Access to this full-text is provided by Springer Nature.
Content available from Humanities and Social Sciences Communications
This content is subject to copyright. Terms and conditions apply.
ARTICLE
Artificial intelligence may affect diversity:
architecture and cultural context reflected through
ChatGPT, Midjourney, and Google Maps
Ingrid Campo-Ruiz 1✉
This study aims to understand how widely used Artificial Intelligence (AI) tools reflect the
cultural context through the built environment. This research explores how outputs obtained
with ChatGPT-4o, Midjourney’s bot on Discord and Google Maps represent the cultural
context of Stockholm, Sweden. Cultural context is important because it shapes people’s
identity, behaviour, and power dynamics. AI-generated recommendations and images of
Stockholm’s cultural context were compared with real photographs, GIS demographic data
and socio-economic information about the city. Results show how outputs written with
ChatGPT-4o mostly listed museums and other venues popular among visitors, while Mid-
journey’s bot mostly represented cafes, streets, and furniture, reflecting a cultural context
heavily shaped by buildings, consumption and commercial interests. Google Maps shows
commercial sites while also enabling users to directly add information about places, like
opinions, photographs and the main features of a business. These AI perspectives on cultural
context can broaden the understanding of the urban environment and facilitate a deeper
insight into the prevailing ideas behind the data that train these algorithms. Results suggest
that the generative AI systems analysed convey a narrow view of the cultural context,
prioritising buildings and a sense of cultural context that is curated, exhibited and com-
mercialised. Generative AI tools could jeopardise cultural diversity by prioritising some ideas
and places as “cultural”, exacerbating power relationships and even aggravating segregation.
Consequently, public institutions should promote further discussion and research on AI tools,
and help users combine AI tools with other forms of knowledge. The providers of AI systems
should ensure more inclusivity in AI training data, facilitate users’writing of prompts and
disclose the limitations of their data sources. Despite the current potential reduction of
diversity of the cultural context, AI providers have a unique opportunity to produce more
nuanced outputs, which promote more societal diversity and equality.
https://doi.org/10.1057/s41599-024-03968-5 OPEN
1KTH Royal Institute of Technology, ABE School of Architecture and the Built Environment, School of Architecture, Stockholm, Sweden. ✉email: icr@kth.se
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5 1
1234567890():,;
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Introduction
This study aims to understand how widely used Artificial
Intelligence (AI) tools reflect the cultural context through
the built environment. This research explores how AI tools
interpret and represent the cultural context of Stockholm, Swe-
den, comparing AI-generated recommendations and images of
Stockholm’s cultural context with real photographs and demo-
graphic information about the city. This research critically
examines the impact of AI on societies and equality, particularly
through its influence on urban spaces. This study explores the
consequences for society, urban space, and social justice of the
perspectives on cultural context conveyed by mainstream AI
tools.
The research question is: how is cultural context represented by
mainstream AI tools and what are their consequences for society,
urban space, and social justice? To explore this question, datasets on
cultural context from interactions with ChatGPT-4o and Mid-
journey’s bot on Discord were compared and analysed with Google
Maps, and with photographs of Stockholm and Geographic Infor-
mation System statistical geolocated population data.
Cultural context affects communication (Marion, 2017), and can
facilitate social diversity, and inclusion. In terms of architecture,
appreciating cultural context is key to a better understanding of the
needs and motivations of people inhabiting a space. The terms
‘context’,‘contextual’,and‘contextualism’became important to the
critics of the early modern movement in architecture after the
publication of an article by Ernesto Rogers, in which the Italian
word ambiente was translated into the English language as “con-
text”(Forty, 2000, pp. 132–135). The word context comes from
Latin con texere meaning weaving together and it aligns with the
idea that people and places are all interconnected in multiple ways.
The relationship with the physical environment defines people’s
identities, for example, the place where people belong (Peng et al.
2020). Culture can affect how people behave and include others
(Adobor, 2021). It can be understood as a selection of frames of
reality, which can help identify problems and their causes, and can
also be a form of exerting power (McNealy, 2021). The concept of
interculturality needs to be redefined constantly because it is often
connected to a dominating ideology (Dervin, 2023). Cultural
contexts of individuals influence their thoughts, well-being, values,
lives and experiences (Parker et al. 2020). Stereotypes, prejudice,
and discrimination in a diverse social group can erode social
cohesion and enhance divisions within societies, whereas, by
contrast, diversity can foster creativity (Khan, 2024b).
Thus, the current analysis aims to contribute to deeper insights
into the cultural context by examining how increasingly used AI
tools reflect the cultural context of a city, determine what con-
textual actors are highlighted and which are neglected, under-
stand power structures and explore opportunities to enhance
social cohesion, diversity and equality. Reducing inequalities is
one of the United Nations’Sustainable Development Goals.
While AI has been part of everyday life for the last decade,
influencing work, homes, and social relationships (Elliott, 2018),
recent AI systems are a turning point with their human-like
production of conversations and predictions and their extended
usability beyond expert users.
Before AI, many visitors explored cities with printed guides,
city maps, information from tourist offices, guided tours, and
personal recommendations. Locals moved across the city based
on previous knowledge and recommendations from their net-
work. However, the amount of data collected in cities through
sensors and reviews is now enormous and AI tools can help us
better understand the places we inhabit (Ullah et al. 2020). Tri-
pAdvisor and other social networks have transformed and
changed the way travellers and tourists seek, find, and share
information from online reviews rather than tourism providers
(Ali et al. 2021). Additionally, many AI tools are readily available
to many Internet users and can provide data about a place.
ChatGPT attracted 100 million users in the first two months after
its release in November 2022 by OpenAI (Anon, 2023). ChatGPT
has been rapidly adopted in different industries such as educa-
tion, healthcare, and entertainment (Gupta et al. 2024).
Therefore, the new context in cities includes historical and
personal information, and AI recommendations, based on undi-
sclosed parameters. Widely used AI tools may exert a significant
influence on users’choices of where to go and how they experi-
ence a place, the routes they choose, or the way they illustrate
their works. With AI, the new context includes many curated
inputs from previous users who have expressed their opinions
and with whom not everyone might relate, which act as big filters
of reality through their recommendations and images.
According to the OECD, an AI system is “a machine-based
system that can, for a given set of human-defined objectives,
make predictions, recommendations or decisions influencing real
or virtual environments”(OECD, 2019). The European Com-
mission defines AI as follows:
“AI system’means a machine-based system that is designed
to operate with varying levels of autonomy and that may
exhibit adaptiveness after deployment, and that, for explicit
or implicit objectives, infers, from the input it receives, how
to generate outputs such as predictions, content, recom-
mendations, or decisions that can influence physical or
virtual environments (The European Parliament and the
Council of the European Union, 2024)’.
Generative AI models are a subset of AI that can generate new
data such as the patterns, structures, and features of the data on
which they were trained (Khan, 2024a) and according to user
requirements. Some limitations of generative AI models include
some misleading outputs with severe social consequences (Khan,
2024a) and environmental impact (George et al. 2023). In the
same AI Act, the European Parliament states that:
‘If the AI system is not trained with high-quality data, does
not meet adequate requirements in terms of its performance,
its accuracy or robustness, or is not properly designed and
tested before being put on the market or otherwise put into
service, it may single out people in a discriminatory or
otherwise incorrect or unjust manner (The European
Parliament and the Council of the European Union, 2024)’.
This new context with AI also includes a global struggle for
control of these influential tools. Tech giants like Alphabet
(Google), Apple, Meta (Facebook), Amazon, and Microsoft from
the USA, and Baidu, Alibaba, and Tencent from China dominate
and control the market with increasingly powerful AI tools
(Verdegem, 2022). The Chinese government is aiming to become
the largest AI development hub by 2030 (Mozur, 2017).
In the face of the rapid and powerful development of AI sys-
tems, over 30,000 people have called for this development to be
paused, in order to plan and manage the risks to humankind
(Future of Life Institute, 2023). Among the risks identified, the
lack of transparency, whereby users cannot understand how AI
systems work, jeopardises fairness, accountability (Lo Piano,
2020), reliability of information and the organisations that pro-
duce it (von Eschenbach, 2021).
