Collecting valuable consumer data: Motivating consumers to disclose personal information

Collecting and analyzing consumer data is essential in today’s data-driven business environment. However, consumers are becoming more aware of the value of the information they can provide to companies, thereby being more reluctant to share it for free. Therefore, companies need to find ways to motivate consumers to disclose personal information. The main research question of the study was formed as “How can companies motivate consumers to disclose personal information?” and it was further divided into two subquestions: 1) What types of benefits motivate consumers to disclose personal information? 2) How does the disclosure context affect the consumers’ information disclosure behavior? The conceptual framework consisted of a classification of extrinsic and intrinsic benefits, and moderating factors, which were recognized on the basis of prior research in the field. The study was conducted by using qualitative research methods. The primary data was collected by interviewing ten representatives from eight companies. The data was analyzed and reported according to predetermined themes. The findings of the study confirm that consumers can be motivated to disclose personal information by offering different types of extrinsic (monetary saving, time saving, self-enhancement, and social adjustment) and intrinsic (novelty, pleasure, and altruism) benefits. However, not all the benefits are equally useful ways to convince the customer to disclose information. Moreover, different factors in the disclosure context can either alleviate or increase the effectiveness of the benefits and the consumers’ motivation to disclose personal information. Such factors include the consumer’s privacy concerns, perceived trust towards the company, the relevancy of the requested information, personalization, website elements (especially security, usability, and aesthetics of a website), and the consumer’s shopping motivation. This study has several contributions. It is essential that companies recognize the most attractive benefits regarding their business and their customers, and that they understand how the disclosure context affects the consumer’s information disclosure behavior. The likelihood of information disclosure can be increased, for example, by offering benefits that meet the consumers’ needs and preferences, improving the relevancy of the asked information, stating the reasons for data collection, creating and maintaining a trustworthy image of the company, and enhancing the quality of the company’s website.

Capability Matrix for Open Data

Part 14: Interoperability and Integration

A Bayesian network dealing with measurements and residuals for system monitoring

International audience

WordPress as a framework for automated data capture, filtering and structuring processes

The Exhibitium Project , awarded by the BBVA Foundation, is a data-driven project developed by an international consortium of research groups . One of its main objectives is to build a prototype that will serve as a base to produce a platform for the recording and exploitation of data about art-exhibitions available on the Internet . Therefore, our proposal aims to expose the methods, procedures and decision-making processes that have governed the technological implementation of this prototype, especially with regard to the reuse of WordPress (WP) as development framework.

Multivalent reuse of web data about temporary art exhibitions: The Exhibitium Project

Our proposal aims to display the analysis techniques, methodologies as well as the most relevant results expected within the Exhibitium project framework (http://www.exhibitium.com). Awarded by the BBVA Foundation, the Exhibitium project is being developed by an international consortium of several research groups . Its main purpose is to build a comprehensive and structured data repository about temporary art exhibitions, captured from the web, to make them useful and reusable in various domains through open and interoperable data systems.

Business Process Management and Process Mining within a Real Business Environment: An Empirical Analysis of Event Logs Data in a Consulting Project

Il presente elaborato esplora l’attitudine delle organizzazioni nei confronti dei processi di business che le sostengono: dalla semi-assenza di struttura, all’organizzazione funzionale, fino all’avvento del Business Process Reengineering e del Business Process Management, nato come superamento dei limiti e delle problematiche del modello precedente. All’interno del ciclo di vita del BPM, trova spazio la metodologia del process mining, che permette un livello di analisi dei processi a partire dagli event data log, ossia dai dati di registrazione degli eventi, che fanno riferimento a tutte quelle attività supportate da un sistema informativo aziendale. Il process mining può essere visto come naturale ponte che collega le discipline del management basate sui processi (ma non data-driven) e i nuovi sviluppi della business intelligence, capaci di gestire e manipolare l’enorme mole di dati a disposizione delle aziende (ma che non sono process-driven). Nella tesi, i requisiti e le tecnologie che abilitano l’utilizzo della disciplina sono descritti, cosi come le tre tecniche che questa abilita: process discovery, conformance checking e process enhancement. Il process mining è stato utilizzato come strumento principale in un progetto di consulenza da HSPI S.p.A. per conto di un importante cliente italiano, fornitore di piattaforme e di soluzioni IT. Il progetto a cui ho preso parte, descritto all’interno dell’elaborato, ha come scopo quello di sostenere l’organizzazione nel suo piano di improvement delle prestazioni interne e ha permesso di verificare l’applicabilità e i limiti delle tecniche di process mining. Infine, nell’appendice finale, è presente un paper da me realizzato, che raccoglie tutte le applicazioni della disciplina in un contesto di business reale, traendo dati e informazioni da working papers, casi aziendali e da canali diretti. Per la sua validità e completezza, questo documento è stata pubblicato nel sito dell'IEEE Task Force on Process Mining.

