Urban Informatics

Big Data is the term being used to describe a wide spectrum of observational or “naturally-occurring” data generated through transactional, operational, planning and social activities that are not specifically designed for research. Due to the structure and access conditions associated with such data, research and analysis using such data becomes significantly complicated. New sources of Big Data are rapidly emerging as a result of technological, institutional, social, and business innovations. The objective of this background paper is to describe emerging sources of Big Data, their use in urban research, and the challenges that arise with their use. To a certain extent, Big Data in the urban context has become narrowly associated with sensor (e.g., Internet of Things) or socially generated (e.g., social media or citizen science) data. However, there are many other sources of observational data that are meaningful to different groups of urban researchers and user communities. Examples include privately held transactions data, confidential administrative micro-data, data from arts and humanities collections, and hybrid data consisting of synthetic or linked data.

The emerging area of Urban Informatics focuses on the exploration and understanding of urban systems by leveraging novel sources of data. The major potential of Urban Informatics research and applications is in four areas: (1) improved strategies for dynamic urban resource management, (2) theoretical insights and knowledge discovery of urban patterns and processes, (3) strategies for urban engagement and civic participation, and (4) innovations in urban management, and planning and policy analysis. Urban Informatics utilizes urban Big Data in innovative ways by retrofitting or repurposing existing urban models and simulations that are underpinned by a wide range of theoretical traditions, as well as through data-driven modeling approaches that are largely theory agnostic, although these divergent research approaches are starting to converge in some ways. The paper surveys the kinds of urban problems being considered by going from a data-poor environment to a data-rich world and ways in which such enquiry have the potential to enhance our understanding, not only of urban systems and processes overall, but also contextual peculiarities and local experiences. The paper concludes by commenting on challenges that are likely to arise in varying degrees when using Big Data for Urban Informatics: technological, methodological, theoretical/epistemological, and the emerging political economy of Big Data.

The memory of loss in Asia’s leading global cities has been shaped by recurrent projects of urban renewal, which have sought to deliver economic prosperity and social order at the expense of longstanding spaces and practices. Singapore’s Golden Jubilee in 2015, which commemorated its triumphant postcolonial development, was accompanied by the proliferation of public expressions of nostalgia across a variety of media platforms. Amid the rise of the participatory culture of media convergence, this paper examines how nostalgic longing is no longer necessarily articulated as an antagonistic critique of the precarious present of neoliberal capitalism, which withdraws into a timeless image of a congenial past. Departing from this conventional understanding of nostalgia in the scholarship of Singapore, it explores how the ruling government since independence has reconfigured its dissemination of historical and cultural knowledge to manage its transition from a global city defined by rapid growth to a smart nation reliant on perpetual adjustment by cultivating a form of citizenship centred on entrepreneurship and innovation. Through immersive spatialisation, commissioned mobile video games oblige players to internalise the protocols of knowledge and agency of the Singapore Story, the official narrative of economic success and national progress. Two other state-run interactive digital platforms, the National Library’s online archive the Singapore Memory Project and the National Museum’s art installation 'The Story of the Forest', are designed to cultivate a new openness to the inevitability of iteration in urban informatics. Helping to assuage popular anxiety over the constancy of change and the failure of risk-taking, the latter frames perpetual adjustment as a vital component of the cosmic cyclicality of deep time, in which vanished realities are recreated with different permutations.

Urban informatics is positioned to offer unique insights into complex urban processes through use of big data and pervasive computing. This paper examines the rise of urban informatics as a field of expert urban knowledge, with a focus on the particular visions and epistemologies of the city embedded within the field. By exploring its emergence over the past decade, and reflecting on connections with previous eras of urban computing, the article explores questions about the kind of city that is occupied, resolved and reformed by urban informatics and associated lab-style data sciences.

This chapter considers the relationship between data and the city by critically examining six key issues with respect city dashboards: epistemology, scope and access, veracity and validity, usability and literacy, use and utility, and ethics. While city dashboards provide useful tools for evaluating and managing urban services, understanding and formulating policy, and creating public knowledge and counter-narratives, our analysis reveals a number of conceptual and practical shortcomings. In order for city dashboards to reach their full potential we advocate a number of related shifts in thinking and praxes and forward an agenda for addressing the issues we highlight. Our analysis is informed by our endeavours in building the Dublin Dashboard.

