This preliminary research explores the critical issue of preventing children's exposure to inappropriate advertisements within childtargeted content on streaming platforms.Inspired by real-world examples from Spotify and Disney+, where advertisements were misaligned with the content's target audience, this preliminary work proposes a framework (Junior Guardian) designed to safeguard children's experiences as streaming platform users.Specifically, this framework should incorporate a context-aware recommender system to automate and enhance the objectivity of advertisement suitability assessments.

Unit testing is an essential but resource-intensive step in software development, ensuring individual code units function correctly. This paper introduces AgoneTest, an automated evaluation framework for Large Language Model-generated (LLM) unit tests in Java. AgoneTest does not aim to propose a novel test generation algorithm; rather, it supports researchers and developers in comparing different LLMs and prompting strategies through a standardized end-to-end evaluation pipeline under realistic conditions. We introduce the CLASSES2TEST dataset, which maps Java classes under test to their corresponding test classes, and a framework that integrates advanced evaluation metrics, such as mutation score and test smells, for a comprehensive assessment. Experimental results show that, for the subset of tests that compile, LLM-generated tests can match or exceed human-written tests in terms of coverage and defect detection. Our findings also demonstrate that enhanced prompting strategies contribute to test quality. AgoneTest clarifies the potential of LLMs in software testing and offers insights for future improvements in model design, prompt engineering, and testing practices.

In practice, requirements specification remains a critical challenge. The knowledge necessary to generate a specification can often be fragmented across diverse sources (e.g., meeting minutes, emails, and high-level product descriptions), making the process cumbersome and time-consuming. In this paper, we report our experience using large language models (LLMs) in an IT consulting company to automate the requirements specification process. In this company, requirements are specified using a Functional Design Specification (FDS), a document that outlines the functional requirements and features of a system, application, or process. We provide LLMs with a summary of the requirements elicitation documents and FDS templates, prompting them to generate Epic FDS (including high-level product descriptions) and user stories, which are subsequently compiled into a complete FDS document. We compared the correctness and quality of the FDS generated by three state-of-the-art LLMs against those produced by human analysts. Our results show that LLMs can help automate and standardize the requirements specification, reducing time and human effort. However, the quality of LLM-generated FDS highly depends on inputs and often requires human revision. Thus, we advocate for a synergistic approach in which an LLM serves as an effective drafting tool while human analysts provide the critical contextual and technical oversight necessary for high-quality requirements engineering (RE) documentation.

Increasing emissions due to urbanization pose a significant threat to human health. Air pollutants such as NO2, PM2.5, and PM10have a well-documented impact on quality of life and mortality risk. Numerous studies are currently investigating the correlation between air pollution and adverse health effects, highlighting the risks associated with exposure to such emissions. In this context, models capable of predicting mortality by leveraging information on pollution and socioeconomic factors are essential for prevention. This work contributes to this field by using Machine Learning (ML) to predict mortality in the Municipality of Taranto (Italy). We propose an eXtreme Gradient Boosting (XGBoost) regression model that uses air pollution levels and socioeconomic data to assess mortality risk over a grid-based map of the examined city. Our study aligns with state-of-the-art findings, further expanding the understanding of the correlation between emissions, economic conditions, and mortality. The proposed model achieves a Root Mean Square Error (RMSE) of 1.61 on the test set, demonstrating the effectiveness of this approach. Additionally, eXplainable Artificial Intelligence (XAI) analysis is conducted using Shapley values to gain insights into the model’s decision-making process and better understand the importance of each feature in predicting mortality risk.

Maintaining a consistent brand identity across a global network of retail stores while adhering to local constraints has long challenged Visual Merchandisers.Legacy processes, often reliant on subjective "by-eye" adjustments, can drive up operational costs and lead to inconsistent in-store execution.We formalize a user modeling framework implementing a multi-criteria utility function that balances brand identity and operational overhead.We integrated our framework in a 3D virtual tour design platform, deploying it in the ecosystem of OVS, a global fashion firm.Through a preliminary user study, we showcase that our solution enables lower iteration cycles and decreases store-to-store discrepancies.