Network Construction and Graph Theoretical Analysis of Functional Language Networks in Pediatric Epilepsy

This dissertation introduces a new approach for assessing the effects of pediatric epilepsy on the language connectome. Two novel data-driven network construction approaches are presented. These methods rely on connecting different brain regions using either extent or intensity of language related activations as identified by independent component analysis of fMRI data. An auditory description decision task (ADDT) paradigm was used to activate the language network for 29 patients and 30 controls recruited from three major pediatric hospitals. Empirical evaluations illustrated that pediatric epilepsy can cause, or is associated with, a network efficiency reduction. Patients showed a propensity to inefficiently employ the whole brain network to perform the ADDT language task; on the contrary, controls seemed to efficiently use smaller segregated network components to achieve the same task. To explain the causes of the decreased efficiency, graph theoretical analysis was carried out. The analysis revealed no substantial global network feature differences between the patient and control groups. It also showed that for both subject groups the language network exhibited small-world characteristics; however, the patient’s extent of activation network showed a tendency towards more random networks. It was also shown that the intensity of activation network displayed ipsilateral hub reorganization on the local level. The left hemispheric hubs displayed greater centrality values for patients, whereas the right hemispheric hubs displayed greater centrality values for controls. This hub hemispheric disparity was not correlated with a right atypical language laterality found in six patients. Finally it was shown that a multi-level unsupervised clustering scheme based on self-organizing maps, a type of artificial neural network, and k-means was able to fairly and blindly separate the subjects into their respective patient or control groups. The clustering was initiated using the local nodal centrality measurements only. Compared to the extent of activation network, the intensity of activation network clustering demonstrated better precision. This outcome supports the assertion that the local centrality differences presented by the intensity of activation network can be associated with focal epilepsy.

Classi cation of new electricity customers based on surveys and smart metering data

This paper proposes a process for the classifi cation of new residential electricity customers. The current state of the art is extended by using a combination of smart metering and survey data and by using model-based feature selection for the classifi cation task. Firstly, the normalized representative consumption profi les of the population are derived through the clustering of data from households. Secondly, new customers are classifi ed using survey data and a limited amount of smart metering data. Thirdly, regression analysis and model-based feature selection results explain the importance of the variables and which are the drivers of diff erent consumption profi les, enabling the extraction of appropriate models. The results of a case study show that the use of survey data signi ficantly increases accuracy of the classifi cation task (up to 20%). Considering four consumption groups, more than half of the customers are correctly classifi ed with only one week of metering data, with more weeks the accuracy is signifi cantly improved. The use of model-based feature selection resulted in the use of a signifi cantly lower number of features allowing an easy interpretation of the derived models.

Hybrid Artificial Intelligence to Extract Patterns and Rules from Argumentative and Legal Texts

This Thesis is composed of a collection of works written in the period 2019-2022, whose aim is to find methodologies of Artificial Intelligence (AI) and Machine Learning to detect and classify patterns and rules in argumentative and legal texts. We define our approach “hybrid”, since we aimed at designing hybrid combinations of symbolic and sub-symbolic AI, involving both “top-down” structured knowledge and “bottom-up” data-driven knowledge. A first group of works is dedicated to the classification of argumentative patterns. Following the Waltonian model of argument and the related theory of Argumentation Schemes, these works focused on the detection of argumentative support and opposition, showing that argumentative evidences can be classified at fine-grained levels without resorting to highly engineered features. To show this, our methods involved not only traditional approaches such as TFIDF, but also some novel methods based on Tree Kernel algorithms. After the encouraging results of this first phase, we explored the use of a some emerging methodologies promoted by actors like Google, which have deeply changed NLP since 2018-19 — i.e., Transfer Learning and language models. These new methodologies markedly improved our previous results, providing us with best-performing NLP tools. Using Transfer Learning, we also performed a Sequence Labelling task to recognize the exact span of argumentative components (i.e., claims and premises), thus connecting portions of natural language to portions of arguments (i.e., to the logical-inferential dimension). The last part of our work was finally dedicated to the employment of Transfer Learning methods for the detection of rules and deontic modalities. In this case, we explored a hybrid approach which combines structured knowledge coming from two LegalXML formats (i.e., Akoma Ntoso and LegalRuleML) with sub-symbolic knowledge coming from pre-trained (and then fine-tuned) neural architectures.