The IDDF (Intelligent Data-Driven Design Futures) symposium brought together some of the world-leading thinkers, practitioners and innovators from the Built Environment and Urban Informatics research and practice to explore what “data-integrated” future might hold for our sector. The presentations and discussions challenged our “business as usual” mode of thinking and highlighted diverse insights and perspectives for more agile and adaptive solutions for the future, and in discovering sustainable modes of imagining, creating and working intelligently. With this report, we aim to summarize the
presentations and discussions, and highlight some of the diverse insights and perspectives we captured from this day-long symposium.

The purpose of this paper is to consider the role of ICT within the formalisation programme put forward by Recife’s City Council to regulate the informal trade that pervades the city’s popular squares and streets. This formalisation takes shape by issuing formal licenses to give informal workers ‘permission’ to sell pre-determined items at specific sites. Drawing on Foucault we will argue that ICT is a formalising technology, which serves this formalising regime to control, discipline and survey informal traders. We will argue that the technology’s disciplinary intent was shaped by: a) the ways by which the socio-political context, rather than a technical rationality, affected how both control and surveillance were performed and disciplinary decisions were enacted; b) how its appropriation by licensed workers facilitated the reach of the regime’s surveillance but in some cases also sabotaged the programme’s disciplinary intents, c) how the information system reinforced the marginalization of informal workers and strengthened the position of the municipality.

Currently, both private and institutional actors are using the most common social networks to promote the public dimension of their work, but only big players can afford large investments for spreading their initiatives, practices or building a participatory process of any kind. The existing social networks have several limitations: they have been modelled on a personalistic logic centred on the individual and on his/her private life. On the other hand, information about initiatives and actions of public interest are shattered in institutional and private websites making impossible to depict what is happening in the city. This contribution addresses the design a public platform for public initiatives, opened to any kind of public players, from citizens to institutions, from non-profit organizations to companies. We present the outcomes of the scenario analysis and the participatory design process, showing how general requirements have been translated in design principles and functionalities available in the platform FirstLife.

Developing a civic social network requires to consider users meeting in real life, collaborating on digital entries related to real urban entities. This makes necessary to think about collaboration tools in a new perspective: ensuring the participation of users with different levels and forms of legitimacy to represent complex relations among entities, and ensuring the accountability of each contributor. We present a set of technical solutions allowing the collaboration on complex entities, keeping interactions simple, and representing multiple perspectives about shared entities.

This paper assesses non-traditional urban digital infomediaries who are pushing the agenda of urban Big Data and Open Data. Our analysis identified a mix of private, public, non-profit and informal infomediaries, ranging from very large organizations to independent developers. Using a mixed-methods approach, we identified four major groups of organizations within this dynamic and diverse sector: general-purpose ICT providers, urban information service providers, open and civic data infomediaries, and independent and open source developers. A total of nine types of organizations are identified within these four groups. We align these nine organizational types along five dimensions that account for their mission and major interests, products and services, as well activities they undertake: techno-managerial, scientific, business and commercial, urban engagement , and openness and transparency. We discuss urban ICT entrepreneurs, and the role of informal networks involving independent developers, data scientists and civic hackers in a domain that historically involved professionals in the urban planning and public management domains. Additionally, we examine convergence in the sector by analyzing overlaps in their activities, as determined by a text mining exercise of organizational webpages. We also consider increasing similarities in products and services offered by the infomediaries, while highlighting ideological tensions that might arise given the overall complexity of the sector, and differences in the backgrounds and end-goals of the participants involved. There is much room for creation of knowledge and value networks in the urban data sector and for improved cross-fertilization among bodies of knowledge.

This article examines the dreams and wishes of young-adult city residents regarding future ICT development, comparing its findings with two visions of ICT development offered by large-scale urban agendas, namely ‘smart cities’ and ‘ubiquitous computing.’ The article explores how the visions of ordinary city inhabitants contest or resonate with grand visions of urban future, and investigates alternative agendas that might be built upon those visions. The research site, the city of Oulu in northern Finland, offers a concrete example of a ‘future city’ in which many ideas relating to ‘smart’ and ‘ubiquitous’ urban space have been put into practice. The results indicate there is an urgent need to address questions pertaining to control, agency, and resistance in designing further technology for cities and to employ design practices that enable the creation and implementation of bottom-up visions.

