We present an extension of Triangolazioni (a Cultural Heritage webapp) to enrich curated content with context-dependent, external information provided by Large Language Models (LLMs) within a loosely-coupled architecture agnostic to the LLM. The system supports context-dependent information search and presentation within an architecture agnostic to the exploited LLM.

Travel experiences can challenge individuals with Autism Spectrum Disorder (ASD) before embarking on a trip, because of the complexity of planning, but also during the trip, due to sensory overstimulation while visiting places. Artificial Intelligence (AI) could help overcome some obstacles. However, it might represent a barrier for people with mid-functioning autism if their needs for assistance are not considered when designing tourism applications. Moreover, most trip planners fully control the generation of solutions, undermining users’ decision autonomy. To address these challenges, we explored the development of itinerary planning technologies through a human-centered approach. We aimed to balance guiding users in their decision-making with empowering them to plan tours independently. The result is CARES, an Artificial Intelligence-driven trip planner designed for autistic adults, which we present in this article. CARES applies a collaborative approach to developing itineraries, based on the exploitation of (i) AI technologies for information filtering and interactive itinerary planning that are robust to the data scarcity characterizing the autism domain; (ii) a user interface that reduces information overload and decision fatigue in information exploration. We tested CARES with 14 autistic adults, gathering insights to guide future design and improve the usability of Artificial Intelligence for neurodivergent users. The results indicate that our approach provides an accessible solution for enhancing the travel experiences of mid- to high-functioning autistic adults. In doing so, it contributes to more inclusive tourism. • We found that, despite difficulties, autistic adults wish to plan trips autonomously. • We propose a Human-Centered AI trip planner for mid/high-functioning ASD users. • Step-by-step guidance helps autistic users plan trips with limited effort. • The app empowers users to make choices while AI guides the process, ensuring balanced control. • The app balances user guidance and decision-making control.

User experience and trust in AI-assisted technologies are key factors in controlling their adoption. We investigate these aspects in an Agentic AI platform that integrates routine productivity services and exhibits different levels of autonomy: a manual baseline that lacks AI-driven automation, an Agentic AI with medium autonomy that requires user confirmation before acting, and an Agentic AI with high autonomy that acts proactively for low-stakes tasks. The study, involving 230 participants with heterogeneous professional backgrounds, examines how autonomy of the system affects user activity, user workload, perceived support, and trust. We found that both Agentic AI systems outperformed the baseline in user productivity. In task execution, they achieved a precision of over 82%, higher than the baseline’s 65%. The recall of the Agentic AI system with high autonomy was 63%. This denotes much higher throughput than the system without AI-driven automation (14%). The Agentic AI systems outperformed the baseline in workload reduction (NASA-TLX Aggregate score) with a statistically significant difference. Both AI-driven systems received equivalent or slightly higher trust than the baseline. However, the system with medium autonomy was the best at balancing productivity gains and user preferences for control. Specifically, the correlations between individual user characteristics (Desirability of Control and Propensity to Trust) and the resulting trust in the systems suggest that the influence of personal traits on system evaluation is least pronounced when automation is combined with explicit user intervention. These results encourage the adoption of user-controllable Agentic AI architectures in multitasking support.

The current models for the explanation and justification of recommender systems results focus on qualitative and quantitative data about items, overlooking the power of images to describe the different aspects of experience that the consumer should expect from their selection to post-sales. In the present paper, we extend previous justification models by exploiting object recognition on images to support a service-oriented presentation of multimodal (textual, quantitative, and images) information about items. As a testbed for our model, we chose the home-booking domain. In a user study, we found that item comparison can be enhanced by empowering the user to filter multimodal data based on a set of evaluation dimensions describing the experience with items. These results encourage the introduction of service-based filters for multimodal information retrieval in product and service catalogs.