Variational and learning models for image and time series inverse problems

Inverse problems are at the core of many challenging applications. Variational and learning models provide estimated solutions of inverse problems as the outcome of specific reconstruction maps. In the variational approach, the result of the reconstruction map is the solution of a regularized minimization problem encoding information on the acquisition process and prior knowledge on the solution. In the learning approach, the reconstruction map is a parametric function whose parameters are identified by solving a minimization problem depending on a large set of data. In this thesis, we go beyond this apparent dichotomy between variational and learning models and we show they can be harmoniously merged in unified hybrid frameworks preserving their main advantages. We develop several highly efficient methods based on both these model-driven and data-driven strategies, for which we provide a detailed convergence analysis. The arising algorithms are applied to solve inverse problems involving images and time series. For each task, we show the proposed schemes improve the performances of many other existing methods in terms of both computational burden and quality of the solution. In the first part, we focus on gradient-based regularized variational models which are shown to be effective for segmentation purposes and thermal and medical image enhancement. We consider gradient sparsity-promoting regularized models for which we develop different strategies to estimate the regularization strength. Furthermore, we introduce a novel gradient-based Plug-and-Play convergent scheme considering a deep learning based denoiser trained on the gradient domain. In the second part, we address the tasks of natural image deblurring, image and video super resolution microscopy and positioning time series prediction, through deep learning based methods. We boost the performances of supervised, such as trained convolutional and recurrent networks, and unsupervised deep learning strategies, such as Deep Image Prior, by penalizing the losses with handcrafted regularization terms.

Towards Unstructured Knowledge Integration in Natural Language Processing

In the last decades, Artificial Intelligence has witnessed multiple breakthroughs in deep learning. In particular, purely data-driven approaches have opened to a wide variety of successful applications due to the large availability of data. Nonetheless, the integration of prior knowledge is still required to compensate for specific issues like lack of generalization from limited data, fairness, robustness, and biases. In this thesis, we analyze the methodology of integrating knowledge into deep learning models in the field of Natural Language Processing (NLP). We start by remarking on the importance of knowledge integration. We highlight the possible shortcomings of these approaches and investigate the implications of integrating unstructured textual knowledge. We introduce Unstructured Knowledge Integration (UKI) as the process of integrating unstructured knowledge into machine learning models. We discuss UKI in the field of NLP, where knowledge is represented in a natural language format. We identify UKI as a complex process comprised of multiple sub-processes, different knowledge types, and knowledge integration properties to guarantee. We remark on the challenges of integrating unstructured textual knowledge and bridge connections with well-known research areas in NLP. We provide a unified vision of structured knowledge extraction (KE) and UKI by identifying KE as a sub-process of UKI. We investigate some challenging scenarios where structured knowledge is not a feasible prior assumption and formulate each task from the point of view of UKI. We adopt simple yet effective neural architectures and discuss the challenges of such an approach. Finally, we identify KE as a form of symbolic representation. From this perspective, we remark on the need of defining sophisticated UKI processes to verify the validity of knowledge integration. To this end, we foresee frameworks capable of combining symbolic and sub-symbolic representations for learning as a solution.

Abusing data dominance in the digital market. The application of merger control and article 102 TFEU to data-related conducts.

The internet and digital technologies revolutionized the economy. Regulating the digital market has become a priority for the European Union. While promoting innovation and development, EU institutions must assure that the digital market maintains a competitive structure. Among the numerous elements characterizing the digital sector, users’ data are particularly important. Digital services are centered around personal data, the accumulation of which contributed to the centralization of market power in the hands of a few large providers. As a result, data-driven mergers and data-related abuses gained a central role for the purposes of EU antitrust enforcement. In light of these considerations, this work aims at assessing whether EU competition law is well-suited to address data-driven mergers and data-related abuses of dominance. These conducts are of crucial importance to the maintenance of competition in the digital sector, insofar as the accumulation of users’ data constitutes a fundamental competitive advantage. To begin with, part 1 addresses the specific features of the digital market and their impact on the definition of the relevant market and the assessment of dominance by antitrust authorities. Secondly, part 2 analyzes the EU’s case law on data-driven mergers to verify if merger control is well-suited to address these concentrations. Thirdly, part 3 discusses abuses of dominance in the phase of data collection and the legal frameworks applicable to these conducts. Fourthly, part 4 focuses on access to “essential” datasets and the indirect effects of anticompetitive conducts on rivals’ ability to access users’ information. Finally, Part 5 discusses differential pricing practices implemented online and based on personal data. As it will be assessed, the combination of an efficient competition law enforcement and the auspicial adoption of a specific regulation seems to be the best solution to face the challenges raised by “data-related dominance”.

