs both on the input side with systems approach smart cities from a city planning or organization multiple connected systems and data sources, as well as on the perspective. Some frameworks exist that aim at recommendations output side with needs for results to span these systems and options for city planners, but often not with a computational approach and possibly combine them to satisfy user needs. [37]. Yet, some systems for city planners support smarter planning Cross-domain: recommendations may come from multiple do- and management, often in the form of decision-support systems mains of a smart city depending on user context, or set recommen- [28]. There are also some very specialised systems, such as recom- dations may be needed. mendations for the position of air quality measurement stations Integrated and new domains: Recommendations as a support tool [25]. to explore and experience and use the city, for both tourists and Finally, towards sustainable cities and citizen involvement, initial locals. work is exploring the use of recommendations as an offer to citizens Stakeholders: Systems need to address the right users, which to adapt their behaviour, for example in the choice of mobility with can range from citizens, visitors, tourists, commuters, students, personalised options that provide easier access [30]. homeowners, children, adults, elderly, municipality, service users, businesses, civic society, NGOs etc. User involvement: How do we find relevant civic engagement 3 SMART CITY RECOMMENDER opportunities? This can range from urban plans and consultations CHALLENGES up to NGO engagement or concern the development of these sys- There are some initial promising approaches in the related literature. tems themselves as civic tech or systems for the common good, for Smart City sensors are already initially included to broaden data example by involving citizens and communities in development sources [10, 14] and some work shows a positive vision towards and use cases, requirements, or systems. more complex city level scenarios [21, 43, 44]. However, there is a Individual vs. community targets: New challenges can occur for strong need to broaden the scope of recommenders and to focus public services, where recommendations should be both for the more strongly on wide integration of systems and more complex common good and the individual needs [39], which may be achieved scenarios. by more inclusion of participatory design and open data use. For the overall Smart City Recommendation System vision, we Algorithms: new scenario-based approaches may require other see a strong need to get away from single-item and single-domain recommendation algorithms, moving beyond item-based, collabo- recommendations. Development should be towards multi-criteria, rative, or knowledge-based paradigms. multi-domain, multi-community, multi-source, multi-faceted, multi- Evaluation: Not just accuracy, but also diversity, serendipity, level, and multi-dimensional recommendations. Further, set rec- robustness, trust, security, privacy, usefulness, quality, unobtrusive- ommendation would be important where not a single item, but ness. rather a set of items from multiple domains/systems is the suitable Dirk Ahlers Privacy and data ownership: Privacy issues in many forms can In the breadth that we have presented our vision here, it is an arise from the smart city concept [48], especially if it is seen imple- as-yet underspecified problem. The ambitions sketched out here mented as the data-driven, surveillance-prone variant. But also the will have to be conceptualised and refined in more detail. In this variation mostly described here would generate a lot of privacy- paper, we made a small contribution towards this goal. related data, that needs to be properly safeguarded. It is also not just about obvious CCTV blanket coverage; also the combination ACKNOWLEDGEMENTS of less invasive data sources can lead to privacy leaks. Such issues We thank our colleagues at the NTNU Smart Sustainable Cities are already necessary considerations in existing data collections group and others for helpful discussions around the topics presented and systems, and should be treated there initially. However, also here, for data ecosystems, data use, and inspiration for use cases. systems only built on top of those even without own data gathering, Special thanks go to Sole Pera, who inspired the integrative view have a responsibility and need to consider the use of such data, and of this paper and shared invaluable insights and discussions. for recommender systems to for example avoid data leakage [47]. Also data governance and ownership is an important issue, where REFERENCES larger systems make it harder to understand what is happening [1] Gediminas Adomavicius and Alexander Tuzhilin. 