Abstract With the increasing demand for predictable and accountable Artificial Intelligence, the ability to explain or justify recommender systems results by specifying how items are suggested, or why they are relevant, has become a primary goal. However, current models do not explicitly represent the services and actors that the user might encounter during the overall interaction with an item, from its selection to its usage. Thus, they cannot assess their impact on the user’s experience. To address this issue, we propose a novel justification approach that uses service models to (i) extract experience data from reviews concerning all the stages of interaction with items, at different granularity levels, and (ii) organize the justification of recommendations around those stages. In a user study, we compared our approach with baselines reflecting the state of the art in the justification of recommender systems results. The participants evaluated the Perceived User Awareness Support provided by our service-based justification models higher than the one offered by the baselines. Moreover, our models received higher Interface Adequacy and Satisfaction evaluations by users having different levels of Curiosity or low Need for Cognition (NfC). Differently, high NfC participants preferred a direct inspection of item reviews. These findings encourage the adoption of service models to justify recommender systems results but suggest the investigation of personalization strategies to suit diverse interaction needs.

ACM PATCH 2020, organized in conjunction with the 28th International Conference on User Modeling, Adaptation and Personalization, is the latest event of the PATCH series, started in 2007 and held within the UMAP and IUI Conference series. We summarize the main ideas addressed in the papers accepted for publication in the workshop proceedings and for presentation at the event.

The suggestion of Points of Interest to people with Autism Spectrum Disorder (ASD) challenges recommender systems research because these users' perception of places is influenced by idiosyncratic sensory aversions which can mine their experience by causing stress and anxiety. Therefore, managing individual preferences is not enough to provide these people with suitable recommendations. In order to address this issue, we propose a Top-N recommendation model that combines the user's idiosyncratic aversions with her/his preferences in a personalized way to suggest the most compatible and likable Points of Interest for her/him. We are interested in finding a user-specific balance of compatibility and interest within a recommendation model that integrates heterogeneous evaluation criteria to appropriately take these aspects into account. We tested our model on both ASD and "neurotypical" people. The evaluation results show that, on both groups, our model outperforms in accuracy and ranking capability the recommender systems based on item compatibility, on user preferences, or which integrate these two aspects by means of a uniform evaluation model.

Collaborative Filtering is largely applied to personalize item recommendation but its performance is affected by the sparsity of rating data. In order to address this issue, recent systems have been developed to improve recommendation by extracting latent factors from the rating matrices, or by exploiting trust relations established among users in social networks. In this work, we are interested in evaluating whether other sources of preference information than ratings and social ties can be used to improve recommendation performance. Specifically, we aim at testing whether the integration of frequently co-occurring interests in information search logs can improve recommendation performance in User-to-User Collaborative Filtering (U2UCF). For this purpose, we propose the Extended Category-based Collaborative Filtering (ECCF) recommender, which enriches category-based user profiles derived from the analysis of rating behavior with data categories that are frequently searched together by people in search sessions. We test our model using a big rating dataset and a log of a largely used search engine to extract the co-occurrence of interests. The experiments show that ECCF outperforms U2UCF and category-based collaborative recommendation in accuracy, MRR, diversity of recommendations and user coverage. Moreover, it outperforms the SVD++ Matrix Factorization algorithm in accuracy and diversity of recommendation lists.

Many collaborative recommender systems leverage social correlation theories to improve suggestion performance. However, they focus on explicit relations between users and they leave out other types of information that can contribute to determine users' global reputation; e.g., public recognition of reviewers' quality.

In Geographical Information search, map visualization can challenge the user because results can consist of a large set of heterogeneous items, increasing visual complexity. We propose a novel visualization model to address this issue. Our model represents results as markers, or as geometric objects, on 2D/3D layers, using stylized and highly colored shapes to enhance their visibility. Moreover, the model supports interactive information filtering in the map by enabling the user to focus on different data categories, using transparency sliders to tune the opacity, and thus the emphasis, of the corresponding data items. A test with users provided positive results concerning the efficacy of the model.