Background and related studies
After Alan Turing questioned whether machines could think, the
1956 Dartmouth Summer Research Project was widely accepted
as the birthplace of AI (OECD, 2019). Research on AI and culture
ARTICLE HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5
2HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
dates back to the beginnings of AI and the explorations of the
relationship between the human mind and algorithms (Newell
and Simon, 1976; Searle, 1980; Dreyfus and Dreyfus, 1988;
Churchland and Churchland, 1990). In the 1970s, Weizenbaum
argued that people should not be regarded as mere information-
processing machines, against the metaphor of machine dom-
inance, and that AI should be understood within its cultural
context (Weizenbaum 1984). In the 1990s, Richard Wallace
developed the Artificial Linguistic Internet Computer Entity,
which could interact with humans in simple conversation, and
IBM’s Deep Blue defeated chess champion Gary Kasparov
(OECD, 2019).
Today, urban AI focuses on the relationship between AI sys-
tems and urban contexts, whereby AI can affect the governance of
cities and their relationship with other areas (Luusua et al. 2023).
Urban AI comprises different AI systems that affect cities and by
which cities also affect AI systems, where citizens could even play
a marginal role (Cugurullo et al. 2023).
AI systems can help analyse extensive datasets that affect
urban planning, such as demographics, land use, and traffic
(Peng et al. 2023). AI tools could help urban planners analyse
multiple parameters simultaneously and mitigate inequalities
(Lyu et al. 2024). AI can also help promote the accessibility of
urban data for greater participatory governance and justice
(Howe et al. 2022).
However, the ubiquitous and constant AI systems that analyse
people, traffic, and other phenomena in cities could also be
viewed as a centralised and omnipresent system that controls
citizens (Crawford, 2021), or a “Polyopticon”, a network of sen-
sors and algorithms with multiple perspectives under continuous
observation (Bratton, 2021; Sherman, 2023). However, AI systems
in the urban context could be understood as an assemblage of
distributed systems from heterogenous stakeholders and in con-
tinuous transformation (Tseng, 2023). In fact, in some of the so-
called smart cities, a holistic approach to AI systems is lacking
(Cugurullo, 2021; Macrorie et al. 2021). Urban AI systems require
a holistic understanding to be implemented with transparency,
communicability, and visibility in the urban context (Popelka
et al. 2023).
Beyond analysis, AI can influence life in cities at other levels
and can affect urban form in unknown ways through technologies
operating at landscape scale (Bratton, 2021). It can also affect the
governance of cities through machines that behave autonomously
(Cugurullo, 2020) and through systems that perform unsu-
pervised managerial functions (Cugurullo et al. 2024). AI systems
applied in the urban context could also increase disadvantages
between cities (Macrorie et al. 2021).
Moreover, AI systems affect social diversity, equality, and
inclusion (Cachat-Rosset and Klarsfeld, 2023). Sex and gender
diversity are often at risk in AI applications (Fosch-Villaronga
and Poulsen, 2022). Many AI systems extract average trends from
enormous quantities of data and these averages may narrowly
integrate the diversity of people, perpetuating stereotypes and
biases (Sloan and Warner, 2020). AI can even portray migrants as
a security threat (Bircan and Korkmaz, 2021). Recommendations
powered by AI from social media could isolate users in ‘filter
bubbles’of virtual groups of people with similar affinities (Pariser,
2011), contribute to the dissemination of fake news (Rhodes,
2022), add new biases to existing ones (Bozdag, 2013), limit
information diversity (Sun et al. 2022), and exacerbate political
polarisation (Geschke et al. 2019). However, users’choices are
still the main driver of engagement with partisan and unreliable
news on Google Search rather than algorithmic recommendations
(Robertson et al. 2023).
In this study, cultural context is considered through multiple
interconnected dimensions, including education, employment,
financial resources, political empowerment, gender, and space.
Mironenko and Sorokin (2018)define culture as follows:
‘Culture includes material objects: artefacts, ranging from
planetary scale to jewellery. There are also spiritual, non-
material components: languages, literature, art, science, etc.
Culture also includes processes: external –social, ranging
from individual to collective modes of behaviour (for
instance, relating to constantly emerging and changing
customs and traditions); and internal –individually-
psychic’.
Cultural context is closely related to place identity or the
characteristics that distinguish one place from another and affect
human–environment interactions (Jang et al. 2023).
As regards culture, AI systems can mismatch the cultural
norms and expectations of target cultural groups and produce
cultural barriers by imposing hegemonic classifications, offensive
or toxic settings, violating cultural values that are important for a
group, and by omitting, trivialising, or simplifying certain iden-
tities and histories (Prabhakaran et al. 2022).
Therefore, AI systems and their implementation at urban level
by local authorities require urgent further research (Yigitcanlar
et al. 2021). Additional research on AI could help urban man-
agement and development processes (Son et al. 2023). Urban AI
systems should be combined with other forms of knowledge while
contemplating social and environmental contexts (Palmini and
Cugurullo, 2023). There is a relative lack of interdisciplinarity
connecting experts on AI, architecture, and civil society (Tseng,
2023). Combining urban AI with real-life needs and practical
applications may accelerate the use and benefits of AI in urban
planning (Sanchez et al. 2023).
Stockholm city centre and closest municipalities are a suitable
testbed to study how tools with AI reflect the cultural context
through a combination of social equality and digitalisation.
Sweden has led changes toward greater social equality inter-
nationally (Kent, 2008) and has become an international refer-
ence in this area, despite persisting inequalities (Henning et al.
2023). Women acquired the right to vote in Sweden in 1921.
Between the 1930s and 1960s, Swedish authorities launched
initiatives for granting individuals greater economic indepen-
dence. Buildings like new day-care centres, libraries, and others
were a step toward greater individual freedom and supported this
social change. After the 1960s, public housing and public build-
ings supported further equal opportunities for all members of
society. Sweden also aims to rank among the pioneering states of
digital transformation and AI (Rönnblom et al. 2023; Berman
et al. 2024).
By bridging the knowledge gaps, this research innovatively
analyses key aspects of the cultural context of Stockholm reflected
by AI tools, along with their mismatches and omissions, to
address the implications for social justice and architecture and the
opportunities AI brings.
This study focuses on the possibilities offered by AI to relate to
different cultural contexts through the built environment and its
potential impact on social equality and diversity.
Research materials and methods
Four datasets were developed. Inclusion criteria for the AI sys-
tems tools selected were that they included AI, were widely used,
and could potentially influence how people engage with urban
space. ChatGPT-4o, Midjourney’s bot in Discord, and Google
Maps were used.
ChatGPT is accessible to anyone with an Internet connection
and basic knowledge of how to use a computer or smartphone
and is growing exponentially as a search tool (Raile, 2024).
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5 ARTICLE
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5 3
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Midjourney is a generative AI tool that produces images from
natural language descriptions, called prompts, through a bot on
Discord. Midjourney’s bot can produce photorealistic images or
images in a specific style suggested by the user.
Google Maps is a leader among navigation apps, with six times
more usage than the next most used (Haria et al. 2019) and
billions of users worldwide (Phuangsuwan et al. 2024). Google
Maps has led the way among navigation systems, with user-
friendly advanced technologies, including satellite imagery, aerial
photography, street maps, 360-degree panoramic views, street
view, turn-by-turn instructions, public transit schedules and
retrieving data from users. Google Maps is therefore an assem-
blage of sources of information and technologies in continuous
change (McQuire, 2019).
The scope of this research to examine widely used AI tools and
discuss findings.
The first dataset originated from interacting with ChatGPT-4o
and prompting the following (18 September 2024): ‘List ten places
in Stockholm that reflect the city’s cultural context’. The prompt
was limited to ten bullet points to ensure the consistency of the
data gathered from the prompts. The output obtained with
ChatGPT-4o can thus be compared and analysed (see Table 1).
ChatGPT-4o was then prompted to extend the scope of the
answer: ‘List ten places that reflect the cultural context in
Stockholm city and its suburbs’(see Table 2).
ChatGPT-4o was also prompted ‘Recommend ten top cultural
activities to do in Stockholm’(21 September 2024). Responses
written with ChatGPT-4o were given in the following order: visit
the Vasa Museum, Gamla Stan, the Royal Palace, Nobel Prize
Museum, Skansen Open-Air Museum, Fotografiska, ABBA The
Museum, the City Hall, Moderna Museet, and Millesgården.
When the user identified as a man, output obtained with
ChatGPT-4o listed: Vasa Museum, ABBA The Museum, Viking
Museum, Fotografiska Museum, Gamla Stan Pub Tour, Military
History Museum, Drottningholm Palace, Skansen Open-Air
Museum, Ericsson Globe Skyview and the Nobel Prize
Museum. When the user identified as a woman, the outputs
obtained with ChatGPT-4 listed: The Vasa Museum, Foto-
grafiska, ABBA The Museum, Gamla Stan, Skansen Open-Air
Museum, Rosendals Trädgård, Nordic Museum, Millesgården,
Nobel Prize Museum and Art Galleries in Södermalm.
