Search

Large language models (LLMs) have shown promising capabilities in healthcare analysis but face several challenges like hallucinations, parroting, and bias manifestation. These challenges are exacerbated in complex, sensitive, and low-resource domains. Therefore, in this work we introduce IC-AnnoMI, an expert-annotated motivational interviewing (MI) dataset built upon AnnoMI by generating in-context conversational dialogues leveraging LLMs, particularly ChatGPT. IC-AnnoMI employs targeted prompts accurately engineered through cues and tailored information, taking into account therapy style (empathy, reflection), contextual relevance, and false semantic change. Subsequently, the dialogues are annotated by experts, strictly adhering to the Motivational Interviewing Skills Code (MISC), focusing on both the psychological and linguistic dimensions of MI dialogues. We comprehensively evaluate the IC-AnnoMI dataset and ChatGPT's emotional reasoning ability and understanding of domain intricacies by modeling novel classification tasks employing several classical machine learning and current state-of-the-art transformer approaches. Finally, we discuss the effects of progressive prompting strategies and the impact of augmented data in mitigating the biases manifested in IC-AnnoM. Our contributions provide the MI community with not only a comprehensive dataset but also valuable insights for using LLMs in empathetic text generation for conversational therapy in supervised settings., Comment: International Conference on Natural Language Processing and Artificial Intelligence for Cyber Security (NLPAICS) 2024

Diffusion-based recommender systems have recently proven to outperform traditional generative recommendation approaches, such as variational autoencoders and generative adversarial networks. Nevertheless, the machine learning literature has raised several concerns regarding the possibility that diffusion models, while learning the distribution of data samples, may inadvertently carry information bias and lead to unfair outcomes. In light of this aspect, and considering the relevance that fairness has held in recommendations over the last few decades, we conduct one of the first fairness investigations in the literature on DiffRec, a pioneer approach in diffusion-based recommendation. First, we propose an experimental setting involving DiffRec (and its variant L-DiffRec) along with nine state-of-the-art recommendation models, two popular recommendation datasets from the fairness-aware literature, and six metrics accounting for accuracy and consumer/provider fairness. Then, we perform a twofold analysis, one assessing models' performance under accuracy and recommendation fairness separately, and the other identifying if and to what extent such metrics can strike a performance trade-off. Experimental results from both studies confirm the initial unfairness warnings but pave the way for how to address them in future research directions.

Recent developments in recommendation have harnessed the collaborative power of graph neural networks (GNNs) in learning users' preferences from user-item networks. Despite emerging regulations addressing fairness of automated systems, unfairness issues in graph collaborative filtering remain underexplored, especially from the consumer's perspective. Despite numerous contributions on consumer unfairness, only a few of these works have delved into GNNs. A notable gap exists in the formalization of the latest mitigation algorithms, as well as in their effectiveness and reliability on cutting-edge models. This paper serves as a solid response to recent research highlighting unfairness issues in graph collaborative filtering by reproducing one of the latest mitigation methods. The reproduced technique adjusts the system fairness level by learning a fair graph augmentation. Under an experimental setup based on 11 GNNs, 5 non-GNN models, and 5 real-world networks across diverse domains, our investigation reveals that fair graph augmentation is consistently effective on high-utility models and large datasets. Experiments on the transferability of the fair augmented graph open new issues for future recommendation studies. Source code: https://github.com/jackmedda/FA4GCF.

In this paper, we introduce the Dynamic Modularity-Spectral Algorithm (DynMSA), a novel approach to identify clusters of stocks with high intra-cluster correlations and low inter-cluster correlations by combining Random Matrix Theory with modularity optimisation and spectral clustering. The primary objective is to uncover hidden market structures and find diversifiers based on return correlations, thereby achieving a more effective risk-reducing portfolio allocation. We applied DynMSA to constituents of the S&P 500 and compared the results to sector- and market-based benchmarks. Besides the conception of this algorithm, our contributions further include implementing a sector-based calibration for modularity optimisation and a correlation-based distance function for spectral clustering. Testing revealed that DynMSA outperforms baseline models in intra- and inter-cluster correlation differences, particularly over medium-term correlation look-backs. It also identifies stable clusters and detects regime changes due to exogenous shocks, such as the COVID-19 pandemic. Portfolios constructed using our clusters showed higher Sortino and Sharpe ratios, lower downside volatility, reduced maximum drawdown and higher annualised returns compared to an equally weighted market benchmark.