The presentation of search results in GIS can expose the user to cluttered geographical maps, challenging the identification of relevant information. In order to address this issue, we propose a visualization model supporting interactive information filtering on 2D/3D maps. Our model is based on the introduction of transparency sliders that enable the user to tune the opacity, and thus the emphasis, of data categories in the map. In this way, he or she can focus the maps on the most relevant types of information for the task to be performed. A test with users provided positive results concerning the efficacy of our model.

Exploratory information search can challenge users in the formulation of efficacious search queries. Moreover, complex information spaces, such as those managed by Geographical Information Systems, can disorient people, making it difficult to find relevant data. In order to address these issues, we developed a session-based suggestion model that proposes concepts as a \em "you might also be interested in»» function, by taking the user»s previous queries into account. Our model can be applied to incrementally generate suggestions in interactive search. It can be used for query expansion, and in general to guide users in the exploration of possibly complex spaces of data categories. Our model is based on a concept co-occurrence graph that describes how frequently concepts are searched together in search sessions. Starting from an ontological domain representation, we generated the graph by analyzing the query log of a major search engine. Moreover, we identified clusters of ontology concepts which frequently co-occur in the sessions of the log via community detection on the graph. The evaluation of our model provided satisfactory accuracy results.

The Information Retrieval research has used semantics to provide accurate search results, but the analysis of conceptual abstraction has mainly focused on information integration. We consider session-based query expansion in Geographical Information Retrieval, and investigate the impact of semantic granularity (i.e., specificity of concepts representation) on the suggestion of relevant types of information to search for. We study how different levels of detail in knowledge representation influence the capability of guiding the user in the exploration of a complex information space. A comparative analysis of the performance of a query expansion model, using three spatial ontologies defined at different semantic granularity levels, reveals that a fine-grained representation enhances recall. However, precision depends on how closely the ontologies match the way people conceptualize and verbally describe the geographic space.

Ecological Networks (ENs) are a way to describe the structures of existing real ecosystems and to plan their expansion, conservation and improvement.In this work, we present a model to represent the specifications for the local planning of ENs in a way that can support reasoning, e.g., to detect violations within new proposals of expansion, or to reason about improvements of the networks.Moreover, we describe an OWL ontology for the representation of ENs themselves.In the context of knowledge engineering, ENs provide a complex, inherently geographic domain that demands for the expressive power of a language like OWL augmented with the GeoSPARQL ontology to be conveniently represented.More importantly, the set of specification rules that we consider (taken from the project for a local EN implementation) constitute a challenging problem for representing constraints over complex geographic domains, and evaluating whether a given large knowledge base satisfies or violates them.

We test the impact of integrating a measure of common friendship in collaborative filtering, in order to capture the intuition that socially interconnected groups of people tend to have similar tastes. An experiment on the Yelp dataset shows that using preference information derived from the commonalities of interests in networks of friends achieves higher accuracy than item-to-item collaborative filtering.

Textual queries are largely employed in information retrieval to let users specify search goals in a natural way. However, differences in user and system terminologies can challenge the identification of the user's information needs, and thus the generation of relevant results. We argue that the explicit management of ontological knowledge, and of the meaning of concepts (by integrating linguistic and encyclopaedic knowledge in the system ontology), can improve the analysis of search queries, because it enables a flexible identification of the topics the user is searching for, regardless of the adopted vocabulary. This paper proposes an information retrieval support model based on semantic concept identification. Starting from the recognition of the ontology concepts that the search query refers to, this model exploits the qualifiers specified in the query to select information items on the basis of possibly fine-grained features. Moreover, it supports query expansion and reformulation by suggesting the exploration of semantically similar concepts, as well as of concepts related to those referred in the query through thematic relations. A test on a data-set collected using the OnToMap Participatory GIS has shown that this approach provides accurate results.

Since 2007, the PATCH workshop series (https://patchworkshopseries.wordpress.com/) have been gathering successfully researchers and professionals from various countries and institutions to discuss the topics of digital access to cultural heritage and specifically the personalization aspects in this process. Due to this rich history, the reach of the PATCH workshop in various research communities is extensive.