This paper applies urban informatics methods and techniques on big data generated from the concentrated environment of the second largest music festival in the world, Roskilde Festival. First, we explain how to utilize relevant dimensions from human geography theories towards mapping a 'Geography of Importance'. Second, we elaborate on methods deployed for collecting both mobile GPS and social media traces that the smart phone generates in physical spaces. Third, we compare and contrast the automatically geocoded presence in space and at events with the intentionally socially tagged consumption of these spaces and events as place-based experiences. In doing so, these two layers of space-based movements and place-based experiences reveal the appropriation of affordances and choices of aesthetic appreciation by the crowd at large of what is subjectively and relatively meaningful, actionable, and valuable.

Urban areas are increasingly playing a bigger role in our societies. “Approximately 359 million people – 72% of the total EU population – live in cities, towns and suburbs. Urban areas face multiple and interconnected challenges related to employment, migration, demography, water and soil pollution, etc. But, they are also engines of new ideas and solutions, dynamic places where changes happen on a larger scale and at a fast pace. Over 70% of the EU’s population lives in towns and cities and this growth is set to continue in the coming years. Many of the social, economic and environmental issues Europe faces have an urban dimension and are most likely to have a larger impact in cities. On the other hand, cities are where the potential for innovation lies to solve these issues.” (1).
The European Union adopted the Pact of Amsterdam on the 30 May of 2016, a new European Urban Agenda (2). This document make official the strategy to improve the cooperation among cities and strengthen the "urban dimension" in EU decision making by assuming cities as priority funds target.
In order to stimulate growth, liveability and innovation in the cities of Europe and to ensure the maximum utilisation of the growth potential of cities to successfully tackle social challenges, the European Commission decided to fixe new working methods with the following objectives:
• To promote, develop, implement and evaluate regulations and legislation in line with local practice in cities, integrating the operative level of Member state with the local entities.
• To support cities in having a better access and utilisation of European funds, shifting the focus from territories to cities.
• To improve the cooperation based on sharing good practices, urban knowledge and innovation.
The United Nations Conference on Housing and Sustainable Urban Development took place this year in Quito, Ecuador (https://habitat3.org/) involving thirty thousand people from 167 countries and from different sectors: mostly local government and majors, but also non- profit, business and academia. The product of this event, happening ones in 20 years, is the New Urban Agenda, an action oriented document that set global standards of achievement in sustainable development. One of the major point of this global summit has been the new positive role accorded to the urbanization and the rethinking of cities as resources centre to exploit for improving the quality of life of the world population and address future challenges. The new role of ICT in shaping the future of cities has been synthetize in:
“We will promote the development of national information and communications technology policies and e government strategies as well as citizen-centric digital governance tools, tapping into technological innovations, including capacity development programmes, in order to make information and communications technologies accessible to the public, including women and girls, children and youth, persons with disabilities, older persons and persons in vulnerable situations, to enable them to develop and exercise civic responsibility, broadening participation and fostering responsible governance, as well as increasing efficiency. The use of digital platforms and tools, including geospatial information systems, will be encouraged to improve long-term integrated urban and territorial planning and design, land
3

administration and management, and access to urban and metropolitan services.” New Urban Agenda (3).
It is not surprising that Computer Science is increasingly focusing on urban areas to support solutions towards the above challenges. If firstly Computer Science proposed technological solutions, as witnessed by the Smart Cities trend, nowadays citizens are becoming the centre of the debate. Marcus Foth in the Handbook of Research on Urban Informatics (4) affirms that “information is literally what constitutes a city” highlighting how the role of the physical city is to be a container for information-based human activities.
It is not surprising that Computer Science is increasingly focusing on urban areas to support solutions towards the above challenges. If firstly Computer Science proposed technological solutions, as witnessed by the Smart Cities trend, nowadays citizens are becoming the centre of the debate. Marcus Foth in the Handbook of Research on Urban Informatics (4) affirms that “information is literally what constitutes a city” highlighting how the role of the physical city is to be a container for information-based human activities.
Among the many challenges offered by urban areas we focus on the collaborative management by citizens of commons. A growing literature in sociology, economics, law architecture, etc. recognizes that cities are commons: urban areas are not only private or public, but they belong also to a third dimension of economics where citizens manage and take care of urban spaces and municipalities assume the role of enablers. This trend makes pair with the recognition that citizens play a role in public services and when this role is recognized and supported, it is likely that the services are improved. The Nobel prize Elinor Ostrom has been the economist who introduced in the scientific debate both issues from the ‘90s.
In both cases the point is supporting the cooperation among citizens via a civic platform. The first two requirements for such a platform are self-evident:
1. It must express the geographical dimension of urban spaces.
2. It must offer social network functionalities.
Already these two requirements pose a challenge, since there is no solution combining the two aspects both at a research and commercial level. Moreover, entering in the details of putting these two dimensions together raises a number of further research questions:
1. Since many social networks already exists, which are the requirements requesting for a new one of a different kind?
2. Which kind of entities should populate the urban map? which are the properties of such entities? which are their functionalities? how they are connect the one with the other?
3. Traditional cartography associates different information at different level of details. Current GIS or VGI technology don’t. How to allow users to interact with an urban map at different levels of detail? How to build automatically different scales starting from cartographic data such as OpenStreetMap?
4. Since the platform’s aim is to support cooperation, an explicit management of time is requested. Most social applications and VGI sistems don’t consider time. How to model the temporal dimension of urban entities in an effective and efficient way?
5. How organize the architecture of such a system, which merges social networking functionalities and GIS? Being a platform oriented to citizens, how to involve them in the co-design of the platform so to take advantage of a participatory approach?
4