A second dataset was obtained by interacting with Mid-
journey’s bot (Figs. 1–5). The prompt given to Midjourney’s bot
was: ‘A place in Stockholm that reflects the city’s cultural context’.
Ten prompts to Midjourney’s bot resulted in 40 images.
The third dataset analysed is a map (Fig. 6) created with data
from © Statistics Sweden on the distribution of the population
born in Sweden in 2020, with map lines from © Lantmäteriet. The
map also includes the geographical location of the places obtained
from interacting with ChatGPT-4o from the first dataset as
representing the cultural context. Additionally, the author has
added the locations of the main museums, cultural centres, and
libraries in Stockholm’s city centre and nearby suburbs to the
map. This map shows that the population living in most of
Stockholm is a mixture of nationalities.
The fourth and fifth datasets comprised photographs taken
around Stockholm by the author to illustrate the diversity of
buildings and urban space and to show the places listed in the
interactions with ChatGPT-4o respectively (Figs. 7and 8).
ChatGPT was excluded as a tool for providing routes because the
obtained recommendations were nonsensical. Navigation
research with AI was limited to Google Maps.
ChatGPT and popular venues for visitors
In late 2022, OpenAI, based in San Francisco, California, released
the first public version of ChatGPT (GPT meaning Generative
pre-trained Transformer). The model was then updated to
ChatGPT-4 and GPT-4o, March 2023 and May 2024, respec-
tively. OpenAI (49% is owned by Microsoft) describes itself as ‘an
AI research and deployment company. Our mission is to ensure
that artificial general intelligence benefits all of humanity’
(OpenAI, 2023).
ChatGPT has amazed many: it understands and remembers
interactions with humans, generates text, codes, reasons (Wu et al.
2023), summarises, interacts through voice, and detects emotional
tone. While Open AI has not disclosed the number of parameters
with which they work, estimations point to over 1.8 trillion
Table 1 The following output was generated with ChatGPT-4o when prompted on 18 September 2024 ‘List ten places in
Stockholm that reflect the city’s cultural context’.
Here are ten culturally significant places in Stockholm that reflect the city’s rich history and diverse cultural context
Gamla Stan (Old Town) The historic heart of Stockholm, Gamla Stan is one of the best-preserved medieval city centers in Europe. It features
narrow cobblestone streets, colorful buildings, and landmarks like the Royal Palace and Storkyrkan Cathedral.
Skansen Opened in 1891, Skansen is the world’s oldest open-air museum, showcasing Swedish culture and traditions through
historic buildings, folk art, crafts, and live animals. It offers a glimpse into Sweden’s rural history.
Vasa Museum The Vasa Museum houses the well-preserved 17th-century warship, Vasa, which sank on its maiden voyage in 1628. It’san
iconic symbol of Swedish maritime history and a must-visit for anyone interested in naval history.
ABBA The Museum This museum celebrates the global success of Sweden’s most famous pop group, ABBA. It’sareflection of Sweden’s strong
pop music heritage and its influence on global pop culture.
Moderna Museet Stockholm’s museum of modern and contemporary art, the Moderna Museet, hosts a wide array of works by Swedish and
international artists. It’s a center of Stockholm’s vibrant contemporary art scene.
The City Hall (Stadshuset) Stockholm City Hall is an iconic symbol of the city and a masterpiece of Swedish National Romantic architecture. It’s also
the venue for the annual Nobel Prize banquet.
Fotografiska This museum is dedicated to contemporary photography and has become a cultural hub in Stockholm. Fotografiska
regularly hosts thought-provoking exhibitions and is an important space for modern artistic expression.
Drottningholm Palace A UNESCO World Heritage Site, Drottningholm Palace is the private residence of the Swedish royal family. Its stunning
Baroque architecture and gardens reflect Sweden’s royal history and influence.
The Nobel Prize Museum Located in the heart of Gamla Stan, this museum explores the history and significance of the Nobel Prize, one of Sweden’s
most significant contributions to global intellectual and cultural life.
Södermalm District Once a working-class neighborhood, Södermalm has transformed into a trendy area known for its alternative culture,
independent boutiques, street art, and cultural spaces. It’s a hub for Stockholm’s modern, creative scene.
These places capture the breadth of Stockholm’s cultural, historical, and artistic significance’.
ARTICLE HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5
4HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
(Howarth, 2024). ChatGPT has also concerned many with its
shortcomings, including factual errors, lack of accurate infor-
mation, high computing costs (Wu et al. 2023) and environ-
mental impact (George et al. 2023).
The elements obtained interacting with ChatGPT-4o from the
prompt ‘List ten places in Stockholm that reflect the city’scultural
context’were six museums, the old city centre, the City Hall, the
Royal Palace Drottningholm, and the southern district of Södermalm
(Table 1). These places are all located in the city centre, except for
Drottningholm, which is in the suburbs (Fig. 8). The places listed in
the first interaction with ChatGPT-4o reflected a cultural scene
mainly based on museums in the city centre. Two of the suggested
places are districts, Gamla Stan and Södermalm, and the other places
are buildings or an open-air museum in a group of buildings,
Skansen.
The places listed in the second interaction with ChatGPT-
4o, including the word suburbs in the prompt ‘List ten places
that reflect the cultural context in Stockholm city and suburbs’,
reduced the number of museums to four, and included the old
city centre, Sergel Square, Kulturhuset cultural centre, the
Royal Palace, a botanical garden, a butterfly house, and Tensta
exhibition hall (Table 2). The listed places are primarily
buildings.
The map with geolocated data (Fig. 6) shows a high con-
centration of museums, libraries and exhibition halls in the city
centre. In the suburbs of Stockholm, a broad range of cultural
buildings also enhance education, employment opportunities, and
health care services—libraries like Rinkeby-Kista Bibliotek (2004)
are home to cultural events and exhibitions. The list of places
obtained in the second interaction with ChatGPT-4o correctly
highlights another of these suburban public buildings, Tensta Art
Centre, which reflects Stockholm’s multicultural fabric.
People from around 180 different countries live in Stockholm
(Mahmud, 2013). In the 1950s and 1970s, Sweden needed
workers for its expanding industry, attracting immigrants from
the Nordic and southern European countries. Between the mid-
1970s and 1990s, immigrants came from Chile, Bosnia, and
Somalia (Murdie and Borgegård, 1998). Stockholm has also
attracted many people from different areas of Sweden.
Some of the Stockholm suburbs are home to lower-income
households and a larger population of non-European origin
(Andersson and Bråmå, 2018). Stockholm registers higher seg-
regation and polarisation compared to other European capitals
(Musterd et al. 2017; Haandrikman et al. 2023). Some Swedish
newspapers establish a connection between immigrants and “un-
Swedish values”, framing them as a threat to gender equality and
the welfare system (Norocel et al. 2020, pp. 101–103). In parallel,
Sweden has reduced its immigration policies to meet the Eur-
opean Union minimum, reflecting a broader trend of political
polarisation in Europe (Borbáth et al. 2023).
Therefore, the multicultural nature of Stockholm is broader
than the idea of cultural context obtained from interacting with
ChatGPT-4o. The list of places obtained from the first inter-
action with ChatGPT-4o describes a limited form of culture,
which prioritises buildings, and among them popular museums.
When prompted about places in the city centre and suburbs,
the list obtained with ChatGPT-4o extended the scope of cul-
tural context beyond museums, exhibition centres and popular
districts, to also include a square and two parks. Among the
results obtained with ChatGPT-4o, buildings in the city centre
—many of which are museums with an entrance fee—are pre-
valent and results give a sense of cultural context that is cura-
ted, exhibited, and commercialised. Importantly, the resulting
list of places written with ChatGPT-4o suggested different
places when requested to ‘Recommend ten top cultural activ-
ities to do in Stockholm’, if the user identifies as a man or as
awoman.
If huge numbers of people follow these texts written with
ChatGPT-4o as if they were recommendations, some areas will be
increasingly neglected, whereas others will become more attrac-
tive to visitors and economically powerful and could potentially
decrease diversity.
Table 2 The following output was generated with ChatGPT-4o when prompted on 18 September 2024: ‘List ten places that
reflect the cultural context in Stockholm city and its suburbs’.