2005. Toward the Next Gener- to user-provided or sensed data further downstream, who owns ation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions. IEEE Trans. on Knowl. and Data Eng. 17, 6 (2005). it and can decide on sharing or integration, and whether/how it [2] Dirk Ahlers, Patrick Driscoll, Erica Löfström, John Krogstie, and Annemie Wyck- may be used. But with the integration across systems discussed mans. 2016. Understanding Smart Cities As Social Machines. In Workshop on the here, more critical privacy issues could arise and also need to be Theory and Practice of Social Machines (WWW ’16 Companion). IW3C2, 759–764. [3] Dirk Ahlers, Leendert W.M. Wienhofen, Sobah Abbas Petersen, and Mohsen considered in building these aggregating systems. Privacy should Anvaari. 2019. A Smart City Ecosystem Enabling Open Innovation. In 19th be a guiding factor in such future systems. Surveillance of citizens International Conference on Innovations for Community Services (I4CS2019) (Com- munications in Computer and Information Science, Vol. 1041). Springer, 109–122. and data abuses are not specifically to recommender systems. In https://doi.org/10.1007/978-3-030-22482-0_9 the context of Smart Cities, it is a particular crucial aspect, when [4] M-Dyaa Albakour, Craig Macdonald, and Iadh Ounis. 2015. Using Sensor Meta- data collection systems are deployed city-wide, also opening up data Streams to Identify Topics of Local Events in the City (SIGIR ’15). ACM. [5] Cristina Ampatzidou, Matthijs Bouw, Froukje van de Klundert, Michiel de Lange, issues of ownership and anonymous use of public spaces and ser- and Martijn de Waal. 2015. The Hackable City: A Research Manifesto and Design vices and rights to the city [18]. However, this issue is also one of Toolkit. Amsterdam Creative Industries Publishing. cultural background. Some countries place a much stronger focus [6] Francesco Paolo Appio, Marcos Lima, and Sotirios Paroutis. 2019. Understanding Smart Cities: Innovation ecosystems, technological advancements, and societal on commercialisation and surveillance in the smart city concept, challenges. Technological Forecasting and Social Change 142 (2019), 1 – 14. https: while others set a stronger counterpoint of municipal needs, ap- //doi.org/10.1016/j.techfore.2018.12.018 [7] Amos Azaria and Jason Hong. 2016. Recommender Systems with Personality. propriate governance approaches [19], and citizen focus [2]. It will In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys ’16). require work to strengthen or maintain these democratic aspects Association for Computing Machinery, New York, NY, USA, 207–210. https: throughout. //doi.org/10.1145/2959100.2959138 [8] Jie Bao, Yu Zheng, David Wilkie, and Mohamed F. Mokbel. 2015. Recommen- The initial discussion shows that a lot of work is already available, dations in Location-based Social Networks: A Survey. GeoInformatica 19, 3 but that merely combining it would not be enough. Strong new (2015). research approaches are necessary. [9] Michael Batty. 2013. The New Science of Cities. MIT Press. [10] Fran Casino, Edgar Batista, Constantinos Patsakis, and Agusti Solanas. 2015. Context-aware recommender for smart health. In IEEE First International Smart Cities Conference (ISC2). IEEE. 4 CONCLUSION [11] María E. Cortés-Cediel, Iván Cantador, and Olga Gil. 2017. Recommender Systems for E-Governance in Smart Cities: State of the Art and Research Opportunities. The metropolitan region is now the functional unit of In Proceedings of the International Workshop on Recommender Systems for Citizens our environment, and it is desirable that this functional @ RecSys2017 (CitRec ’17). ACM, New York, NY, USA. https://doi.org/10.1145/ 3127325.3128331 unit should be identified and structured by its inhabi- [12] Alberto Del Bimbo, Andrea Ferracani, Daniele Pezzatini, Federico D’Amato, and tants. The new means of communication which allow us Martina Sereni. 