The rapid digitalization of the fashion industry has transformed marketing strategies, emphasizing the need for personalized and adaptive advertising content.This paper presents a case study on fine-tuning Large Language Models (LLMs) for fashion advertising, focusing on OVS, a major Italian fashion retailer.By leveraging real-world marketing data from OVS's newsletters and social media campaigns, we developed a fine-tuned model capable of generating engaging and stylistically coherent promotional content.To evaluate the effectiveness of this approach, we introduced a novel brand compliance index, measuring the alignment of AI-generated text with key branding requirements, such as audience targeting, event specificity, and platform appropriateness.Experimental results show that the fine-tuned model achieved a compliance score of 0.82, significantly outperforming the baseline model (0.63).Although this approach introduces a minor increase in generation latency, the enhanced alignment with brand identity justifies its use in marketing automation.Our findings highlight the potential of fine-tuned LLMs to streamline advertising content generation while maintaining brand consistency, offering valuable insights for the future of AI-driven digital marketing.

In the ever-expanding landscape of Artificial Intelligence (AI), where innovation thrives and new products and services are continuously being delivered, ensuring that AI systems are designed and developed responsibly throughout their entire lifecycle is crucial. To this end, several AI ethics principles and guidelines have been issued to which AI systems should conform. Nevertheless, relying solely on high-level AI ethics principles is far from sufficient to ensure the responsible engineering of AI systems. In this field, AI professionals often navigate by sight. Indeed, while recommendations promoting Trustworthy AI (TAI) exist, they are often high-level statements difficult to translate into concrete implementation strategies. Currently, there is a significant gap between high-level AI ethics principles and low-level concrete practices for AI professionals. To address this challenge, our work presents an experience report where we develop a novel holistic framework for Trustworthy AI --- designed to bridge the gap between theory and practice --- and report insights from its application in an industrial case study. The framework builds up from the results of a systematic review of the state of the practice as well as a survey and think-aloud interviews with 34 AI practitioners. The framework, unlike most of the ones in literature, is designed to provide actionable guidelines and tools to support different types of stakeholders throughout the entire Software Development Life Cycle (SDLC). Our goal is to empower AI professionals to confidently navigate the ethical dimensions of TAI through practical insights, ensuring that the vast potential of AI is exploited responsibly for the benefit of society as a whole.

Recently, there has been growing attention on behalf of both academic and practice communities towards the ability of Artificial Intelligence (AI) systems to operate responsibly and ethically. As a result, a plethora of frameworks and guidelines have appeared to support practitioners in implementing Trustworthy AI applications (TAI). However, little research has been done to investigate whether such frameworks are being used and how. In this work, we study the vision AI practitioners have on TAI principles, how they address them, and what they would like to have – in terms of tools, knowledge, or guidelines – when they attempt to incorporate such principles into the systems they develop. Through a survey and semi-structured interviews, we systematically investigated practitioners’ challenges and needs in developing TAI systems. Based on these practical findings, we highlight recommendations to help AI practitioners develop Trustworthy AI applications.

Software correctness is crucial, with unit testing playing an indispensable role in the software development lifecycle. However, creating unit tests is time-consuming and costly, underlining the need for automation. Leveraging Large Language Models (LLMs) for unit test generation is a promising solution, but existing studies focus on simple, small-scale scenarios, leaving a gap in understanding LLMs' performance in real-world applications, particularly regarding integration and assessment efficacy at scale. Here, we present AgoneTest, a system focused on automatically generating and evaluating complex class-level test suites. Our contributions include a scalable automated system, a newly developed dataset for rigorous evaluation, and a detailed methodology for test quality assessment.