Here are ten places in both Stockholm city and its suburbs that reflect the cultural context of the region
In Stockholm City:
Gamla Stan (Old Town) As one of Europe’s most well-preserved medieval centers, this historic core reflects Stockholm’s rich
heritage with its narrow streets, colorful facades, and key landmarks like the Royal Palace.
Skansen The world’s oldest open-air museum, Skansen, showcases Swedish traditions, culture, and rural life through
historical buildings, folk performances, and native animals.
Vasa Museum This museum houses the 17th-century warship Vasa, offering insight into Sweden’s naval history and its
imperial ambitions during the time.
Moderna Museet Stockholm’s leading museum for contemporary art, Moderna Museet highlights both Swedish and
international modern art, making it a central hub for the city’s vibrant art scene.
Sergels Torg and Kulturhuset The bustling plaza of Sergels Torg and the adjacent Kulturhuset (House of Culture) reflect the modern, urban
character of Stockholm, hosting events, exhibitions, and performances in a very contemporary setting.
In Stockholm’s Suburbs:
Drottningholm Palace (Drottningholm) Situated just outside the city, this UNESCO World Heritage Site and royal residence mirrors Sweden’s
monarchical history and Baroque architecture, offering beautifully preserved gardens and a palace theatre.
Millesgården (Lidingö) The home and studio of renowned Swedish sculptor Carl Milles, Millesgården is both an art museum and
sculpture park on the island of Lidingö, showcasing Swedish art and design in a serene, scenic location.
Bergianska Trädgården (Norra
Djurgården)
This botanical garden, located just outside the central city, offers insight into Sweden’s relationship with
nature and botany, featuring diverse plant collections from around the world.
Tensta Konsthall (Tensta) Located in the suburb of Tensta, this contemporary art gallery is a cultural hub that showcases
international and local artists, often focusing on themes of migration, identity, and diversity, reflecting
Stockholm’s multicultural fabric.
Fjärilshuset Haga Trädgård (Solna) A butterfly house and tropical greenhouse in Haga Park, Solna, this location reflects Sweden’s love for
nature, biodiversity, and ecology, making it a relaxing space that connects suburban life with nature.
These places represent the blend of history, contemporary culture, and diverse influences that define both central Stockholm and its surrounding suburbs’.
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5 ARTICLE
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5 5
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Midjourney and the cultural atmosphere
Midjourney Inc., based in San Francisco, California, which
launched its open beta on 12 July 2022, describes itself as:
an independent research lab exploring new mediums of
thought and expanding the imaginative powers of the
human species. We are a small self-funded team focused
on design, human infrastructure, and AI. We have 11
full-time staff and an incredible set of advisers
(Midjourney, 2024).
Midjourney’s bot on Discord is trained to create images with
associated words. The results obtained from Midjourney’s bot
depend heavily on the semantics of the prompts (Tan and
Luhrs, 2024).
To the best of available knowledge, the data used to train
Midjourney’s bot is undisclosed. However, AI is generally trained
on data that has been provided manually, from structured data-
bases, data streams such as sensors, application programming
interfaces that obtain data from other platforms, the Internet, and
through interaction with users (Khan, 2024a).
From the prompt ‘a place in Stockholm that reflects the city’s
cultural context’, the images generated with Midjourney's bot
mostly showed street-level cafes, with wooden furniture, in ochre,
yellow, and grey mortar-rendered buildings, and cobblestone
Fig. 1 The images produced with Midjourney’s bot, representing
Stockholm's cultural context, predominantly feature buildings and
street-level cafes. Images generated with Midjourney’s bot on Discord
from the prompt: ‘a place in Stockholm that reflects the city’s cultural
context’on 21 September 2024, first and second prompts.
Fig. 2 The images produced with Midjourney’s bot, representing
Stockholm's cultural context, predominantly feature buildings and
street-level cafes. Images generated with Midjourney’s bot on Discord
from the prompt: ‘a place in Stockholm that reflects the city’s cultural
context’on 21 September 2024, third and fourth prompts.
ARTICLE HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5
6HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
streets. The images produced with Midjourney’s bot pre-
dominantly and realistically depict cafés (20 out of 40), settings
near water (11 out of 40), a staircase that could be part of an
urban park, and artistic works such as a stained-glass façade,
urban sculptures, and a frescoed vault. One of the images even
resembles one of the colourful grottos that form part of the
subway stations in Stockholm.
The images produced with Midjourney’s bot predominantly
show buildings or other urban design elements, such as water-
fronts or a staircase. Midjourney’s bot’s images also feature fur-
niture and decorative elements, which are important aspects of
culture. These images blend contemporary and 17th-18th-
century-like Stockholm architecture, similar to the old town,
Gamla Stan, with some images featuring water, reflecting the
city’s archipelago setting. Overall, the photos generated with
Midjourney’s bot highlight places like cafes that connect culture
with consumption and economic activity.
A comparison of the author’s photos (Fig. 7) with Midjourney’s
bot-generated images (Figs. 1–5) reveals that the bot’s images
resemble diverse urban areas across Stockholm’s city centre, albeit
without the diversity of Stockholm’s architecture and urban space
built across the centuries. The images obtained with Midjourney’s
bot do not show iconic landmarks like the Royal Palace, Concert
Hall (1926), City Library (1928), Kulturhuset (1974), Vasa
Fig. 3 The images produced with Midjourney’s bot, representing
Stockholm's cultural context, predominantly feature buildings and
street-level cafes. Images generated with Midjourney’s bot on Discord
from the prompt: ‘a place in Stockholm that reflects the city’s cultural
context’on 21 September 2024, fifth and sixth prompts.
Fig. 4 The images produced with Midjourney’s bot, representing
Stockholm's cultural context, predominantly feature buildings and
street-level cafes. Images generated with Midjourney’s bot on Discord
from the prompt: ‘a place in Stockholm that reflects the city’s cultural
context’on 21 September 2024, seventh and eighth prompts.
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5 ARTICLE
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5 7
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Museum (1990), or the new building of Moderna Museet (1998),
nor key places like Sergel Square (1967), urban parks, or Million
Programme housing blocks (1965–1974).
Culture goes beyond architecture. However, Midjourney’s
images overlook other places that reflect other forms of cultural
context like theatre, dance, music, or street markets. Science,
technology and sustainability, still deeply rooted in Stockholm
through its world-famous innovative organizations, are poorly
represented with few contemporary-like constructions. Further-
more, the images obtained with Midjourney’s bot show only
modern or well-maintained architectural settings, omitting other
architectural settings such as housing blocks from the 1950s to
the 1980s.
Google Maps and participative context
Google Maps was launched in 2005. In 2004, Google had
acquired a start-up from Danish-born brothers Lars and Jens
Rasmussen, which targeted rival mapping services of the time
(McQuire, 2019). Google Maps attracted ten million views when
it was launched, providing users with the unprecedented
experience of exploring maps without having to refresh the
image (McQuire, 2019). Google combines its master map with
aerial and satellite imagery and data harvested from users,
combining GPS, sensors, and voluntary online reviews and
conversations (McQuire, 2019).
For Google Maps, providing maps as a service generates
advertising revenue and retrieves user data, which are essential
for keeping the map updated (Heckmann et al. 2022). AI is also
used to recommend information to users based on sophisticated
analysis of their behaviours, including text and images they
have viewed and their drifting interests (Zhang et al. 2021). In
2009, Google began personalised searches aimed at predicting
user preferences (Pariser, 2011). Big Techs usually commer-
cialise user information such as location, preferences, and
searches (Verdegem, 2022). Algorithms that issue recommen-
dations for users are profitable for Big Techs that provide media
content as they maximize the time users engage with their
content (Geschke et al. 2019).
Google Maps uses the A*algorithm to find the shortest path
between two points (Mehta et al. 2019). The A*algorithm is a
search engine used within AI systems, but it does not learn over
time. Already in 2009, Google began personalised searches to
predict user preferences (Pariser, 2011).
Google Maps limits users’queries to date, time, and means of
transport. It does not address many other parameters that could
influence the decision of a route, even though technology is already
able to support considering other person-dependent parameters
(Heckmann et al. 2022). Although Google Maps’suggested routes
are the fastest, other aspects of urban space, such as aesthetics,
sounds, smells, safety, or comfort may be neglected. However,
Google Maps has expanded user knowledge of the urban context
and set up a system whereby anyone with access to the Internet
and technology skills can add information to their map. While
activities of people without access to the Internet might easily be
left out of Google Maps, the platform has been instrumental for
many in learning about, accessing, and engaging with the sur-
rounding urban space, traffic, and activities. Google Maps has
enhanced the visibility of local businesses, facilitated consumer
engagement through reviews, and increased foot traffic, thereby
contributing to economic growth and development (Phuangsuwan
et al. 2024).