2014. LiveCities: Revealing the Pulse of Cities by Location-based to live and work in such a large interdependent region, Social Networks Venues and Users Analysis (WWW’14 Companion). [13] M del Carmen Rodríguez-Hernández, S Ilarri, R Trillo-Lado, and R Hermoso. could also allow us to make our images commensurate 2015. Location-aware recommendation systems: Where we are and where we with our experiences. [32] recommend to go. In LocalRec’15 @ RecSys2015. [14] Romain Deveaud, M-Dyaa Albakour, Craig Macdonald, and Iadh Ounis. 2014. Challenges in recommending venues within smart cities. In Information Access The Smart City scenario is a challenging next frontier to explore. in Smart Cities Workshop (i-ASC 2014) @ ECIR2014. Improving cities and sustainability will be one of the major issues [15] Romain Deveaud, M-Dyaa Albakour, Jarana Manotumruksa, Craig Macdonald, and Iadh Ounis. 2014. SmartVenues: Recommending Popular and Personalised facing us in coming years. Cities can be made more liveable, sus- Venues in a City (CIKM ’14). ACM. tainable, and understandable through a range of measures. Their [16] Alexander Felfernig, Michael Jeran, Gerald Ninaus, Florian Reinfrank, and Stefan growing complexity coupled with growing data, information ac- Reiterer. 2013. Multimedia Services in Intelligent Environments: Advances in Recommender Systems. In Toward the Next Generation of Recommender Systems: cess, and urban options opens huge pathways for development of Applications and Research Challenges, A. George Tsihrintzis, Maria Virvou, and innovation, citizen involvement, and data-intensive smart systems. C. Lakhmi Jain (Eds.). Springer. [17] João C. Ferreira, Vítor Duarte Fernandes Monteiro, and João L. Afonso. 2012. Recommendation Systems can and must help to shape this urban Electric vehicle route recommender system. In 1st International Conference on future towards important real-life recommendations. The multi- Smart Grids and Green IT Systems. tude of open challenges coupled with interesting opportunities [18] Marcus Foth, Martin Brynskov, and Timo Ojala (Eds.). 2015. Citizen’s Right to the Digital City. Springer. https://doi.org/10.1007/978-981-287-919-6 makes this a very valuable and rewarding area for research to drive [19] Savis Gohari, Dirk Ahlers, Brita F. Nielsen, and Eivind Junker. 2020. The recommendation systems towards their urban future. Governance Approach of Smart City Initiatives. Evidence from Trondheim, Making Sense of the Urban Future: Recommendation Systems in Smart Cities Bergen, and Bodø. Infrastructures 5, 4 (2020), 31. https://doi.org/10.3390/ [47] Feng Zhang, Victor E. Lee, Ruoming Jin, Saurabh Garg, Kim-Kwang Raymond infrastructures5040031 Choo, Michele Maasberg, Lijun Dong, and Chi Cheng. 2019. Privacy-aware smart [20] Stephen Goldsmith and Susan Crawford. 2014. The Responsive City: Engaging city: A case study in collaborative filtering recommender systems. J. Parallel and Communities Through Data-Smart Governance. John Wiley & Sons. Distrib. Comput. 127 (2019), 145 – 159. https://doi.org/10.1016/j.jpdc.2017.12.015 [21] Charles Gouin-Vallerand and J. Alberto-Montero De La Cruz. 2013. Analysis of [48] Kuan Zhang, Jianbing Ni, Kan Yang, Xiaohui Liang, Ju Ren, and Xuemin Sherman a Context-aware Recommender System Model for Smart Urban Environment Shen. 2017. Security and privacy in smart city applications: Challenges and (MoMM ’13). ACM. solutions. IEEE Communications Magazine 55, 1 (2017), 122–129. [22] Kevin Hamilton, Karrie Karahalios, Christian Sandvig, and Cedric Langbort. 2014. The image of the algorithmic city: a research approach. ID&A 20 (2014). [23] Negar Hariri, Bamshad Mobasher, and Robin Burke. 2014. Context Adaptation in Interactive Recommender Systems (RecSys ’14). ACM. [24] Drew Hemment and Anthony Townsend. 