Thiago H Silva

Neemias da Silva, Myriam Delgado, Rodrigo Minetto et al.

We study how persona prompting shapes language generated by multimodal large language models in an urban perception setting. Using 59,808 annotations from 1,200 persona-conditioned agents and two no-persona settings, we analyze captions, justifications, and perception tags across personas. Results indicate strong convergence in captions for different personas, whereas justifications display systematic variation associated with socioeconomic and political attributes, while perception tags show no statistically significant persona-related differences, though effect trends are observed. Topic analysis further reveals that personas emphasize different evaluative themes when interpreting the same scenes.

Neemias B da Silva, Rodrigo Minetto, Daniel Silver et al.

Large Language Models (LLMs) are increasingly used as proxies for human perception in urban analysis, yet it remains unclear whether persona prompting produces meaningful and reproducible behavioral diversity. We investigate whether distinct personas influence urban sentiment judgments generated by multimodal LLMs. Using a factorial set of personas spanning gender, economic status, political orientation, and personality, we instantiate multiple agents per persona to evaluate urban scene images from the PerceptSent dataset and assess both within-persona consistency and cross-persona variation. Results show strong convergence among agents sharing a persona, indicating stable and reproducible behavior. However, cross-persona differentiation is limited: economic status and personality induce statistically detectable but practically modest variation, while gender shows no measurable effect and political orientation only negligible impact. Agents also exhibit an extremity bias, collapsing intermediate sentiment categories common in human annotations. As a result, performance remains strong on coarse-grained polarity tasks but degrades as sentiment resolution increases, suggesting that simple label-based persona prompting does not capture fine-grained perceptual judgments. To isolate the contribution of persona conditioning, we additionally evaluate the same model without personas. Surprisingly, the no-persona model sometimes matches or exceeds persona-conditioned agreement with human labels across all task variants, suggesting that simple label-based persona prompting may add limited annotation value in this setting.

Thiago H Silva, Daniel Silver

Urban research has long recognized that neighbourhoods are dynamic and relational. However, lack of data, methodologies, and computer processing power have hampered a formal quantitative examination of neighbourhood relational dynamics. To make progress on this issue, this study proposes a graph neural network (GNN) approach that permits combining and evaluating multiple sources of information about internal characteristics of neighbourhoods, their past characteristics, and flows of groups among them, potentially providing greater expressive power in predictive models. By exploring a public large-scale dataset from Yelp, we show the potential of our approach for considering structural connectedness in predicting neighbourhood attributes, specifically to predict local culture. Results are promising from a substantive and methodologically point of view. Substantively, we find that either local area information (e.g. area demographics) or group profiles (tastes of Yelp reviewers) give the best results in predicting local culture, and they are nearly equivalent in all studied cases. Methodologically, exploring group profiles could be a helpful alternative where finding local information for specific areas is challenging, since they can be extracted automatically from many forms of online data. Thus, our approach could empower researchers and policy-makers to use a range of data sources when other local area information is lacking.

Frances Santos, Thiago H Silva, Antonio A F Loureiro et al.

The automatic extraction of urban perception shared by people on location-based social networks (LBSNs) is an important multidisciplinary research goal. One of the reasons is because it facilitates the understanding of the intrinsic characteristics of urban areas in a scalable way, helping to leverage new services. However, content shared on LBSNs is diverse, encompassing several topics, such as politics, sports, culture, religion, and urban perceptions, making the task of content extraction regarding a particular topic very challenging. Considering free-text messages shared on LBSNs, we propose an automatic and generic approach to extract people's perceptions. For that, our approach explores opinions that are spatial-temporal and semantically similar. We exemplify our approach in the context of urban outdoor areas in Chicago, New York City and London. Studying those areas, we found evidence that LBSN data brings valuable information about urban regions. To analyze and validate our outcomes, we conducted a temporal analysis to measure the results' robustness over time. We show that our approach can be helpful to better understand urban areas considering different perspectives. We also conducted a comparative analysis based on a public dataset, which contains volunteers' perceptions regarding urban areas expressed in a controlled experiment. We observe that both results yield a very similar level of agreement.