Conclusions
The outputs obtained with ChatGPT-4o on cultural context show
a realistic list of venues which are particularly interesting for
visitors to Stockholm. The outputs from Midjourney’s bot are
photorealistic images of places that could well be in Stockholm’s
city centre because of the colours, materials, and atmospheric
light. Google Maps provides accurate information about the city
with multiple views of streets, timing of traffic, public transpor-
tation, and possible routes.
The outputs on cultural context obtained from interaction with
ChatGPT-4o focused on popular venues for visitors, while Mid-
journey focused on cafes, streets, and everyday objects like chairs
and tables, reflecting a cultural context heavily shaped by con-
sumption and commercial interests. The cultural context of
Fig. 5 The images produced with Midjourney’s bot, representing
Stockholm's cultural context, predominantly feature buildings and
street-level cafes. Images generated with Midjourney’s bot on Discord
from the prompt: ‘a place in Stockholm that reflects the city’s cultural
context’on 21 September 2024, ninth and tenth prompts.
ARTICLE HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5
8HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Stockholm, reflected in the places listed with ChatGPT-4o and
represented by Midjourney’s bot, is rather narrow compared to
the city’s extensive multiculturalism. Google Maps also shows
commercial activities, while enabling active participation from
users who can add information to their main map, for example,
their opinions. Therefore, Google Maps reflects a more diverse
cultural context.
Reasons for ChatGPT-4o and Midjourney’sbot’sspecificviews
on cultural context may be shaped by their training data. AI sys-
tems curate datasets, establishing the parameters and hierarchies
for their outputs. If their training data is taken from the Internet
and interactions with users, their output could therefore potentially
overlook the perspectives of those less engaged with the Internet
and these AI tools, including older persons, introverts, privacy-
conscious persons, and those with limited time or lower incomes.
Large amounts of statistical data are processed by a few actors,
while citizens’individual perspectives and preferences become less
relevant (Sareen et al. 2020). Data contributors to these AI tools do
not necessarily represent most societies or their minorities. By
following AI recommendations, people may enhance the opinions
of the majority of data contributors.
Shortcomings of Google Maps’participative map might
include the fact that some users may find it challenging to con-
tribute —senior citizens, people with visual or cognitive dis-
abilities, people lacking time to engage due to demanding work
schedules or personal family commitments, or people who do not
possess updated smartphones. Most educated persons can engage
more easily with information and communication technologies,
while older people avoid sharing online and often show little
interest (Elena-Bucea et al. 2021).
Many are very excited about the short-term impact of AI,
though predicting the long-term societal effects of generative AI is
rather unforeseeable (Sabherwal and Grover, 2024). The outputs
analysed from AI systems have important implications in the
built environment at social, economic, and political levels. AI
systems can:
1. Broaden the understanding of context. AI systems can
augment our knowledge of the urban space we inhabit.
2. Facilitate a deeper insight into prevailing ideas of culture
on the data that train these algorithms. If the Internet
and interactions with users are the data sources of these
AI tools, then these outputs also provide an average
representation of the unfathomable number of images
online and show a substantial Internet bias regarding
culture. If ChatGPT and Midjourney disclosed their data
sources, users could identify potential societal omissions
and neglect of these data, and key concentrations of
power, and further understand the multiple parameters
that describe reality.
Fig. 6 This map of Stockholm shows that the population living in the city is a mixture of nationalities. The places obtained from interacting with
ChatGPT, which reflect the cultural context of Stockholm, are mostly located in the city centre. Actually, there are more landmark museums, cultural
centres, and libraries (represented with blue stars) in and around Stockholm city centre than in the suburbs. Map 1:100 000 with vector data on the
property map, the overview map, and place names (fastighetskartan, översiktskartan, ortnamn) from © Lantmäteriet. Source of distribution of population
born in Sweden in 2020 © Statistics Sweden. Source of location of museums, cultural centres, and libraries: Ingrid Campo-Ruiz. Source of location of the
places suggested during interaction with ChatGPT-4o: Ingrid Campo-Ruiz.
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5 ARTICLE
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5 9
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
3. Redefine culture. The output analysed from interactions
with ChatGPT-4o and Midjourney’s bot privileges perspec-
tives on a culture that enhances buildings, mainly museums
or cafes, economic and consumption perspectives over
other activities that are also part of local culture.
4. Jeopardise cultural diversity that represents different
members of society. The outputs from interactions with
AI show only a limited aspect of the city’s complex cultural
diversity, prioritising buildings, museums, and cafes as
“cultural”over others and conveying a sense of cultural
context that is curated, exhibited, and commercialised.
These outputs could redefine people’s ideas on culture, by
disseminating ideologies about what culture is, empowering
certain perspectives, neglecting other views, and decreasing
diversity. Furthermore, rendering more visibility to few
commercial buildings would contribute to the increasing
commercialisation of cultural space in the city and
inequalities (Campo-Ruiz, 2024).
Fig. 7 Photographs taken by Ingrid Campo-Ruiz that exemplify the
diversity of urban areas throughout Stockholm's city centre. Photos of
different urban settings in Stockholm city centre: aStockholm City Library,
bSubway station Stadion, cStockholm Woodland Cemetery, dFilmhuset,
eKTH Royal Institute of Technology, fLadugårdsgärdet Park,
gSkeppsholms Bridge, hStadion (photographer: Ingrid Campo-Ruiz).
People in the photographs have been blurred using Photoshop to protect
their privacy in compliance with GDPR.
Fig. 8 Photographs taken by Ingrid Campo-Ruiz of places in Stockholm
that reflect the cultural context, as described with ChatGPT-4. Photos of
places in Stockholm that reflect the cultural context as listed in the outputs
frominteractionwithChatGPT-4oon18September2024:aGamla Stan,
bSkansen, cVasa Museum, dABBA The Museum, eModerna Museet, fThe
City Hall, gFotografiska, hDrottningholm Palace (photographer: Ingrid
Campo-Ruiz). People in the photographs have been blurred using Photoshop
to protect their privacy in compliance with GDPR.
ARTICLE HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5
10 HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
5. Exacerbate power relationships in the built environment that
perpetuate a limited set of ideas. The places obtained in the
interactions with ChatGPT-4o and Midjourney’sbotthat
reflect the cultural context in Stockholm predominantly benefit
a few organisations while disregarding other forms of cultural
expression, potentially increasing inequalities. Those excluded
from the conversation might feel even more disengaged.
Neocolonialism has been described as a way to control a
territory and influence its people, with psychological domina-
tion and the denigration of local values (Flikschuh et al. 2015).
From this perspective, some AI tools could contribute to
establishing forms of urban space control limited to a few
powerful actors, enhancing their interests, increasing the
vulnerability of some, and multiplying inequalities.
6. Enhance segregation. The outputs obtained with ChatGPT-
4o on cultural context are mostly located in the city centre,
while Midjourney’s images also resemble places in Stock-
holm city centre, risking becoming yet another factor
perpetuating segregation.
These findings highlight how AI is triggering rearrangements
of social relationships and information pathways and trans-
forming urban space from the perspective of urban environment
and societal equality, by contributing an innovative and com-
plementary view of the influence of AI in the urban context.
Urban analysis has included multiple technologies like robots and
self-driving cars that affect the built environment (Cugurullo et al.
2023). Generative AI, which is rapidly expanding, also plays a key
role alongside other AI systems. While generative AI may not
manage cities autonomously, it will significantly influence deci-
sions concerning engaging and understanding urban space.
Governments should avoid introducing further risks, such as
discrimination and power imbalances, when implementing AI
systems, by adhering to principles of equality, freedom, and
human rights, while ensuring citizen involvement and open
access to information (Duberry, 2022).
In light of these findings, the following actions are proposed to
engage with AI for greater social justice through architecture:
1. Public organisations should promote further public discus-
sion and research about these AI tools and their implica-
tions for people through the places they inhabit. Some of
the abovementioned risks of narrowly redefining cultural
context through AI tools could promote inequalities and
segregation, challenging democratic and social justice
principles in public space.
2. Public organisations should raise awareness of the limita-
tions of some AI systems, which may neglect important
aspects that shape the cultural context of a place. Many
users constantly feed algorithms with their interactions and
the data they upload, including comments, photos,
purchases, and searches. Public authorities should empower
users to critically consider who they are supporting and
neglecting by following AI outputs.
