This study proposes a novel approach to social analysis through social media data and generative artificial intelligence (GAI). To demonstrate its practical application, we examine the relationship between visitor perceptions and the amenity mix of urban places, specifically Internet Famous Sites (IFSs). Social media data of 50 IFS across 26 Chinese cities were collected from platforms such as Ctrip and Rednote. Using GPT-4 as the semantic analysis model alongside prompt engineering techniques, we identified the perceived thematic characteristics of these IFS. Additionally, Points of Interest (POI) data were utilized to calculate the amenity mix, reflecting the actual thematic characteristics of the sites. The study tests four hypotheses: the perceptibility of themes, the correlation between visitor perceptions and the amenity mix, the disparity between perceived themes, and the correlation between different theme perceptions. The results demonstrate that the themes of IFS are highly perceptible and diverse, closely linked to the amenity mix. Significant disparities in theme perception were observed within the same site, and evidence of synergistic or competitive relationships between themes at the same site was also identified. This innovative method enhances the efficiency of social sensing, particularly in capturing visitor perceptions of places. By providing a nuanced understanding of visitor perceptions and their relationship to the amenity mix, this approach offers valuable insights for planners, enabling more informed decision-making and practical guidance for optimization and management of these sites.
AdhyaA. (2012) Jane Jacobs and the theory of placemaking in debates of sustainable urbanism.The urban wisdom of Jane Jacobs, 215–228.
3.
Al AsadMAImranHMAlaminM, et al. (2023) Sentiment and interest detection in social media using gpt-based large language models. In: Proceedings of the 2023 6th international conference on machine learning and natural language processing, Sanya, China, 27 - 29 December 2023, 209–214.
4.
AlaimoCKallinikosJ (2017) Computing the everyday: social media as data platforms. The Information Society33: 175–191.
5.
AmirzadehMSharifiA (2024) The evolutionary path of place making: from late twentieth century to post-pandemic cities. Land Use Policy141: 107124.
6.
Balsa-BarreiroJCebriánMMenéndezM, et al. (2024) Leveraging generative AI models in urban science. Current Topics in Behavioral Neurosciences68: 239–275.
7.
BibriSE (2021) Data-driven smart sustainable cities of the future: urban computing and intelligence for strategic, short-term, and joined-up planning. Computational Urban Science1(8): 8.
8.
BrownTMannBRyderN, et al. (2020) Language models are few-shot learners. Advances in Neural Information Processing Systems33: 1877–1901.
9.
BurmanEHansboPLarsonMG, et al. (2023) Extension operators for trimmed spline spaces. Computer Methods in Applied Mechanics and Engineering403: 115707.
10.
CarmonaM. (2021) Public places urban spaces: The dimensions of urban design (pp. 110–115, 200–203). Routledge.
11.
ChenCMaJSusiloY, et al. (2016) The promises of big data and small data for travel behavior (aka human mobility) analysis. Transportation Research Part C: Emerging Technologies68: 285–299.
12.
ChinWCBFuYLimKH, et al. (2023) Identifying urban functional zones by analysing the spatial distribution of amenities. Environment and Planning B: Urban Analytics and City Science51(6): 1274–1289.
13.
DupreK (2018) Trends and gaps in place-making in the context of urban development and tourism: 25 years of literature review (2018). Journal of Place Management and Development12: 102–120.
14.
DwivediYKIsmagilovaEHughesDL, et al. (2021) Setting the future of digital and social media marketing research: perspectives and research propositions. International Journal of Information Management59: 102168.
15.
GalesicMOlssonH (2021) Human social sensing is an untapped resource for computational social science. Nature Human Behaviour5: 159–167.
16.
GuoWZhouSZhangM, et al. (2024) The digital practice of internet-famous sites and the production of new spatial forms. Tropical Geography44(9): 1527–1548.
17.
HidalgoCACastañerESevtsukA (2020) The amenity mix of urban neighborhoods. Habitat International106: 102205.
18.
HuangQCaoGWangC (2014) From where do tweets originate? a GIS approach for user location inference. In Proceedings of the 7th ACM SIGSPATIAL international workshop on location-based social networks (pp. 1-8). ACM.
19.
HuangYZhengB (2024) Social media users’ visual and emotional preferences of internet-famous sites in urban riverfront public spaces: a case study in Changsha, China. Land13(7): 930.
20.
JiaJZhangXZhangW (2025) Between place attachment and urban planning in Jinan: does environmental quality affect human perception in a developing country context?Land Use Policy148: 107384.
21.
JiangYChaoQChenY, et al. (2024) UrbanLLM: autonomous urban activity planning and management with large language models [Preprint]. arXiv. https://arxiv.org/abs/2406.12360
22.
JiangHLiMWitteP, et al. (2025) Urban chatter: exploring the potential of ChatGPT-like and generative AI in enhancing planning support. Cities158: 105701.
23.
JuhászSPintérGKovácsÁJ, et al. (2023) Amenity complexity and urban locations of socio-economic mixing. EPJ Data Science12(1): 34.
24.
KaddariZMellahYBerrichJ, et al. (2021) Natural Language processing: challenges and future directions. In: Lecture Notes in Networks and Systems. Switzerland: Springer Nature Switzerland AG, 236.
25.
KalayYE (2006) The impact of information technology on design methods, products and practices. Design Studies27(3): 357–380.
26.
KharlamovAAPilgunMA (2024) Cognitive studies in the interpretation of social media data: TextAnalyst and ChatGPT. Pattern Recognition and Image Analysis34(3): 597–609.
27.
KontokostaCEFreemanLLaiY (2024) Up-and-Coming or down-and-out? Social media popularity as an indicator of neighborhood change. Journal of Planning Education and Research44(2): 662–673.
28.