Recommender systems, though widely used, often struggle to engage users effectively. While deep learning methods have enhanced connections between users and items, they often neglect the user’s perspective. Knowledge-based approaches, utilizing knowledge graphs, offer semantic insights and address issues like knowledge graph embeddings, hybrid recommendation, and interpretable recommendation. More recently, neural-symbolic systems, combining data-driven and symbolic techniques, show promise in recommendation systems, especially when used with knowledge graphs. Moreover, content features become vital in conversational recommender systems, which demand multi-turn dialogues. Recent literature highlights increasing interest in this area, particularly with the emergence of Large Language Models (LLMs), which excel in understanding user queries and generating recommendations in natural language. Sixth Knowledge-aware and Conversational Recommender Systems (KaRS) Workshop aims to disseminate advancements and discuss about challenges and opportunities.

Abstract Knowledge Graphs (KGs) have already proven their strength as a source of high-quality information for different tasks such as data integration, search, text summarization, and personalization. Another prominent research field that has been benefiting from the adoption of KGs is that of Recommender Systems (RSs). Feeding a RS with data coming from a KG improves recommendation accuracy, diversity, and novelty, and paves the way to the creation of interpretable models that can be used for explanations. This possibility of combining a KG with a RS raises the question whether such an addition can be performed in a plug-and-play fashion – also with respect to the recommendation domain – or whether each combination needs a careful evaluation. To investigate such a question, we consider all possible combinations of (i) three recommendation tasks (books, music, movies); (ii) three recommendation models fed with data from a KG (and in particular, a semantics-aware deep learning model, that we discuss in detail), compared with three baseline models without KG addition; (iii) two main encyclopedic KGs freely available on the Web: DBpedia and Wikidata. Supported by an extensive experimental evaluation, we show the final results in terms of accuracy and diversity of the various combinations, highlighting that the injection of knowledge does not always pay off. Moreover, we show how the choice of the KG, and the form of data in it, affect the results, depending on the recommendation domain and the learning model.

In the last years, the raise of Artificial Intelligence (AI), and its pervasiveness in our lives, has sparked a flourishing debate about the ethical principles that should lead its implementation and use in society. Driven by these concerns, we conduct a rapid review of several frameworks providing principles, guidelines, and/or tools to help practitioners in the development and deployment of Responsible AI (RAI) applications. We map each framework w.r.t. the different Software Development Life Cycle (SDLC) phases discovering that most of these frameworks fall just in the Requirements Elicitation phase, leaving the other phases uncovered. Very few of these frameworks offer supporting tools for practitioners, and they are mainly provided by private companies. Our results reveal that there is not a "catching-all" framework supporting both technical and non-technical stakeholders in the implementation of real-world projects. Our findings highlight the lack of a comprehensive framework encompassing all RAI principles and all (SDLC) phases that could be navigated by users with different skill sets and with different goals.

Current AI regulations require discarding sensitive features (e.g., gender, race, religion) in the algorithm’s decision-making process to prevent unfair outcomes. However, even without sensitive features in the training set, algorithms can persist in discrimination. Indeed, when sensitive features are omitted (fairness under unawareness), they could be inferred through non-linear relations with the so-called proxy features. In this work, we propose a way to reveal the potential hidden bias of a machine learning model that can persist even when sensitive features are discarded. This study shows that it is possible to unveil whether the black-box predictor is still biased by exploiting counterfactual reasoning. In detail, when the predictor provides a negative classification outcome, our approach first builds counterfactual examples for a discriminated user category to obtain a positive outcome. Then, the same counterfactual samples feed an external classifier (that targets a sensitive feature) that reveals if the modifications to the user characteristics needed for a positive outcome moved the individual to the non-discriminated group. When this occurs, it could be a warning sign for discriminatory behavior in the decision process. Furthermore, we leverage the deviation of counterfactuals from the original sample to determine which features are proxies of specific sensitive information. Our experiments show that, even if the model is trained without sensitive features, it often suffers discriminatory biases.