Interpretable Convolutional Neural Networks for Decoding and Analyzing Neural Time Series Data

Machine learning is widely adopted to decode multi-variate neural time series, including electroencephalographic (EEG) and single-cell recordings. Recent solutions based on deep learning (DL) outperformed traditional decoders by automatically extracting relevant discriminative features from raw or minimally pre-processed signals. Convolutional Neural Networks (CNNs) have been successfully applied to EEG and are the most common DL-based EEG decoders in the state-of-the-art (SOA). However, the current research is affected by some limitations. SOA CNNs for EEG decoding usually exploit deep and heavy structures with the risk of overfitting small datasets, and architectures are often defined empirically. Furthermore, CNNs are mainly validated by designing within-subject decoders. Crucially, the automatically learned features mainly remain unexplored; conversely, interpreting these features may be of great value to use decoders also as analysis tools, highlighting neural signatures underlying the different decoded brain or behavioral states in a data-driven way. Lastly, SOA DL-based algorithms used to decode single-cell recordings rely on more complex, slower to train and less interpretable networks than CNNs, and the use of CNNs with these signals has not been investigated. This PhD research addresses the previous limitations, with reference to P300 and motor decoding from EEG, and motor decoding from single-neuron activity. CNNs were designed light, compact, and interpretable. Moreover, multiple training strategies were adopted, including transfer learning, which could reduce training times promoting the application of CNNs in practice. Furthermore, CNN-based EEG analyses were proposed to study neural features in the spatial, temporal and frequency domains, and proved to better highlight and enhance relevant neural features related to P300 and motor states than canonical EEG analyses. Remarkably, these analyses could be used, in perspective, to design novel EEG biomarkers for neurological or neurodevelopmental disorders. Lastly, CNNs were developed to decode single-neuron activity, providing a better compromise between performance and model complexity.

Advanced statistical models for the segregation, identification and measurement of coexisting sound sources

Long-term monitoring of acoustical environments is gaining popularity thanks to the relevant amount of scientific and engineering insights that it provides. The increasing interest is due to the constant growth of storage capacity and computational power to process large amounts of data. In this perspective, machine learning (ML) provides a broad family of data-driven statistical techniques to deal with large databases. Nowadays, the conventional praxis of sound level meter measurements limits the global description of a sound scene to an energetic point of view. The equivalent continuous level Leq represents the main metric to define an acoustic environment, indeed. Finer analyses involve the use of statistical levels. However, acoustic percentiles are based on temporal assumptions, which are not always reliable. A statistical approach, based on the study of the occurrences of sound pressure levels, would bring a different perspective to the analysis of long-term monitoring. Depicting a sound scene through the most probable sound pressure level, rather than portions of energy, brought more specific information about the activity carried out during the measurements. The statistical mode of the occurrences can capture typical behaviors of specific kinds of sound sources. The present work aims to propose an ML-based method to identify, separate and measure coexisting sound sources in real-world scenarios. It is based on long-term monitoring and is addressed to acousticians focused on the analysis of environmental noise in manifold contexts. The presented method is based on clustering analysis. Two algorithms, Gaussian Mixture Model and K-means clustering, represent the main core of a process to investigate different active spaces monitored through sound level meters. The procedure has been applied in two different contexts: university lecture halls and offices. The proposed method shows robust and reliable results in describing the acoustic scenario and it could represent an important analytical tool for acousticians.

Monitoring time-dependent deformation patterns through geodetic techniques

In this thesis we focus on the analysis and interpretation of time dependent deformations recorded through different geodetic methods. Firstly, we apply a variational Bayesian Independent Component Analysis (vbICA) technique to GPS daily displacement solutions, to separate the postseismic deformation that followed the mainshocks of the 2016-2017 Central Italy seismic sequence from the other, hydrological, deformation sources. By interpreting the signal associated with the postseismic relaxation, we model an afterslip distribution on the faults involved by the mainshocks consistent with the co-seismic models available in literature. We find evidences of aseismic slip on the Paganica fault, responsible for the Mw 6.1 2009 L’Aquila earthquake, highlighting the importance of aseismic slip and static stress transfer to properly model the recurrence of earthquakes on nearby fault segments. We infer a possible viscoelastic relaxation of the lower crust as a contributing mechanism to the postseismic displacements. We highlight the importance of a proper separation of the hydrological signals for an accurate assessment of the tectonic processes, especially in cases of mm-scale deformations. Contextually, we provide a physical explanation to the ICs associated with the observed hydrological processes. In the second part of the thesis, we focus on strain data from Gladwin Tensor Strainmeters, working on the instruments deployed in Taiwan. We develop a novel approach, completely data driven, to calibrate these strainmeters. We carry out a joint analysis of geodetic (strainmeters, GPS and GRACE products) and hydrological (rain gauges and piezometers) data sets, to characterize the hydrological signals in Southern Taiwan. Lastly, we apply the calibration approach here proposed to the strainmeters recently installed in Central Italy. We provide, as an example, the detection of a storm that hit the Umbria-Marche regions (Italy), demonstrating the potential of strainmeters in following the dynamics of deformation processes with limited spatio-temporal signature