3. Public organisations should facilitate users to combine AI
outputs with other tools and knowledge such as humanistic,
social, and ethical values. AI should not be the sole source
of information about the world we live in.
4. The providers of AI systems should ensure more inclusivity
in the data used to train their models and in the way they
are trained, to achieve more nuanced outputs. In research,
all data bear some degree of bias, and researchers are the
curators of the information they manage. The same should
apply to AI systems in the built environment because
developers are responsible for curating data. AI and users
exert reciprocal influence on each other, though users have
less power in general (Airoldi and Rokka, 2022).
5. The providers of AI systems should disclose the
limitations of their training data, users and the rest of
society would better understand and address AI
output bias.
6. All those who have the agency, skills, and time to use AI
should help others interact with AI tools critically,
understanding that not all texts are true, not all images
are representative, and not all recommendations serve
one’s best interests. While some research suggests that
users change behaviours to avoid becoming victims
(Zhang and Hu, 2023), many persons lack the agency,
tools, time, or skills to be active players in shaping AI. AI
systems can be valuable tools but are not accessible to
everyone. Users can be activists to use AI for the greater
good and to have a positive impact on the places they
live in.
One limitation of this research is that the datasets refer to only
one city as a case study. Further research is needed to determine
broader, worldwide implications.
In conclusion, although AI has been around for decades, a new
era is now beginning. A seismic revolution is taking place through
interaction with AI systems, which have been made widely
available and usable to many more people than only a few years
ago. AI systems can aid in understanding of the complexities of
the urban environment by helping users analyse quantities of data
that are unfathomable to the human mind. The shortcomings of
the generative AI models analysed could be considered reason-
able: these tools are recent, yet can still provide jaw-dropping
results. Despite the current potential reduction of cultural context
diversity, AI providers have a unique opportunity to produce
more nuanced outputs, which promote more societal diversity
and equality. AI systems have a huge opportunity to make the
world a better place, but some organisations have more power
and responsibility than other members of society.
Data availability
The datasets generated during the current study are included in
the article. ChatGPT-4o is available at https://chat.openai.com/,
Midjourney’s bot at https://discord.com/channels and the web-
sites and apps have been referenced.
Received: 16 August 2023; Accepted: 16 October 2024;
References
Adobor H (2021) Open strategy: what is the impact of national culture? Manag Res
Rev. 44:1277–1297. https://doi.org/10.1108/MRR-06-2020-0334
Airoldi M, Rokka J (2022) Algorithmic consumer culture. Consum Mark. Cult.
25:411–428. https://doi.org/10.1080/10253866.2022.2084726
Ali T, Marc B, Omar B et al. (2021) Exploring destination’s negative e-reputation
using aspect-based sentiment analysis approach: case of Marrakech destina-
tion on TripAdvisor. Tour. Manag Perspect. 40:100892. https://doi.org/10.
1016/j.tmp.2021.100892
Andersson R, Bråmå Å (2018) The Stockholm estates: a tale of the importance of
initial conditions, macroeconomic dependencies, tenure and immigration. In:
Hess D, Tammaru T, van Ham M (eds.) Housing estates in Europe, 1st edn.
Springer, Cham, p 361–388
Anon (2023) How to worry wisely about artificial intelligence. The Economist.
https://www.economist.com/leaders/2023/04/20/how-to-worry-wisely-about-
artificial-intelligence
Berman A, de Fine Licht K, Carlsson V (2024) Trustworthy AI in the public sector:
an empirical analysis of a Swedish labor market decision-support system.
Technol. Soc. 76:102471. https://doi.org/10.1016/j.techsoc.2024.102471
Bircan T, Korkmaz EE (2021) Big data for whose sake? Governing migration
through artificial intelligence. Humanit Soc. Sci. Commun. 8:1–5. https://doi.
org/10.1057/s41599-021-00910-x
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5 ARTICLE
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5 11
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Borbáth E, Hutter S, Leininger A (2023) Cleavage politics, polarisation and par-
ticipation in Western Europe. West Eur. Polit. 0:1–21. https://doi.org/10.
1080/01402382.2022.2161786
Bozdag E (2013) Bias in algorithmic filtering and personalization. Ethics Inf
Technol 15:209–227. https://doi.org/10.1007/s10676-013-9321-6
Bratton B (2021) AI urbanism: a design framework for governance, program, and
platform cognition. AI Soc. 36:1307–1312. https://doi.org/10.1007/s00146-
020-01121-9
Cachat-Rosset G, Klarsfeld A (2023) Diversity, equity, and inclusion in Artificial
Intelligence: An evaluation of guidelines. Appl Artif Intell 37. https://doi.org/
10.1080/08839514.2023.2176618
Campo-Ruiz I (2024) Economic powers encompass the largest cultural buildings:
market, culture and equality in Stockholm, Sweden (1918–2023). ArchNet-
IJAR. https://doi.org/10.1108/ARCH-06-2023-0160
Churchland PM, Churchland PS (1990) Could a machine think? Sci. Am. Assoc.
Adv. Sci. 262:32–39
Crawford K (2021) Atlas of AI: power, politics, and the planetary costs of artificial
intelligence. Yale University Press, New Haven
Cugurullo F (2021) Frankenstein urbanism: eco, smart and autonomous cities,
artificial intelligence and the end of the city. Routledge, Taylor & Francis
Group, London
Cugurullo F, Caprotti F, Cook M et al. (2024) The rise of AI urbanism in post-
smart cities: a critical commentary on urban artificial intelligence. Urban
Stud. 61:1168–1182. https://doi.org/10.1177/00420980231203386
Cugurullo F (2020) Urban artificial intelligence: from automation to autonomy in
the smart city. Front Sustain Cities 2. https://doi.org/10.3389/frsc.2020.00038
Cugurullo F, Caprotti F, Cook M, Karvonen A, McGuirk P, Marvin S (eds.) (2023)
Artificial intelligence and the city: urbanistic perspectives on AI, 1st edn.
Taylor & Francis, London
Dervin F (2023) The paradoxes of interculturality: a toolbox of out-of-the-box
ideas for intercultural communication education. Routledge, New York
Dreyfus HL, Dreyfus SE (1988) Making a mind versus modeling the brain: Arti-
ficial Intelligence back at a branchpoint. Daedalus Camb. Mass 117:15–43
Duberry J (2022) Artificial Intelligence and democracy: risks and promises of AI-
mediated citizen-government relations. Edward Elgar Publishing, Northampton
Elena-Bucea A, Cruz-Jesus F, Oliveira T, Coelho PS (2021) Assessing the role of
age, education, gender and income on the digital divide: evidence for the
European Union. Inf. Syst. Front 23:1007–1021. https://doi.org/10.1007/
s10796-020-10012-9
Elliott A (2018) The Culture of AI: everyday life and the digital revolution, 1st edn.
Routledge, Milton
von Eschenbach WJ (2021) Transparency and the black box problem: why we do
not trust AI. Philos. Technol. 34:1607–1622. https://doi.org/10.1007/s13347-
021-00477-0
European Parliament and the Council of the European Union (2024) Regulation
(EU) 2024/1689 of the European Parliament and of the Council of 13 June
2024 laying down harmonised rules on artificial intelligence and amending
Regulations (EC) No 300/2008, (EU) No 167/2013, (EU) No 168/2013, (EU)
2018/858, (EU) 2018/1139 and (EU) 2019/2144 and Directives 2014/90/EU,
(EU) 2016/797 and (EU) 2020/1828 (Artificial Intelligence Act). https://eur-
lex.europa.eu/eli/reg/2024/1689/oj. Accessed 20 Sep 2024
Flikschuh K, Ypi L, Ajei M (2015) Kant and colonialism: historical and critical
perspectives. University Press, Oxford
Forty A (2000) Words and buildings: a vocabulary of modern architecture. Thames
& Hudson, London
Fosch-Villaronga E, Poulsen A (2022) Diversity and inclusion in Artificial Intel-
ligence. In: Custers B, Fosch-Villaronga E (eds) Law and Artificial Intelli-
gence: regulating AI and applying AI in legal practice. T.M.C. Asser Press,
The Hague, p 109–134
Future of Life Institute (2023) Pause giant AI experiments: an open letter. In:
Future Life Inst. https://futureoflife.org/open-letter/pause-giant-ai-
experiments/. Accessed 3 Sep 2024
George AS, George ASH, Martin ASG (2023) The environmental impact of AI: a
case study of water consumption by Chat GPT. Part. Univers Int Innov. J.