6. Finally, given the general-purpose character of such a platform, how to test it in different settings?
The methodology to answer these questions is not merely theoretical but it resulted in the development of the georeferenced FirstLife civic social network which the candidate worked on and in its testing, in an action-research fashion. In doing this, the candidate lead a team of several programmers and cooperated with the other researchers working on the co-design and testing, under the overall supervision of Prof. Guido Boella within the framework of several funded research projects (see Chapter 8).
Integral part of the thesis is thus the platform itself deriving from the research answering the above research questions. FirstLife is a fully functional prototype developed using precise software engineering methodologies and tested in several scenarios with around 2,000 users.

We describe the Integrated Multimedia City Data (iMCD), a data platform involving detailed person-level self-reported and sensed information, with additional Internet, remote sensing, crowdsourced and environmental data sources that measure the wider social, economic and physical context of the participant. Selected aspects of the platform, which covers the Glasgow, UK, city-region, are available to other researchers, and allows knowledge discovery on critical urban living themes, for example in transportation, lifelong learning, sustainable behavior, social cohesion, ways of being in a digital age, and other topics. It further allows research into the technological and methodological aspects of emerging forms of urban data. Key highlights of the platform include a multi-topic household and person-level survey; travel and activity diaries; a privacy and personal device sensitivity survey; a rich set of GPS trajectory data; accelerometer, light intensity and other personal environment sensor data from wearable devices; an image data collection at approximately 5-second resolution of participants' daily lives; multiple forms of text-based and multimedia Internet data; high resolution satellite and LiDAR data; and data from transportation, weather and air quality sensors. We demonstrate the power of the platform in understanding personal behavior and urban patterns by means of three examples: an examination of the links between mobility and literacy/learning using the household survey, a social media analysis of urban activity patterns, and finally, the degree of physical isolation levels using deep learning algorithms on image data. The analysis highlights the importance of purposefully designed multi-construct and multi-instrument data collection approaches that are driven by theoretical frameworks underpinning complex urban challenges, and the need to link to policy frameworks (e.g., Smart Cities, Future Cities, UNESCO Learning Cities agendas) that have the potential to translate data to impactful decision-making.

This report provides a summary of the organization, program, and outcome of the Dagstuhl Seminar titled "Do-it-yourself networking: an interdisciplinary perspective". We first motivate our interest in wireless networks operating outside the public Internet and the selection of the most relevant areas of expertise. Then we describe the process of bringing together a balanced group of representatives from these areas, and the evolution of the seminar over time. An overview of the interactions during the work in groups on specific application areas and explorations of the concept of failure, edited collectively by the members of the different groups, summarizes the main outcomes of the seminar. Finally, we identify some important lessons learned for facilitating interdisciplinary collaborations and conclude with our plans toward building a DIY networking community of researchers and activists.

As data-driven approaches are introducing and establishing a new set of economic, social and cultural values, we have started to question some of our age old assumptions, conceptions and practices about our built habitat. One of the most profound implications is the transformation of the AEC (Architecture, Engineering and Construction) industry from a document based to an information based business. Both the impact and scale of this transformation will become more dramatic with the increase in global data traffic two thirds of which is predicted to move on to cloud computing systems by 2016 (Cisco Global Cloud Index, 2011-2016). This implies the introduction of even more complex and diverse interactions (e.g. through internet of things) between buildings, infrastructures and humans. Such developments have already made significant impact in other industries and are likely to be a step change in how we build and operate in the near future. “Data” is not new to our industry, however what is new is the amount of data that is currently available to us and our improved capacity to share, capture, measure, compile, process and translate data into meaningful and actionable information. Although the potentials are vast, Architectural/Engineering practice and Construction sector are slow to adopt the data-driven approaches. The IDDF (Intelligent Data-Driven Design Futures) symposium brought together some of the world-leading thinkers, practitioners and innovators from the Built Environment and Urban Informatics research and practice to explore what “data-integrated” future might hold for our sector. The presentations and discussions challenged our “business as usual” mode of thinking and highlighted diverse insights and perspectives for more agile and adaptive solutions for the future, and in discovering sustainable modes of imagining, creating and working intelligently. With this document we aim to summarize the presentations and discussions, and highlight some of the diverse insights and perspectives we captured from this day-long symposium.

