Andrea Bonetti

Mr. Andrea Bonetti

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
14 May 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
ABAndrea Bonetti
Andrea Bonetti
Marcelino Martínez SoberMarcelino Martínez Sober
Marcelino Martínez Sober
JTJulio Torres
Julio Torres
JVJose Maria Vega
Jose Maria Vega
SPSebastien Pellerin
Sebastien Pellerin
Joan Vila-FrancésJoan Vila-Francés
Joan Vila-Francés
The way we communicate has been revolutionised by the widespread use of social networks. Any kind of online message can reach anyone in the world almost instantly. The speed with which information spreads is undoubtedly the strength of social networks, but at the same time, any user of these platforms can see how toxic messages spread in parallel with likes, comments and ratings about any person or entity. In such cases, the victim feels even more helpless and defenceless as a result of the rapid spread. For this reason, we have implemented an automatic detector of toxic messages on social media. This allows us to stop toxicity in its tracks and protect victims. In particular, the aim of the survey is to demonstrate how traditional Machine Learning methods of Natural Language Processing (NLP) work on equal terms with Deep Learning methods represented by a Transformer architecture and characterised by a higher computational cost. In particular, the paper describes the results obtained by testing different supervised Machine Learning classifiers (Logistic Regression, Random Forest and Support Vector Machine) combined with two topic-modelling techniques of NLP, (Latent Semantic Analysis and Latent Dirichlet Allocation). A pre-trained Transformer named BERTweet was also tested. All models performed well in this task, so much so that values close to or above 90% were achieved in terms of the F1 score evaluation metric. The best result achieved by Transformer BERTweet, 91.40%, was therefore not impressive in this context, as the performance gains are too small compared to the computational overhead.

5 December 2025 in Tourism and Hospitality
Verified
Journal Article
Open access
PDF file
ABAndrea Bonetti
Andrea Bonetti
APAdrián Salcedo Puche
Adrián Salcedo Puche
Joan Vila-FrancésJoan Vila-Francés
Joan Vila-Francés
XBXaro Benavent
Xaro Benavent
EFEmilio Fernández-Vargas
Emilio Fernández-Vargas
EMILIO SORIAEMILIO SORIA
EMILIO SORIA
The contemporary digital landscape overwhelms visitors with fragmented and dynamic information, complicating travel planning and often leading to decision paralysis. This paper presents a real-world case study on the design and deployment of an intelligent tourism assistant for Valencia, Spain, built upon a Retrieval-Augmented Generation (RAG) architecture. To address the complexity of integrating static attraction data, live events, and geospatial context, we implemented a multi-agent system orchestrated via the ReAct (Reason + Act) paradigm, comprising specialized Retrieval, Events, and Geospatial Agents. Powered by a large language model, the system unifies heterogeneous data sources—including official tourism repositories and OpenStreetMap—within a single conversational interface. Our contribution centers on practical insights and engineering lessons from developing RAG in an operational urban tourism environment. We outline data preprocessing strategies, such as coreference resolution, to improve contextual consistency and reduce hallucinations. System performance is evaluated using Retrieval Augmented Generation Assessment (RAGAS) metrics, yielding quantitative results that assess both retrieval efficiency and generation quality, with the Mistral Small 3.1 model achieving an Answer Relevancy score of 0.897. Overall, this work highlights both the challenges and advantages of using agent-based RAG to manage urban-scale information complexity, providing guidance for developers aiming to build trustworthy, context-aware AI systems for smart destination management.

11 November 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
ABAndrea Bonetti
Andrea Bonetti
APAdrián Salcedo Puche
Adrián Salcedo Puche
Joan Vila-FrancésJoan Vila-Francés
Joan Vila-Francés
XBXaro Benavent
Xaro Benavent
EFEmilio Fernández-Vargas
Emilio Fernández-Vargas
EMILIO SORIAEMILIO SORIA
EMILIO SORIA
The contemporary digital landscape overwhelms visitors with fragmented and dynamic information, complicating travel planning and often leading to decision paralysis. This paper presents a real-world case study on the design and deployment of an intelligent tourism assistant for Valencia, Spain, built upon a Retrieval-Augmented Generation (RAG) architecture. To address the complexity of integrating static attraction data, live events, and geospatial context, we implemented a multi-agent system comprising specialized Retrieval, Events, and Geospatial Agents. Powered by a large language model, the system unifies heterogeneous data sources — including official tourism repositories and OpenStreetMap — within a single conversational interface. Our contribution centers on practical insights and engineering lessons from developing RAG in an operational urban tourism environment. We outline data preprocessing strategies such as coreference resolution to improve contextual consistency and reduce hallucinations. System performance is evaluated using Retrieval Augmented Generation Assessment (RAGAS) metrics, yielding quantitative results that assess both retrieval efficiency and generation quality, with the Mistral Small 3.1 model achieving an Answer Relevancy score of 0.897. Overall, this work highlights both the challenges and advantages of using agent-based RAG to manage urban-scale information complexity, providing guidance for developers aiming to build trustworthy, context-aware AI systems for smart destination management.

7 May 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
EFEmilio Fernández-Vargas
Emilio Fernández-Vargas
ABAndrea Bonetti
Andrea Bonetti
Joan Vila-FrancésJoan Vila-Francés
Joan Vila-Francés
RMRafael Magdalena
Rafael Magdalena
XBXaro Benavent-Garcia
Xaro Benavent-Garcia
SDSergio Daly-Terrén
Sergio Daly-Terrén
Efficient monitoring of urban water consumption is essential for sustainable resource management and early detection of distribution network irregularities. Single-method anomaly detection approaches often fail to capture the diversity of patterns present in real consumption data, such as leaks, meter malfunctions, abrupt demand shifts, and data inconsistencies. This study proposes an ensemble anomaly detection framework that combines complementary time series techniques, including decomposition, forecasting, density-based, and smoothing-based methods. The framework was applied to neighborhood-level daily water consumption data from Valencia, Spain, where six individual neighborhoods were selected to reflect distinct consumption patterns. Each time series was analyzed independently to preserve local consumption behavior. The ensemble approach demonstrated improved robustness in identifying diverse irregularities compared to individual methods, without requiring labeled training data. Results were explored through a geospatial visualization interface that enabled spatial interpretation of detected anomalies across neighborhoods. The proposed framework is scalable, interpretable, and adaptable to evolving consumption patterns, supporting data-driven decision-making for urban water management in smart city contexts.

31 August 2026 in City and Environment Interactions
Verified
Journal Article
Open access
EFEmilio Fernández-Vargas
Emilio Fernández-Vargas
ABAndrea Bonetti
Andrea Bonetti
Joan Vila-FrancésJoan Vila-Francés
Joan Vila-Francés
RMRafael Magdalena
Rafael Magdalena
XBXaro Benavent-Garcia
Xaro Benavent-Garcia
SDSergio Daly-Terrén
Sergio Daly-Terrén