Sara Tori

Sara Tori

Auto-generated profile, based on publicly available information

Sara Tori

Vrije Universiteit Brussel, Mobilise Mobility and Logistics Research Group, House of Sustainable Transitions (HOST), Brussels, Belgium

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 April 2023 in Futures
Verified
Journal Article
Closed access
STSara Tori
Sara Tori
GBGeert Te Boveldt
Geert Te Boveldt
IKImre Keseru
Imre Keseru

30 March 2022 in Regional Science Policy & Practice
Verified
Journal Article
Open access
ASAlice de Séjournet
Alice de Séjournet
CMCathy Macharis
Cathy Macharis
STSara Tori
Sara Tori
LVLieselot Vanhaverbeke
Lieselot Vanhaverbeke
The goal of this research is to understand the impact of COVID‐19 restriction measures on the change in urban mobility in Brussels, Belgium. With daily data over the past 2 years depicting both the affluence to different places and the level and type of restrictions, we investigate through regression analysis their impacts on the changes in driving, public transport and cycling use. We find that cycling increased significantly (+63%), and that driving levels have returned to pre‐COVID levels after a significant reduction in spring 2020, while the return to public transport has been slower. We also find that the change in cycling use was not influenced by COVID‐19 restrictions, although telework and closing of retail establishments strongly affected the other modes.

11 April 2024 in Data Science for Transportation
Verified
Journal Article
Open access
PDF file
FTFloriano Tori
Floriano Tori
STSara Tori
Sara Tori
IKImre Keseru
Imre Keseru
Vincent GinisVincent Ginis
Vincent Ginis
Objectives: Mobility is a core challenge to transition towards sustainability. Cities are, therefore, rethinking their mobility to reduce negative externalities such as (greenhouse) gas emissions or congestion. When trying to implement sustainable urban mobility plans, there is often resistance from citizens. This can indicate a disconnect between the public and policymakers due to a lack of participation, coupled with the fact that current data-collection methods often used (such as travel surveys) are limited in scope. Advances in big data analysis and user-generated content provide opportunities to gain deeper insights into citizens' perceptions of mobility policy changes. This paper explores how sentiment analysis through deep learning can be used in transport planning. Materials and Methods: In this research, we analyse the sentiments of citizens towards recent changes in mobility policy in Brussels, Belgium, through Twitter data. We analyse 1998 tweets about changing mobility policy in Brussels between July 18th, 2019 (forming of the last Brussels regional government), and December 31st, 2022 (starting date of the analyses). For our analysis, we employ two pre-trained language models: XLM-T and GPT4. Results: Our results show that the sentiment with regard to the new mobility interventions is, as reflected by Twitter posts, not overwhelmingly negative. Furthermore, we find that the performance scores of XLM-T when no domain-specific fine-tuning has occurred (zero-shot evaluation) is fairly low (0.48). Once the model is trained on our domain-specific data, it reaches an accuracy of 0.67. When using GPT4, the model reaches an accuracy of 0.66. Additionally, GPT4 seems better suited at identifying mismatched tweets, i.e. tweets using vocabulary that has a different sentiment than the one the tweets expresses (e.g., sarcasm). This might indicate that large language models might be better suited to obtain implicit sentiments expressed in a text. Conclusions: From a machine learning perspective, our experiments highlight the difficulty of recognising contextual sentiment (in this case, a sentiment towards changes in mobility policies), which may differ from the sentiment reflected in the vocabulary used. This is especially important if these two sentiments do not correspond, a problem both models struggled with. Additionally, we show that GPT4 can provide additional information when performing sentiment analysis by prompting it to attribute scores to texts. This paper opens new perspectives on understanding and addressing public sentiment in urban mobility policies. The advancements in language models, and the effective integration of user-generated content, can provide policymakers with a more comprehensive understanding of public sentiment, facilitating the implementation of certain policies. Clinical Relevance: None.

22 July 2022 in European Transport Research Review
Verified
Journal Article
Open access
PDF file
STSara Tori
Sara Tori
JPJesse Pappers
Jesse Pappers
IKImre Keserü
Imre Keserü
Background: Historically, quantitative forecasting methods have been used in transport planning. As forecasts can be unreliable to plan for the medium- and long-term, scenario building has recently been increasingly used. However, scenario building methods often fail to take disruptions and wild cards into account, i.e., low probability but high impact events. When unaccounted for, wild card events, like the COVID-19 pandemic, lower the efficacy of scenario building in policy making, as these events may completely disturb the developed scenarios of the future. Methods: In this paper, we develop and apply a creative and participatory methodology to develop visions and disrupted scenarios for rural mobility. Our research was carried out in the Belgian village of Oetingen, where inhabitants developed more resilient views of the future by creating disrupted mobility scenarios and a preferred mobility vision for their village for the year 2050 in a participatory scenario building exercise. Wild cards related to mobility were collected from mobility experts and inhabitants in three workshops. Inhabitants were engaged to define their mobility vision on a postcard that was distributed to all houses in the village as well as on a project website. Respondents were invited for a follow-up interview in which their preferred mobility vision was subjected to the wild cards, and participants described how these wild cards would change their preferred vision. As children tend to have more creative ideas, they were engaged via workshops at school. Results: This process resulted in mobility scenarios for the village for the year 2050 based on the different wild cards, as well as an overall desired vision. We found that the use of wild cards did not significantly change the scenarios when compared to the vision, although it did make the interviewees step outside of their comfort zones. We also found that the citizens did not have more original and less path-dependent ideas in developing wild cards when compared to experts. Lastly, we found that children have many outside-of-the-box suggestions when it comes to the future. Although some of their ideas can be judged as impractical by today’s standards, many ideas had an indirect implication for mobility in the village and gave insights into children’s priorities, as potential future residents of the village.

18 May 2022 in Future Transportation
Verified
Journal Article
Open access
PDF file
EXElpida Xenou
Elpida Xenou
Georgia AifadopoulouGeorgia Aifadopoulou
Georgia Aifadopoulou
BRBeatriz Royo
Beatriz Royo
STSara Tori
Sara Tori
MMMarco Mazzarino
Marco Mazzarino
The various social, political, environmental, and economical mega-trends together with the rapid rise of digitalization are shaping cities worldwide including the way that citizens and products move within the urban environment. New mobility services are popping up which are showing the path toward more on-demand and personalized mobility patterns. The transformation of the urban mobility environment though constitutes a great challenge for policy-makers, as little is known about the impact of these trends on the city’s current mobility environment while the assessment of the future state of a mobility system can be considered a quite complex process taken its multi-parametric and multi-dimensional nature. This paper aims to simplify this process by presenting a coherent multi-actor consequence analysis framework as a tool for assessing future mobility scenarios which was developed in the framework of the H2020 SPROUT. This paper presents in detail the main components of this framework together with the list of key performance indicators used for assessing the performance in terms of sustainability of future mobility scenarios as well as indicative results from its use by the city of Padua.

13 September 2024 in Children's Geographies
Verified
Journal Article
Closed access
STSara Tori
Sara Tori
JPJesse Pappers
Jesse Pappers
LRLluis Martinez Ramirez
Lluis Martinez Ramirez
IKImre Keseru
Imre Keseru