1:97–104. https://doi.org/10.5281/zenodo.7855594
Geschke D, Lorenz J, Holtz P (2019) The triple-filter bubble: Using agent-based
modelling to test a meta-theoretical framework for the emergence of filter
bubbles and echo chambers. Br. J. Soc. Psychol. 58:129–149. https://doi.org/
10.1111/bjso.12286
Gupta R, Nair K, Mishra M et al. (2024) Adoption and impacts of generative
artificial intelligence: theoretical underpinnings and research agenda. Int J.
Inf. Manag Data Insights 4:100232. https://doi.org/10.1016/j.jjimei.2024.
100232
Haandrikman K, Costa R, Malmberg B et al. (2023) Socio-economic segregation in
European cities. A comparative study of Brussels, Copenhagen, Amsterdam,
Oslo and Stockholm. Urban Geogr. 44:1–36. https://doi.org/10.1080/
02723638.2021.1959778
Haria V, Shah Y, Gangwar V et al. (2019) The working of Google Maps, and the
commercial usage of navigation systems. IJIRT 6:184–191
Heckmann R, Kock S, Gaspers L (2022) Artificial intelligence supporting sus-
tainable and individual mobility: development of an algorithm for mobility
planning and choice of means of transport. In: Coors V, Pietruschka D,
Zeitler B (eds) iCity. Transformative research for the livable, intelligent, and
sustainable city. Springer International Publishing, Stuttgart, p 27–40
Henning M, Westlund H, Enflo K (2023) Urban–rural population changes and
spatial inequalities in Sweden. Reg. Sci. Policy Pr. 15:878–892. https://doi.org/
10.1111/rsp3.12602
Howarth J (2024) Number of parameters in GPT-4 (Latest Data). https://
explodingtopics.com/blog/gpt-parameters. Accessed 8 Sep 2024
Howe B, Brown JM, Han B, Herman B, Weber N, Yan A, Yang S, Yang Y (2022)
Integrative urban AI to expand coverage, access, and equity of urban data.
Eur. Phys. J. Spec. Top. 231:1741–1752. https://doi.org/10.1140/epjs/s11734-
022-00475-z
Jang KM, Chen J, Kang Y, Kim J, Lee J, Duarte F (2023) Understanding place
identity with generative AI. Leibniz International Proceedings in Informatics,
Leibniz, pp 1–6
Kent N (2008) A concise history of Sweden. Cambridge University Press,
Cambridge
Khan I (2024a) The quick guide to prompt engineering. John Wiley & Sons,
Newark
Khan S (2024b) Cultural diversity and social cohesion: perspectives from social
science. Phys. Educ. Health Soc. Sci. 2:40–48
Lo Piano S (2020) Ethical principles in machine learning and artificial intelligence:
cases from the field and possible ways forward. Humanit Soc Sci Commun
7:1–7. https://doi.org/10.1057/s41599-020-0501-9
Luusua A, Ylipulli J, Foth M, Aurigi A (2023) Urban AI: understanding the
emerging role of artificial intelligence in smart cities. AI Soc. 38:1039–1044.
https://doi.org/10.1007/s00146-022-01537-5
Lyu Y, Lu H, Lee MK, Schmitt G, Lim B (2024) IF-City: intelligible fair city
planning to measure, explain and mitigate inequality. IEEE Trans. Vis.
Comput Graph 30:3749–3766. https://doi.org/10.1109/TVCG.2023.3239909
Macrorie R, Marvin S, While A (2021) Robotics and automation in the city: a
research agenda. Urban Geogr. 42(2):197–217
Mahmud HJA (2013) Social cohesion in multicultural society: a case of Bangladeshi
immigrants in Stockholm. Dissertation, Stockholm University
Marion G (2017) How Culture Affects Language and Dialogue. In: The Routledge
Handbook of Language and Dialogue. Routledge, London
McNealy JE (2021) Framing and language of ethics: technology, persuasion, and
cultural context. J. Soc. Comput 2:226–237. https://doi.org/10.23919/JSC.
2021.0027
McQuire S (2019) One map to rule them all? Google Maps as digital technical object.
Commun. Public 4:150–165. https://doi.org/10.1177/2057047319850192
Mehta H, Kanani P, Lande P (2019) Google Maps. Int J. Comput. Appl 178:41–46.
https://doi.org/10.5120/ijca2019918791
Midjourney (2024) About. www.midjourney.com/home. Accessed 23 Oct 2024
Mironenko IA, Sorokin PS (2018) Seeking for the definition of “culture”: current
concerns and their implications. a comment on Gustav Jahoda’s article
“Critical reflections on some recent definitions of “culture’”. Integr. Psychol.
Behav. Sci. 52:331–340. https://doi.org/10.1007/s12124-018-9425-y
Mozur P (2017) Beijing wants A.I. to be made in China by 2030. N. Y. Times.
https://www.nytimes.com/2017/07/20/business/china-artificial-intelligence.
html
Murdie RA, Borgegård L-E (1998) Immigration, spatial segregation and housing
segmentation of immigrants in metropolitan Stockholm, 1960-95. Urban
Stud. Edinb. Scotl. 35:1869–1888. https://doi.org/10.1080/0042098984196
Musterd S, Marcińczak S, van Ham M, Tammaru T (2017) Socioeconomic segre-
gation in European capital cities. Increasing separation between poor and rich.
Urban Geogr. 38:1062–1083. https://doi.org/10.1080/02723638.2016.1228371
Newell A, Simon HA (1976) Computer science as empirical inquiry: symbols and
search. Commun. ACM 19:113–126. https://doi.org/10.1145/360018.360022
Norocel OC, Hellström A, Jørgensen MB (2020) Nostalgia and hope: intersections
between politics of culture, welfare, and migration in Europe, 1st edn.
Springer International Publishing, Cham
OECD (2019) Artificial Intelligence in Society. OECD Publishing, Paris. https://doi.
org/10.1787/eedfee77-en. Accessed 23 Oct 2024
OpenAI (2023) https://openai.com/about. Accessed 20 Sep 2024
Palmini O, Cugurullo F (2023) Charting AI urbanism: conceptual sources and
spatial implications of urban artificial intelligence. Discov Artif Intell 3.
https://doi.org/10.1007/s44163-023-00060-w
Pariser E (2011) The filter bubble: what the Internet is hiding from you. Viking,
London
Parker PD, Van Zanden B, Marsh HW, Owen K, Duineveld J, Noetel M (2020) The
intersection of gender, social class, and cultural context: a meta-analysis.
Educ. Psychol. Rev. 32:197–228. https://doi.org/10.1007/s10648-019-09493-1
ARTICLE HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5
12 HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
Peng J, Strijker D, Wu Q (2020) Place identity: how far have we come in exploring
its meanings? Front Psychol 11. https://doi.org/10.3389/fpsyg.2020.00294
Peng Z-R, Lu K-F, Liu Y, Zhai W (2023) The pathway of urban planning AI: from
planning support to plan-making. J Plan Educ Res 0. https://doi.org/10.1177/
0739456X231180568
Phuangsuwan P, Siripipatthanakul S, Limna P, Pariwongkhuntorn N (2024) The
impact of Google Maps application on the digital economy. Corp. Bus.
Strategy Rev. 5:192–203. https://doi.org/10.22495/cbsrv5i1art18
Popelka S, Narvaez Zertuche L, Beroche H (2023) Urban AI guide. Urban AI.
https://urbanai.fr/
Prabhakaran V, Qadri R, Hutchinson B (2022) Cultural incongruencies in Artificial
Intelligence. ArXiv Cornell Univ. https://doi.org/10.48550/arxiv.2211.13069
Raile P (2024) The usefulness of ChatGPT for psychotherapists and patients. Humanit
Soc. Sci. Commun. 11:47–48. https://doi.org/10.1057/s41599-023-02567-0
Rhodes SC (2022) Filter bubbles, echo chambers, and fake news: How social media
conditions individuals to be less critical of political misinformation. Polit
Commun 39:1–22. https://doi.org/10.1080/10584609.2021.1910887
Robertson RE, Green J, Ruck DJ, et al. (2023) Users choose to engage with more
partisan news than they are exposed to on Google Search. Nature
618:342–348. https://doi.org/10.1038/s41586-023-06078-5
Rönnblom M, Carlsson V, Öjehag‐Pettersson A (2023) Gender equality in Swedish
AI policies. What’s the problem represented to be? Rev. Policy Res
40:688–704. https://doi.org/10.1111/ropr.12547
Sabherwal R, Grover V (2024) The societal impacts of generative Artificial Intel-
ligence: a balanced perspective. J. Assoc. Inf. Syst. 25:13–22. https://doi.org/
10.17705/1jais.00860
Sanchez TW, Shumway H, Gordner T, Lim T (2023) The prospects of Artificial
Intelligence in urban planning. Int J. Urban Sci. 27:179–194. https://doi.org/
10.1080/12265934.2022.2102538
Sareen S, Saltelli A, Rommetveit K (2020) Ethics of quantification: illumination,
obfuscation and performative legitimation. Palgrave Commun 6. https://doi.
org/10.1057/s41599-020-0396-5
Searle J (1980) Minds, brains and programs. In: Collins A, Smith EE (eds) Readings
in Cognitive Science. Morgan Kaufmann, San Mateo, p 20–31
Sherman S (2023) The polyopticon: a diagram for urban Artificial Intelligences. AI
Soc. 38:1209–1222. https://doi.org/10.1007/s00146-022-01501-3
Sloan RH, Warner R (2020) Beyond bias: Artificial Intelligence and social justice.