Identification of market abuse is an extremely complicated activity that requires the analysis of large and complex datasets. We propose an unsupervised machine learning method for contextual anomaly detection, which allows to support market surveillance aimed at identifying potential insider trading activities. This method lies in the reconstruction-based paradigm and employs principal component analysis and autoencoders as dimensionality reduction techniques. The only input of this method is the trading position of each investor active on the asset for which we have a price sensitive event (PSE). After determining reconstruction errors related to the trading profiles, several conditions are imposed in order to identify investors whose behavior could be suspicious of insider trading related to the PSE. As a case study, we apply our method to investor resolved data of Italian stocks around takeover bids., Comment: This work has been submitted to the IEEE for possible publication

Efforts in the recommendation community are shifting from the sole emphasis on utility to considering beyond-utility factors, such as fairness and robustness. Robustness of recommendation models is typically linked to their ability to maintain the original utility when subjected to attacks. Limited research has explored the robustness of a recommendation model in terms of fairness, e.g., the parity in performance across groups, under attack scenarios. In this paper, we aim to assess the robustness of graph-based recommender systems concerning fairness, when exposed to attacks based on edge-level perturbations. To this end, we considered four different fairness operationalizations, including both consumer and provider perspectives. Experiments on three datasets shed light on the impact of perturbations on the targeted fairness notion, uncovering key shortcomings in existing evaluation protocols for robustness. As an example, we observed perturbations affect consumer fairness on a higher extent than provider fairness, with alarming unfairness for the former. Source code: https://github.com/jackmedda/CPFairRobust

In recommendation literature, explainability and fairness are becoming two prominent perspectives to consider. However, prior works have mostly addressed them separately, for instance by explaining to consumers why a certain item was recommended or mitigating disparate impacts in recommendation utility. None of them has leveraged explainability techniques to inform unfairness mitigation. In this paper, we propose an approach that relies on counterfactual explanations to augment the set of user-item interactions, such that using them while inferring recommendations leads to fairer outcomes. Modeling user-item interactions as a bipartite graph, our approach augments the latter by identifying new user-item edges that not only can explain the original unfairness by design, but can also mitigate it. Experiments on two public data sets show that our approach effectively leads to a better trade-off between fairness and recommendation utility compared with state-of-the-art mitigation procedures. We further analyze the characteristics of added edges to highlight key unfairness patterns. Source code available at https://github.com/jackmedda/RS-BGExplainer/tree/cikm2023., Comment: Accepted as a short paper at CIKM 2023

Nowadays, research into personalization has been focusing on explainability and fairness. Several approaches proposed in recent works are able to explain individual recommendations in a post-hoc manner or by explanation paths. However, explainability techniques applied to unfairness in recommendation have been limited to finding user/item features mostly related to biased recommendations. In this paper, we devised a novel algorithm that leverages counterfactuality methods to discover user unfairness explanations in the form of user-item interactions. In our counterfactual framework, interactions are represented as edges in a bipartite graph, with users and items as nodes. Our bipartite graph explainer perturbs the topological structure to find an altered version that minimizes the disparity in utility between the protected and unprotected demographic groups. Experiments on four real-world graphs coming from various domains showed that our method can systematically explain user unfairness on three state-of-the-art GNN-based recommendation models. Moreover, an empirical evaluation of the perturbed network uncovered relevant patterns that justify the nature of the unfairness discovered by the generated explanations. The source code and the preprocessed data sets are available at https://github.com/jackmedda/RS-BGExplainer.

In recent years, advances in immersive multimedia technologies, such as extended reality (XR) technologies, have led to more realistic and user-friendly devices. However, these devices are often bulky and uncomfortable, still requiring tether connectivity for demanding applications. The deployment of the fifth generation of telecommunications technologies (5G) has set the basis for XR offloading solutions with the goal of enabling lighter and fully wearable XR devices. In this paper, we present a traffic dataset for two demanding XR offloading scenarios that are complementary to those available in the current state of the art, captured using a fully developed end-to-end XR offloading solution. We also propose a set of accurate traffic models for the proposed scenarios based on the captured data, accompanied by a simple and consistent method to generate synthetic data from the fitted models. Finally, using an open-source 5G radio access network (RAN) emulator, we validate the models both at the application and resource allocation layers. Overall, this work aims to provide a valuable contribution to the field with data and tools for designing, testing, improving, and extending XR offloading solutions in academia and industry., Comment: Submitted to IEEE Transactions on Mobile Computing