LaiYKontokostaCE (2019) Topic modeling to discover the thematic structure and spatial-temporal patterns of building renovation and adaptive reuse in cities. Computers, Environment and Urban Systems78: 101383.
29.
LiHWeiYDWuY (2019) Urban amenity, human capital and employment distribution in Shanghai. Habitat International91: 102025.
30.
LiangHZhuJJH (2017) Big data, collection of (social media, harvesting). In: MatthesJ. (ed). The International Encyclopedia of Communication Research Methods. Wiley. doi: 10.1002/9781118901731.iecrm0015
31.
LiangHXueXZhangY, et al. (2018) Urban informatics: the role of citizen engagement in smart cities. Journal of Urban Technology1–102.
32.
LiuYLiuXGaoS, et al. (2015) Social sensing: a new approach to understanding our socioeconomic environments. Annals of the Association of American Geographers105(3): 512–530.
33.
LynchKM (1960) The image of the city. MIT Press, 2–6.
34.
LyuHHuangJZhangD, et al. (2024) GPT-4V(ision) as a social media analysis engine. ACM Transactions on Intelligent Systems and Technology16: 1–54.
35.
MacedaLLLlovidoJLArtiagaMB, et al. (2023) Classifying sentiments on social media texts: a GPT-4 preliminary study. In: Proceedings of the 2023 7th International conference on natural language processing and information retrieval, Seoul Republic of Korea, 15 - 17 December 2023.
36.
MoturuSTKhayalIAharonyN, et al. (2011) Using social sensing to understand the links between sleep, mood, and sociability. In: IEEE International conference on privacy, security, risk, and trust, and IEEE international conference on social computing, Boston, MA, 9–11 October 2011, 208–215.
37.
National Bureau of Statistics of China. (2024). Major Cities Annual Data (2023 City Gross Domestic Product) [Data set]. NationalData. Retrieved June 2, 2025, fromhttps://data.stats.gov.cn/easyquery.htm?cn=E0105
38.
RashidUJurdakRTaylorA (2021) A survey on social-physical sensing: an emerging sensing paradigm that explores the collective intel. Journal of Network and Computer Applications177: 102857.
39.
SilvaBNKhanMJungC, et al. (2018) Urban planning and smart city decision management empowered by real-time data processing using big data analytics. Sensors18: 2994.
40.
SimeJD (1986) Creating places or designing spaces?Journal of Environmental Psychology6(1): 49–63.
41.
SolimanASoltaniKYinJ, et al. (2017) Social sensing of urban land use based on analysis of Twitter users’ mobility patterns. PLoS One12: e0181657.
42.
TaecharungrojVMillingtonS (2022) Amenity mix of innovation districts. Journal of Place Management and Development16: 125–143.
43.
Van NguyenMSSurSThuanDD (2020) IoT and IoE driven smart cities: connectivity considerations and smart initiatives. Advanced Research in Smart Cities: Building an Efficient Symbiotic Society1–50. doi: 10.1007/978-3-030-82715-1
44.
WangDSzymanskiBKAbdelzaherT, et al. (2019) The age of social sensing. Computer52: 1–12.
45.
WangZMaDSunD, et al. (2021) Identification and analysis of urban functional area in Hangzhou based on OSM and POI data. PLoS One16(5): e0251988.
46.
WuMYanBHuangY, et al. (2022) Big data-driven urban management: potential for urban sustainability. Land11: 680.
47.
XiaoMLiuQHanS, et al. (2023) Intelligent recommendation system for internet-famous sites based on web crawler. In: AbawajyJHXuZAtiquzzamanM, et al. (eds) Tenth International Conference on Applications and Techniques in Cyber Intelligence (ICATCI 2022). Cham: Springer International Publishing, 359–366.
48.
XuPDredzeMBroniatowskiDA (2020) The twitter social mobility index: measuring social distancing practices with geolocated tweets. Journal of Medical Internet Research22(12): e21499.
49.
YuanFWeiYDWuJ (2020) Amenity effects of urban facilities on housing prices in China: accessibility, scarcity, and urban spaces. Cities96: 102433.
50.
ZhanXUkkusuriSVZhuF (2014) Inferring urban land use using large-scale social media check-in data. Networks and Spatial Economics14(3): 647–667.
51.
ZhangDYHanRWangD, et al. (2016) On robust truth discovery in sparse social media sensing. In: 2016 IEEE international conference on big data (big data), Washington DC, USA, 5–8 Decemeber 2016, 1076–1081.
52.
ZhangHIbrahimAParsiaB, et al. (2023a) Passive social sensing with smartphones: a systematic review. Computing105: 29–51.
53.
ZhangLLiuJChenX (2023b) Towards human-AI collaborative urban science research enabled by pre-trained large language models. Artificial Intelligence Review55(2): 349–373.
54.
ZhengBHuangYGuoR (2024) Visitors’ behaviors and perceptions of spatial factors of uncultivated internet-famous sites in urban riverfront public spaces: case study in Changsha, China. Buildings14: 3385.
55.
ZhongQDingLLiuJ, et al. (2023) Can ChatGPT Understand too? A Comparative Study on ChatGPT and Fine-Tuned BERT [Preprint]. arXiv. https://arxiv.org/abs/2302.10198
56.
ZhouXZhangL (2016) Crowdsourcing functions of the living city from Twitter and Foursquare data. Cartography and Geographic Information Science43(5): 393–404.
Supplementary Material
Please find the following supplemental material available below.
For Open Access articles published under a Creative Commons License, all supplemental material carries the same license as the article it is associated with.
For non-Open Access articles published, all supplemental material carries a non-exclusive license, and permission requests for re-use of supplemental material or any part of supplemental material shall be sent directly to the copyright owner as specified in the copyright notice associated with the article.