Va J. Law Technol. 24:1
Son TH, Weedon Z, Yigitcanlar T et al. (2023) Algorithmic urban planning for
smart and sustainable development: Systematic review of the literature.
Sustain Cities Soc. 94:104562. https://doi.org/10.1016/j.scs.2023.104562
Sun J, Song J, Jiang Y, et al. (2022) Prick the filter bubble: A novel cross domain
recommendation model with adaptive diversity regularization. Electron Mark
32:101–121. https://doi.org/10.1007/s12525-021-00492-1
Tan L, Luhrs M (2024) Using generative AI Midjourney to enhance divergent and
convergent thinking in an architect’s creative design process. Des. J.
27:677–699. https://doi.org/10.1080/14606925.2024.2353479
Tseng Y-S (2023) Assemblage thinking as a methodology for studying urban AI
phenomena. AI Soc. 38:1099–1110. https://doi.org/10.1007/s00146-022-
01500-4
Ullah Z, Al-Turjman F, Mostarda L, Gagliardi R (2020) Applications of Artificial
Intelligence and Machine Learning in smart cities. Comput Commun.
154:313–323. https://doi.org/10.1016/j.comcom.2020.02.069
Verdegem P (2022) Dismantling AI capitalism: the commons as an alternative to
the power concentration of Big Tech. AI Soc 1–11. https://doi.org/10.1007/
s00146-022-01437-8
Weizenbaum J (1984) Computer power and human reason: from judgment to
calculation. Penguin, Harmondsworth
Wu T, He S, Liu J et al. (2023) A brief overview of ChatGPT: The history, status
quo and potential future development. IEEECAA J. Autom. Sin. 10:
1122–1136. https://doi.org/10.1109/JAS.2023.123618
Yigitcanlar T, Corchado JM, Mehmood R, Li RYM, Mossberger K, Desouza KC
(2021) Responsible urban innovation with local government Artificial Intel-
ligence (AI): A conceptual framework and research agenda. J. Open Innov.
7:1–16. https://doi.org/10.3390/joitmc7010071
Zhang Q, Lu J, Jin Y (2021) Artificial Intelligence in recommender systems.
Complex Intell. Syst. 7:439–457. https://doi.org/10.1007/s40747-020-00212-w
Zhang J, Hu C (2023) Adaptive algorithms: users must be more vigilant. Nat Lond
618:907–907. https://doi.org/10.1038/d41586-023-02033-6
Acknowledgements
This project has received funding from the European Union’s Horizon 2020 Research
and Innovation Programme under the European Commission Marie Skłodowska-Curie
Actions Individual Fellowship Grant Number 101032687 —EQUBUILD.
Competing interests
The author declares no competing interests.
Ethical approval
This article contains no studies with human participants undertaken by the author.
Informed consent
This article contains no studies with human participants undertaken by any of the
authors.
Additional information
Correspondence and requests for materials should be addressed to Ingrid Campo-Ruiz.
Reprints and permission information is available at http://www.nature.com/reprints
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in
published maps and institutional affiliations.
Open Access This article is licensed under a Creative Commons
Attribution-NonCommercial-NoDerivatives 4.0 International License,
which permits any non-commercial use, sharing, distribution and reproduction in any
medium or format, as long as you give appropriate credit to the original author(s) and
the source, provide a link to the Creative Commons licence, and indicate if you modified
the licensed material. You do not have permission under this licence to share adapted
material derived from this article or parts of it. The images or other third party material
in this article are included in the article’s Creative Commons licence, unless indicated
otherwise in a credit line to the material. If material is not included in the article’s
Creative Commons licence and your intended use is not permitted by statutory
regulation or exceeds the permitted use, you will need to obtain permission directly from
the copyright holder. To view a copy of this licence, visit http://creativecommons.org/
licenses/by-nc-nd/4.0/.
© The Author(s) 2024
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | https://doi.org/10.1057/s41599-024-03968-5 ARTICLE
HUMANITIES AND SOCIAL SCIENCES COMMUNICATIONS | (2025) 12:24 | https://doi.org/10.1057/s41599-024-03968-5 13
Content courtesy of Springer Nature, terms of use apply. Rights reserved.
1.
2.
3.
4.
5.
6.
Terms and Conditions
Springer Nature journal content, brought to you courtesy of Springer Nature Customer Service Center GmbH (“Springer Nature”).
Springer Nature supports a reasonable amount of sharing of research papers by authors, subscribers and authorised users (“Users”), for small-
scale personal, non-commercial use provided that all copyright, trade and service marks and other proprietary notices are maintained. By
accessing, sharing, receiving or otherwise using the Springer Nature journal content you agree to these terms of use (“Terms”). For these
purposes, Springer Nature considers academic use (by researchers and students) to be non-commercial.
These Terms are supplementary and will apply in addition to any applicable website terms and conditions, a relevant site licence or a personal
subscription. These Terms will prevail over any conflict or ambiguity with regards to the relevant terms, a site licence or a personal subscription
(to the extent of the conflict or ambiguity only). For Creative Commons-licensed articles, the terms of the Creative Commons license used will
apply.
We collect and use personal data to provide access to the Springer Nature journal content. We may also use these personal data internally within
ResearchGate and Springer Nature and as agreed share it, in an anonymised way, for purposes of tracking, analysis and reporting. We will not
otherwise disclose your personal data outside the ResearchGate or the Springer Nature group of companies unless we have your permission as
detailed in the Privacy Policy.
While Users may use the Springer Nature journal content for small scale, personal non-commercial use, it is important to note that Users may
not:
use such content for the purpose of providing other users with access on a regular or large scale basis or as a means to circumvent access
control;
use such content where to do so would be considered a criminal or statutory offence in any jurisdiction, or gives rise to civil liability, or is
otherwise unlawful;
falsely or misleadingly imply or suggest endorsement, approval , sponsorship, or association unless explicitly agreed to by Springer Nature in
writing;
use bots or other automated methods to access the content or redirect messages
override any security feature or exclusionary protocol; or
share the content in order to create substitute for Springer Nature products or services or a systematic database of Springer Nature journal
content.
In line with the restriction against commercial use, Springer Nature does not permit the creation of a product or service that creates revenue,
royalties, rent or income from our content or its inclusion as part of a paid for service or for other commercial gain. Springer Nature journal
content cannot be used for inter-library loans and librarians may not upload Springer Nature journal content on a large scale into their, or any
other, institutional repository.
These terms of use are reviewed regularly and may be amended at any time. Springer Nature is not obligated to publish any information or
content on this website and may remove it or features or functionality at our sole discretion, at any time with or without notice. Springer Nature
may revoke this licence to you at any time and remove access to any copies of the Springer Nature journal content which have been saved.
To the fullest extent permitted by law, Springer Nature makes no warranties, representations or guarantees to Users, either express or implied
with respect to the Springer nature journal content and all parties disclaim and waive any implied warranties or warranties imposed by law,
including merchantability or fitness for any particular purpose.
Please note that these rights do not automatically extend to content, data or other material published by Springer Nature that may be licensed
from third parties.
If you would like to use or distribute our Springer Nature journal content to a wider audience or on a regular basis or in any other manner not
expressly permitted by these Terms, please contact Springer Nature at
onlineservice@springernature.com
Available via license: CC BY-NC-ND 4.0
Content may be subject to copyright.