2013. Smart Citizens. Vol. 4. FutureEv- erything Publications. [25] Hsun-Ping Hsieh, Shou-De Lin, and Yu Zheng. 2015. Inferring Air Quality for Station Location Recommendation Based on Urban Big Data (KDD ’15). ACM. [26] Dietmar Jannach and Gediminas Adomavicius. 2016. Recommendations with a Purpose. In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys ’16). Association for Computing Machinery, New York, NY, USA, 7–10. https://doi.org/10.1145/2959100.2959186 [27] Craig Johnson, Noah Toly, and Heike Schroeder (Eds.). 2015. The Urban Climate Challenge: Rethinking the Role of Cities in the Global Climate Regime. Taylor & Francis. [28] Y.-K. Juan, L. Wang, J. Wang, J. O. Leckie, and K.-M. Li. 2011. A Decision-support System for Smarter City Planning and Management. IBM J. Res. Dev. 55, 1&2 (2011). [29] Dmitry Kislyuk, Yuchen Liu, David Liu, Eric Tzeng, and Yushi Jing. 2015. Human Curation and Convnets: Powering Item-to-Item Recommendations on Pinterest. arXiv preprint arXiv:1511.04003 (2015). [30] Martin Kracheel. 2015. Changing Mobility Behaviour through Recommendations. In CrowdRec’15 @ RecSys2015. [31] Ago Luberg, Tanel Tammet, and Priit Järv. 2011. Smart City: A Rule-based tourist recommendation system. In Information and Communication Technologies in Tourism. Springer. [32] Kevin Lynch. 1960. The Image of the City. MIT Press. [33] Scott D. Mainwaring, Ken Anderson, and Michele F. Chang. 2005. Living for the Global City: Mobile Kits, Urban Interfaces, and Ubicomp. In Proceedings of the 7th International Conference on Ubiquitous Computing (UbiComp’05). Springer. [34] Deepa Mallela, Dirk Ahlers, and Maria Soledad Pera. 2017. Mining Twitter Features for Event Summarization and Rating. In IEEE/WIC/ACM International Conference on Web Intelligence (WI). ACM, New York, NY, USA, 615–622. https: //doi.org/10.1145/3106426.3106487 [35] Charles Montgomery. 2013. Happy City: Transforming Our Lives Through Urban Design. Macmillan. [36] Tamas Motajcsek, Jean-Yves Le Moine, Martha Larson, Daniel Kohlsdorf, An- dreas Lommatzsch, Domonkos Tikk, Omar Alonso, Paolo Cremonesi, Andrew Demetriou, Kristaps Dobrajs, Franca Garzotto, Ayşe Göker, Frank Hopfgart- ner, Davide Malagoli, Thuy Ngoc Nguyen, Jasminko Novak, Francesco Ricci, Mario Scriminaci, Marko Tkalcic, and Anna Zacchi. 2016. Algorithms Aside: Recommendation As The Lens Of Life. In Proceedings of the 10th ACM Conference on Recommender Systems (RecSys ’16). ACM, 215–219. https://doi.org/10.1145/ 2959100.2959164 [37] Elsa Negre and Camille Rosenthal-Sabroux. 2014. Recommendations to Improve the Smartness of a City. In Smart City. Springer. [38] Daniele Quercia, Rossano Schifanella, and Luca Maria Aiello. 2014. The Shortest Path to Happiness: Recommending Beautiful, Quiet, and Happy Routes in the City. In Proceedings of the 25th ACM Conference on Hypertext and Social Media (HT ’14). ACM. [39] Annelien Smets, Nils Walravens, and Pieter Ballon. 2020. Designing Recom- mender Systems for the Common Good. In UMAP2020. ACM, 276–278. [40] Nava Tintarev and Judith Masthoff. 2007. A Survey of Explanations in Recom- mender Systems (ICDEW ’07). IEEE. [41] Anthony M Townsend. 2013. Smart Cities: Big Data, Civic Hackers, and the Quest for a new Utopia. W.W. Norton & Company. [42] Stefano Valtolina, Marco Mesiti, and Barbara Rita Barricelli. 2014. User-Centered Recommendation Services In Internet of Things Era. In CoPD @ AVI2014. [43] Feng Xia, Nana Yaw Asabere, Aser M Ahmed, Jing Li, and Xiangjie Kong. 2013. Mobile multimedia recommendation in smart communities: A survey. Access, IEEE 1 (2013). [44] Jie Yang, Iván Cantador, Diana Nurbakova, María E. Cortés-Cediel, and Alessan- dro Bozzon. 2017. Recommender Systems for Citizens: The CitRec’17 Workshop Manifesto. In Proceedings of the International Workshop on Recommender Systems for Citizens @ RecSys2017 (CitRec ’17). ACM. https://doi.org/10.1145/3127325. 3177871 [45] Lina Yao, Quan Z. Sheng, Anne H.H. Ngu, Helen Ashman, and Xue Li. 2014. Exploring Recommendations in Internet of Things (SIGIR ’14). ACM. [46] Nicholas Jing Yuan, Yu Zheng, Liuhang Zhang, and Xing Xie. 2013. T-Finder: A Recommender System for Finding Passengers and Vacant Taxis. IEEE Transactions on Knowledge and Data Engineering 25, 10 (2013).