Recommender systems have become ubiquitous in daily life, but their limitations in interacting with human users have become evident. Deep learning approaches have led to the development of data-driven algorithms that identify connections between users and items, but they often miss a critical actor in the loop - the end-user. Knowledge-based approaches are gaining attention due to the availability of knowledge-graphs, such as DBpedia and Wikidata, which provide semantics-aware information on different knowledge domains. These approaches are being used for recommendation and challenges such as knowledge graph embeddings, hybrid recommendation, and interpretable recommendation. Moreover, the emergence of neural-symbolic systems, which combine data-driven and symbolic methods, can significantly improve recommendation systems. A growing number of research papers on such topics demonstrate the growing interest and research potential of these systems. Furthermore, content features become crucial when interaction requires it. The development of conversational recommender systems presents new challenges, as they require multi-turn dialogues between users and systems, blurring the line between recommendation and retrieval. Evaluation of these systems goes beyond simple accuracy metrics and is hampered by the limited availability of datasets. While research and development into conversational recommender systems has been less prominent in the past, recent literature shows growing interest and potential for these systems.

In the last few years, a renewed interest of the research community in conversational recommender systems (CRSs) has been emerging. This is likely due to the massive proliferation of Digital Assistants (DAs) such as Amazon Alexa, Siri, or Google Assistant that are revolutionizing the way users interact with machines. DAs allow users to execute a wide range of actions through an interaction mostly based on natural language utterances. However, although DAs are able to complete tasks such as sending texts, making phone calls, or playing songs, they still remain at an early stage in terms of their recommendation capabilities via a conversation. In addition, we have been witnessing the advent of increasingly precise and powerful recommendation algorithms and techniques able to effectively assess users’ tastes and predict information that may be of interest to them. Most of these approaches rely on the collaborative paradigm (often exploiting machine learning techniques) and neglect the huge amount of knowledge, both structured and unstructured, describing the domain of interest of a recommendation engine. Although very effective in predicting relevant items, collaborative approaches miss some very interesting features that go beyond the accuracy of results and move in the direction of providing novel and diverse results as well as generating explanations for recommended items. Knowledge-aware side information becomes crucial when a conversational interaction is implemented, in particular for preference elicitation, explanation, and critiquing steps.

Over the years, model-based approaches have shown their effectiveness in computing recommendation lists in different domains and settings. By relying on the computation of latent factors, they can recommend items with a very high level of accuracy. Unfortunately, when moving to the latent space, even if the model embeds content-based information, we miss references to the actual semantics of the recommended item. It makes the interpretation of the recommendation process non-trivial. In this paper, we show how to initialize latent factors in Factorization Machines by using semantic features coming from knowledge graphs to train an interpretable model, which is, in turn, able to provide recommendations with a high level of accuracy. In the presented approach, semantic features are injected into the learning process to retain the original informativeness of the items available in the dataset. By relying on the information encoded in the original knowledge graph, we also propose two metrics to evaluate the semantic accuracy and robustness of knowledge-aware interpretability. An extensive experimental evaluation on six different datasets shows the effectiveness of the interpretable model in terms of both accuracy and diversity of recommendation results and interpretability robustness.

Hyper-parameters tuning is a crucial task to make a model perform at its best. However, despite the well-established methodologies, some aspects of the tuning remain unexplored. As an example, it may affect not just accuracy but also novelty as well as it may depend on the adopted dataset. Moreover, sometimes it could be sufficient to concentrate on a single parameter only (or a few of them) instead of their overall set. In this paper we report on our investigation on hyper-parameters tuning by performing an extensive 10-Folds Cross-Validation on MovieLens and Amazon Movies for three well-known baselines: User-kNN, Item-kNN, BPR-MF. We adopted a grid search strategy considering approximately 15 values for each parameter, and we then evaluated each combination of parameters in terms of accuracy and novelty. We investigated the discriminative power of nDCG, Precision, Recall, MRR, EFD, EPC, and, finally, we analyzed the role of parameters on model evaluation for Cross-Validation.