As more people tweet, check-in and share pictures and videos of their daily experiences in the city, new opportunities arise to understand urban activity. When aggregated, these data can uncover invaluable local insights for local stakeholders such as journalists, first responders and city officials. To better understand the needs and requirements for this kind of aggregation tools, we perform an exploratory study that includes interviews with 12 domain experts that utilize local information on a daily basis. Our results shed light on current practices, existing tools and unfulfilled needs of these professionals. We use these findings to discuss the requirements for hyper-local social media data aggregation tools for the study of cities on a large scale. We outline a list of key features that can better serve the discovery of patterns and insights about both real-time activity and historical perspectives of local communities.

Recent increases in the use of and applications for wearable technology has opened up many new avenues of research. In this paper, we consider the use of lifelogging and GPS data to extend fine-grained movement analysis for improving applications in health and safety. We first design a framework to solve the problem of indoor and outdoor movement detection from sensor readings associated with images captured by a lifelogging wearable device. Second we propose a set of measures related with hazard on the road network derived from the combination of GPS movement data, road network data and the sensor readings from a wearable device. Third, we identify the relationship between different socio-demographic groups and the patterns of indoor physical activity and sedentary behaviour routines as well as disturbance levels on different road settings.

The model of urban entities to build a temporal indexing system for co-existing services and activities in the city is based on the development of time-features and time-based solutions for data management and retrieval in complex changing environments, considering the relation between spatial and time attributes, the time granularity organized in a scale theory, the multidimensionality and sematic of time. Starting from the model, this work present a pragmatic solution to build a global calendar of the city to represent real-time and fast retrieve a big dataset of entries. The presented solution on based on the extension of CRON expressivity on the basis of ICalendar basic features in order to switch from Point-Based CRON Expressions to Interval-Based CRON Masks.

The paper presents a comparison between aims, theories and practices in city planning and in the use of web-based technologies in urban activities to highlight the different instances of the two macro-domains in conceptualizing city dynamics and elaborating solutions to address urban challenges. The analysis had been structured by considering the three key dimensions constituting the pillars of Urban Informatics: people, city and technology. The analysis had been developed focusing first on the misalignments between current web-based technologies and city planning, then moving to the identification of their convergences. Building on this analysis, the paper outlines three future directions to rethink the integration and future design of web-based technologies in city planning actions as planning support systems to manage the production and use of city data, the orchestration of local activities , and the integration of city plans with distributed urban initiatives.

In this paper we explore the notion of mobile users’ similarity as a key enabler of innovative applications hinging on opportunistic mobile encounters. In particular, we analyze the performance of known similarity metrics, applicable to our problem domain, as well as propose a novel temporal-based metric, in an attempt to quantify the inherently qualitative notion of similarity. Towards this objective, we first introduce generalized profile structures, beyond mere location, that aim to capture users interests and prior experiences, in the form of a probability distribution. Afterwards, we analyze known and proposed similarity metrics for the proposed profile structures using publicly available data. Apart from the classic Cosine similarity, we identify a distance metric from probability theory, namely Hellinger distance, as a strong candidate for quantifying similarity due to the probability distribution structure of the proposed profiles. In addition, we introduce a novel temporal similarity metric, based on matrix vectorization, to capitalize on the richness in the temporal dimension and maintain low complexity. Finally, the numerical results unveil a number of key insights. First, the temporal metrics yield, on the average, lower similarity indices, compared to the non-temporal ones, due to incorporating the dynamics in the temporal dimension. Second, the Hellinger distance holds great promise for quantifying simi- larity between probability distribution profiles. Third, vectorized metrics constitute a low-complexity approach towards temporal similarity on resource-limited mobile devices.

