We present a demo of RAGTrip, a modular conversational system that integrates Large Language Models (LLMs), spatial reasoning, and information retrieval to generate personalized walking itineraries in urban environments. Unlike traditional route planners or closed-book LLMs, RAGTrip interprets nuanced user preferences, avoids hallucinations, and grounds its suggestions in real-world geographic and factual data. The system features an interactive conversational interface that engages users in refining both the itinerary and the attractions to visit. Through dynamic map visualizations and contextual responses, users can explore and iteratively customize their routes. The demo includes a toggle to enable or disable Retrieval-Augmented Generation (RAG), allowing direct comparison between RAG-enhanced and closed-book LLM responses. This highlights the value of combining spatial and semantic grounding in conversational itinerary recommendation.

With the advent of modern$4 \mathrm{G} / 5 \mathrm{G}$networks, mobile phone data collected by operators now includes detailed, servicespecific traffic information with high spatio-temporal resolution. In this paper, we explore the potential of such data for learning high-quality embeddings (representations) of urban regions. We propose a methodology that takes this data as input and employs a temporal convolutional network-based autoencoder, transformers, and learnable weighted sum models to extract key urban features. In the experimental evaluation, conducted using realworld datasets, we demonstrate that the embeddings generated by our methodology effectively capture urban characteristics. In particular, our embeddings are compared against those of a state-of-the-art multi-modal competitor across two downstream tasks, showing comparable quality. In general, our work highlights the potential and utility of service-specific mobile traffic data for urban research and the importance of making this data accessible to foster public innovation.

Urban research faces challenges in understanding and describing city regions, which are essential for urban planning and tourism management. Traditional methods rely on predefined areas and non-human-readable representations. This paper presents a new unsupervised approach that overcomes these limitations using a data-driven method with Instruction-tuned Large Language Models (ILLMs). Our technique dynamically identifies urban regions with similar features and generates human-readable descriptions. We validate this method using Flickr images from Pisa, Italy, and our results show that it effectively captures the semantic features of urban regions and generates comprehensible textual descriptions.

This study investigates the application of Recom-mender Systems (RS) to predict future Point of Interest (POI) visits based on check-in data, with a particular focus on biases related to individual mobility patterns and POI popularity. We conduct a comprehensive analysis by training and evaluating three RS models based on different architectures: a Convo-lutional Neural Network, an Attention-based Neural Network, and a Markov-based predictor. Our analysis reveals that POI recommenders: do not show bias in terms of the typical distance traveled by users but tend to favor less exploratory users, and are biased towards more popular POIs. Our findings highlight the potential of RS in capturing and forecasting user behavior, while also underscoring the need to mitigate these biases, thereby advancing the understanding of RS and their broader social impact.

The analysis of semantic trajectories has gained significant attention in urban mobility research due to its potential to provide comprehensive insights into movement patterns and associated semantic data. However, integrating multiple semantic aspects with spatio-temporal information often leads to redundancy and computational challenges. To address this issue, we proposed MAT-SUM, a novel method for trajectory summarization while preserving semantic quality. This method identifies urban regions based on associated semantic contexts and discretizes trajectories, yielding a high level of summarization without compromising semantic quality. This paper delves into the research questions we aim to address, focusing on the effectiveness of capturing human mobility and urban dynamics following the summarization of semantic trajectories using MAT-SUM. Our investigation aims to determine if comparable results can be achieved by analyzing summarized semantic trajectories compared to the original ones, such as classifying users exhibiting routine and non-routine behaviours. Furthermore, we examine the usefulness of the identified regions in comprehending urban dynamics. While some research questions remain open, this paper outlines ongoing investigations and potential strategies to enhance outcomes in mobility analysis.

Mobility data analysis provides insights into human movement patterns, traffic flows, and urban planning strategies. Human dynamics analysis focuses on tracking people to investigate how individuals and groups behave, interact, and evolve. Various mobility data sources, such as GPS, mobile phone records, social media, and transportation logs, are often semantically enriched and used for these analyses. This results in the generation of new, complex datasets that require effective summarization methods to reduce data volume while preserving relevant information. In this work, we aim to demonstrate the effective use of summarized semantic trajectories in analyzing human mobility behaviours. We offer empirical evidence from a case study, showing how this type of trajectory helps in understanding human mobility, especially in distinguishing between routine and non-routine behaviours. Experimental results show that the analysis results are comparable with the results obtained in the original (non summarized) dataset.

The proliferation of motion sensors has significantly contributed to the availability of mobility data. An important line of research focuses on augmenting these datasets with diverse semantic information, referred to as aspects, thereby yielding multiple aspect trajectories (MATs). However, a notable gap in the existing literature pertains to the absence of methodologies for obtaining MATs and the scarcity of real-world datasets. To address this gap, we introduce MAT-Builder, an innovative system designed to facilitate the customization of semantic enrichment of trajectories through the use of arbitrary aspects and external data sources. Notably, the richness of information endowed by MAT-Builder may introduce challenges in terms of data management and storage. Consequently, we propose MAT-Sum, an approach tailored to summarize trajectories while preserving their semantic information.

The proliferation of tracking sensors in today's devices has led to the generation of high-frequency, high-volume streams of mobility data capturing the movements of various objects. These movement data can be enriched with semantic contextual information, such as activities, events, user preferences, and more, generating semantically enriched trajectories. Creating and managing these types of trajectories presents challenges due to the massive data volume and the heterogeneous, complex semantic dimensions. To address these issues, we introduce a novel approach, MAT-Sum, which uses a location-centric enrichment perspective to summarize massive volumes of mobility data while preserving essential semantic information. Our approach enriches geographical areas with semantic aspects to provide the underlying context for trajectories, enabling effective data reduction through trajectory summarization. In the experimental evaluation, we show that MAT-Sum effectively minimizes trajectory volume while retaining a good level of semantic quality, thus presenting a viable solution to the relevant issue of managing massive mobility data.

The notion of multiple aspect trajectory (MAT) has been recently introduced in the literature to represent movement data that is heavily semantically enriched with dimensions (aspects) representing various types of semantic information (e.g., stops, moves, weather, traffic, events, and points of interest). Aspects may be large in number, heterogeneous, or structurally complex. Although there is a growing volume of literature addressing the modelling and analysis of multiple aspect tra-jectories, the community suffers from a general lack of publicly available datasets. This is due to privacy concerns that make it difficult to publish such type of data, and to the lack of tools that are capable of linking raw spatio-temporal data to different types of semantic contextual data. In this work we aim to address this last issue by presenting MAT-BUILDER, a system that not only supports users during the whole semantic enrichment process, but also allows the use of a variety of external data sources. Furthermore, MAT-BUILDER has been designed with modularity and extensibility in mind, thus enabling practitioners to easily add new functionalities to the system and set up their own semantic enrichment process. The demonstration scenario, which will be showcased during the demo session, highlights how MAT-BUILDER's main features allow users to easily generate multiple aspect trajectories, hence benefiting the mobility data analysis community.