We present the personal cloud platform (PCP) for the management of service clouds providing the user with a unified environment for handling her/his activities and collaborations. Within a personal cloud, the PCP enables the definition of global collaboration groups and a holistic management of the workspace awareness, concerning all the integrated services. Moreover, being based on an open architecture, the PCP supports the integration of external applications, selected by the enterprise user.

We present the SynCFr framework (synchronization collaboration framework) supporting the management of composite applications and the synchronization of heterogeneous applications and services cooperating within a shared context. SynCFr supports the management of services and applications based on Web APIs, REST interfaces and WSDL/SOAP interfaces. The key element of SynCFr is the cross-application context, a shared dataspace used to collect and distribute the business data and synchronization information generated by the components to be integrated. By exploiting SynCFr, we developed an integrated collaboration environment answering different organizational life needs, both in the user's private life, and in team collaboration. The environment provides the user with a unified view of her activities in multiple collaboration spheres.

Service oriented architecture (SOA) supports the integration of distributed and heterogeneous services by offering Web service composition standards which describe service composition as a business process. However, the composition model proposed in SOA does not explicitly deal with personalization and context-awareness. In order to address such limitations, we have developed the CAWE conceptual framework. In this paper, we describe the personalization support offered by our framework to the development of context-aware, adaptive Web-based systems. CAWE handles the integration of heterogeneous services and information sources; moreover, it manages long-lasting interactions with multiple cooperating users and it personalizes the business logic of the application by adapting the workflow activities to be carried out.

Although personalization and ubiquity are key properties for on-line services, they challenge the development of these systems due to the complexity of the required architectures. In particular, the current infrastructures for the development of personalized, ubiquitous services are not flexible enough to accommodate the configuration requirements of the various application domains. To address such issues, highly configurable infrastructures are needed.In this article, we describe Seta2000, an infrastructure for the development of recommender systems that support personalized interactions with their users and are accessible from different types of devices (e.g., desktop computers and mobile phones). The Seta2000 infrastructure offers a built-in recommendation engine, based on a multi-agent architecture. Moreover, the infrastructure supports the integration of heterogeneous software and the development of agents that can be configured to offer specialized facilities within a recommender system, but also to dynamically enable and disable such facilities, depending on the requirements of the application domain. The Seta2000 infrastructure has been exploited to develop two prototypes: SeTA is an adaptive Web store personalizing the recommendation and presentation of products in the Web. INTRIGUE is a personalized, ubiquitous information system suggesting attractions to possibly heterogeneous tourist groups.

The emerging standards for the specification of Web Services support the publication of the static interfaces of the operations they may execute. However, little attention is paid to the management of long‐lasting interactions between the service providers and their consumers. Although this is not an issue in the case of “one‐shot” services, it challenges the provision of services requiring the exchange of multiple messages between the business partners. In this article, we present a conversational model supporting the management of long‐lasting interactions where several messages have to be exchanged before the service is completed. Our model aims at facilitating the consumers during the service invocation because in this way the establishment of short‐term business relations can be simplified. To this extent, we provide a computational framework that can be exploited to manage a conversation between the consumer and the service provider. Our framework is inspired from the research developed in Computational Linguistics and in the area of Multi‐Agent Systems to manage human‐to‐computer and agent‐to‐agent dialog. However, we employ techniques suitable to comply with the emerging Web Service standards and with the scalability requirements of the Internet.

We present a model for the integration of intelligent user interfaces and configuration techniques. This model enhances the capabilities of online stores by supporting the development of configuration systems that assist customers in a personalised way, while they selects the features of the products/services to be configured.

This paper presents a cooperative consultation system on a restricted domain.The system builds hypotheses on the user's plan and avoids misunderstandings (with consequent repair dialogues) through clarification dialogues in case of ambiguity.The role played by constraints in the generation of the answer is characterized in order to limit the cases of ambiguities requiring a clarification dialogue.The answers of the system are generated at different levels of detail, according to the user's competence in the domain.