Social entrepreneurship is increasingly becoming a tool to undertake social, cultural and environmental issues in communities where startup businesses and entrepreneurs develop fund or implement ideas aimed for the solution of these problems. Whether intentionally or otherwise, numerous startups and spin-offs, have in a way or another, provided services that address larger themes including, but not limited to, sustainability, public transportation and mobility which are also key components to smart cities.

Often led by youth, and through the employment of Information and Communication Technology (ICT) and the Internet of Things (IoT), which have also become integral parts in smart cities thinking, social entrepreneurs are rapidly changing cities in ways city planners may never consider and thus becoming an under-recognised planning force to be reckoned with. On this note, this paper argues, a mobilisation for this force which aims to harnessing its potentials towards sustainable smart cities’ development is becoming an urgent need. Moreover, as social entrepreneurship heavily depends on social networking and social media, thus acquiring an immediate interaction with a larger group of the local community as opposed to traditional planning methods, this paper argues it may further the advancement of participative approaches that include the public in the decision-making and planning of their own cities.

Through showcasing social entrepreneurship endeavours that have successfully addressed smart cities dilemmas in the case of Amman, Jordan, this paper aims to further explore the links between the two concepts. Furthermore, considering the little literature available on both topics in non-western literature and developing countries context, and through looking at the non-traditional ways these projects addressed city planning problems, this paper bids to find ways to inform traditional city planners towards the achievement of smart cities goals.

We describe the Integrated Multimedia City Data (iMCD), a data platform involving detailed person-level selfreported and sensed information, with additional Internet, remote sensing, crowdsourced and environmental data sources that measure the wider social, economic and physical context of the participant. Selected aspects of the platform, which covers the Glasgow, UK, city-region, are available to other researchers, and allows knowledge discovery on critical urban living themes, for example in transportation, lifelong learning, sustainable behavior, social cohesion, ways of being in a digital age, and other topics. It further allows research into the technological and methodological aspects of emerging forms of urban data. Key highlights of the platform include a multi-topic household and person-level survey; travel and activity diaries; a privacy and personal device sensitivity survey; a rich set of GPS trajectory data; accelerometer, light intensity and other personal environment sensor data from wearable devices; an image data collection at approximately 5-second resolution of participants' daily lives; multiple forms of text-based and multimedia Internet data; high resolution satellite and LiDAR data; and data from transportation, weather and air quality sensors. We demonstrate the power of the platform in understanding personal behavior and urban patterns by means of three examples: an examination of the links between mobility and literacy/learning using the household survey, a social media analysis of urban activity patterns, and finally, the degree of physical isolation levels using deep learning algorithms on image data. The analysis highlights the importance of purposefully designed multi-construct and multi-instrument data collection approaches that are driven by theoretical frameworks underpinning complex urban challenges, and the need to link to policy frameworks (e.g., Smart Cities, Future Cities, UNESCO Learning Cities agendas) that have the potential to translate data to impactful decision-making. energy data, or new technologies supporting crowdsourcing and usergenerated text, image, video, audio content, have either extended the ability to address existing research questions in new ways, For example, while earlier research utilized vehicle-based GPS to monitor traffic and transportation networks (Sen, Thakuriah, Zhu, & Karr, 1997; Sethi, Bhandari, Koppelman, & Schofer, 1995), the proliferation of cellphones and wearable devices that individuals can carry with them, allow passive monitoring of daily activities in minute detail leading to new research questions in mobility, health, and wellbeing (Appelboom et al.,

To increase mobile user engagement, photo sharing sites are trying to identify interesting and memorable pictures. Past proposals for identifying such pictures have relied on either metadata (e.g., likes) or visual features. In practice, techniques based on  those two inputs  do not always work: metadata is sparse (only few pictures have considerable number of likes), and extracting visual features is computationally expensive. In mobile solutions,  geo-referenced content becomes increasingly important. The premise behind this work is that pictures of a neighborhood is linked to the way the neighborhood is perceived by people: whether it is, for instance, distinctive and beautiful or not.  Since 1970s, urban theories proposed by Lynch, Milgram and Peterson aimed at systematically capturing the way people perceive neighborhoods. Here we tested whether those theories could be put to use for automatically identifying appealing city pictures.  We did so by gathering geo-referenced Flickr pictures in the city of London; selecting six urban qualities associated with those urban theories; computing proxies for those qualities from online social media data; and ranking Flickr pictures based on those proxies. We find that our proposal enjoys three main desirable properties: it is effective, scalable, and aware of contextual changes such as  time of day and weather condition. All this suggests new promising research directions for multi-modal learning approaches that automatically identify appealing city pictures.