Identifying market abuse activity from data on investors' trading activity is very challenging both for the data volume and for the low signal to noise ratio. Here we propose two complementary unsupervised machine learning methods to support market surveillance aimed at identifying potential insider trading activities. The first one uses clustering to identify, in the vicinity of a price sensitive event such as a takeover bid, discontinuities in the trading activity of an investor with respect to his/her own past trading history and on the present trading activity of his/her peers. The second unsupervised approach aims at identifying (small) groups of investors that act coherently around price sensitive events, pointing to potential insider rings, i.e. a group of synchronised traders displaying strong directional trading in rewarding position in a period before the price sensitive event. As a case study, we apply our methods to investor resolved data of Italian stocks around takeover bids., Comment: 42 pages, 16 Figures

This paper investigates how Covid mobility restrictions impacted the population of investors of the Italian stock market. The analysis tracks the trading activity of individual investors in Italian stocks in the period January 2019-September 2021, investigating how their composition and the trading activity changed around the Covid-19 lockdown period (March 9 - May 19, 2020) and more generally in the period of the pandemic. The results pinpoint that the lockdown restriction was accompanied by a surge in interest toward stock market, as testified by the trading volume by households. Given the generically falling prices during the lockdown, the households, which are typically contrarian, were net buyers, even if less than expected from their trading activity in 2019. This can be explained by the arrival, during the lockdown, of a group of about 185k new investors (i.e. which had never traded since January 2019) which were on average ten year younger and with a larger fraction of males than the pre-lockdown investors. By looking at the gross P&L, there is clear evidence that these new investors were more skilled in trading. There are thus indications that the lockdown, and more generally the Covid pandemic, created a sort of regime change in the population of financial investors., Comment: 25 pages, 16 figures

In this paper we report on the initial activities carried out within a collaboration between Consob and Sapienza University. We focus on Information Extraction from documents describing financial instruments. We discuss how we automate this task, via both rule-based and machine learning-based methods and provide our first results.

Enabling non-discrimination for end-users of recommender systems by introducing consumer fairness is a key problem, widely studied in both academia and industry. Current research has led to a variety of notions, metrics, and unfairness mitigation procedures. The evaluation of each procedure has been heterogeneous and limited to a mere comparison with models not accounting for fairness. It is hence hard to contextualize the impact of each mitigation procedure w.r.t. the others. In this paper, we conduct a systematic analysis of mitigation procedures against consumer unfairness in rating prediction and top-n recommendation tasks. To this end, we collected 15 procedures proposed in recent top-tier conferences and journals. Only 8 of them could be reproduced. Under a common evaluation protocol, based on two public data sets, we then studied the extent to which recommendation utility and consumer fairness are impacted by these procedures, the interplay between two primary fairness notions based on equity and independence, and the demographic groups harmed by the disparate impact. Our study finally highlights open challenges and future directions in this field. The source code is available at https://github.com/jackmedda/C-Fairness-RecSys., Comment: Accepted at the 44th European Conference on Information Retrieval (ECIR 2022)

The human voice conveys unique characteristics of an individual, making voice biometrics a key technology for verifying identities in various industries. Despite the impressive progress of speaker recognition systems in terms of accuracy, a number of ethical and legal concerns has been raised, specifically relating to the fairness of such systems. In this paper, we aim to explore the disparity in performance achieved by state-of-the-art deep speaker recognition systems, when different groups of individuals characterized by a common sensitive attribute (e.g., gender) are considered. In order to mitigate the unfairness we uncovered by means of an exploratory study, we investigate whether balancing the representation of the different groups of individuals in the training set can lead to a more equal treatment of these demographic groups. Experiments on two state-of-the-art neural architectures and a large-scale public dataset show that models trained with demographically-balanced training sets exhibit a fairer behavior on different groups, while still being accurate. Our study is expected to provide a solid basis for instilling beyond-accuracy objectives (e.g., fairness) in speaker recognition., Comment: Accepted at the 2020 European Symposium on Software Engineering (ESSE 2020)