SUMMARY Feature modeling an attractive technique for capturing commonality as well as variability within an application domain for generative programming and software product line engineering. Feature models symbolize an overarching representation of the possible application configuration space, and can hence be customized based on specific domain requirements and stakeholder goals. Most interactive or semi‐automated feature model customization processes neglect the need to have a holistic approach towards the integration and satisfaction of the stakeholder's soft and hard constraints, and the application‐domain integrity constraints. In this paper, we will show how the structure and constraints of a feature model can be modeled uniformly through Propositional Logic extended with concrete domains, called Pscr (𝒩). Furthermore, we formalize the representation of soft constraints in fuzzy 𝒫(𝒩) and explain how semi‐automated feature model customization is performed in this setting. The model configuration derivation process that we propose respects the soundness and completeness properties. Copyright © 2011 John Wiley & Sons, Ltd.

One of the main problems in online advertising is to display ads which are relevant and appropriate w.r.t. what the user is looking for. Often search engines fail to reach this goal as they do not consider semantics attached to keywords. In this paper we propose a system that tackles the problem by two different angles: help (i) advertisers to create more efficient ads campaigns and (ii) ads providers to properly match ads content to keywords in search engines. We exploit semantic relations stored in the DBpedia dataset and use an hybrid ranking system to rank keywords and to expand queries formulated by the user. Inputs of our ranking system are (i) the DBpedia dataset; (ii) external information sources such as classical search engine results and social tagging systems. We compare our approach with other RDF similarity measures, proving the validity of our algorithm with an extensive evaluation involving real users.

Non-standard reasoning in Description Logics (DLs) comprises computing a Least Common Subsumer (LCS), a Concept Difference, a Concept Unifier, or an Interpolant Concept, to name a few. Although some reasoning services have been unified already (e.g., LCS and Most Specific Concept), the definition of non-standard problems and the computation that solve them are very different from each other. We propose to unify the definitions of non-standard services as special Second-order sentences in DLs; when the solution concepts are optimal with respect to some preferences, a fixpoint replaces the Second-order quantification. Moreover, we propose to combine the well-known Tableaux calculi for DLs with rules that compute substitutions of Concept Variables. We prove soundness and completeness of the combined calculus and we give a sufficient condition for termination, which covers some non-trivial cases.

This paper presents a visual application in the framework of semantic-enabled e-marketplaces aimed at fully exploiting semantics of supply/demand descriptions in B2C and C2C e-marketplaces. Distinguishing aspects of the framework include logic-based explanation of request results, semantic ranking of matchmaking results, logic-based request refinement. The visual user interface has been designed and implemented to be immediate and simple, and it requires no knowledge of any logic principle to be fully used.

In this paper we present a knowledge-based approach to the elicitation of information from advertisements, in the framework of a semantic-enabled marketplace. The elicited information can be used for advertisements enriching and refining, without requiring users thorough knowledge of the domain, and to determine a logicbased exact match. The approach exploits non-standard inference services in Description Logics, namely Abduction and Contraction, to tackle a typical problem of semantic-enabled marketplaces, that is the difficulty the average or casual user has in exploiting all the knowledge expressed in an e-commerce domain, which appears necessary to issue requests. We present an algorithm, which returns the set of concepts not included in the request-that can be used for query refinement- and more interesting what is still missing for each available supply, to obtain an exact, bidirectional, match.

We propose a framework and polynomial algorithms for semantic-based automated Web service orchestration, fully compliant with semantic Web technologies. The approach exploits the recently proposed concept abduction inference service in description logics to solve concept covering problems. We present how the proposed approach deals with not exact solutions, computing an approximate orchestration with respect to an agent request modeled using a significant subset of OWL-DL.