Knowledge management in intelligent tutoring systems

In the last years, Intelligent Tutoring Systems have been a very successful way for improving learning experience. Many issues must be addressed until this technology can be defined mature. One of the main problems within the Intelligent Tutoring Systems is the process of contents authoring: knowledge acquisition and manipulation processes are difficult tasks because they require a specialised skills on computer programming and knowledge engineering. In this thesis we discuss a general framework for knowledge management in an Intelligent Tutoring System and propose a mechanism based on first order data mining to partially automate the process of knowledge acquisition that have to be used in the ITS during the tutoring process. Such a mechanism can be applied in Constraint Based Tutor and in the Pseudo-Cognitive Tutor. We design and implement a part of the proposed architecture, mainly the module of knowledge acquisition from examples based on first order data mining. We then show that the algorithm can be applied at least two different domains: first order algebra equation and some topics of C programming language. Finally we discuss the limitation of current approach and the possible improvements of the whole framework.

Mass spectrometry-based protein profiling strategies for biomarker discovery in liver and inflammatory bowel diseases

The study of protein expression profiles for biomarker discovery in serum and in mammalian cell populations needs the continuous improvement and combination of proteins/peptides separation techniques, mass spectrometry, statistical and bioinformatic approaches. In this thesis work two different mass spectrometry-based protein profiling strategies have been developed and applied to liver and inflammatory bowel diseases (IBDs) for the discovery of new biomarkers. The first of them, based on bulk solid-phase extraction combined with matrix-assisted laser desorption/ionization - Time of Flight mass spectrometry (MALDI-TOF MS) and chemometric analysis of serum samples, was applied to the study of serum protein expression profiles both in IBDs (Crohn’s disease and ulcerative colitis) and in liver diseases (cirrhosis, hepatocellular carcinoma, viral hepatitis). The approach allowed the enrichment of serum proteins/peptides due to the high interaction surface between analytes and solid phase and the high recovery due to the elution step performed directly on the MALDI-target plate. Furthermore the use of chemometric algorithm for the selection of the variables with higher discriminant power permitted to evaluate patterns of 20-30 proteins involved in the differentiation and classification of serum samples from healthy donors and diseased patients. These proteins profiles permit to discriminate among the pathologies with an optimum classification and prediction abilities. In particular in the study of inflammatory bowel diseases, after the analysis using C18 of 129 serum samples from healthy donors and Crohn’s disease, ulcerative colitis and inflammatory controls patients, a 90.7% of classification ability and a 72.9% prediction ability were obtained. In the study of liver diseases (hepatocellular carcinoma, viral hepatitis and cirrhosis) a 80.6% of prediction ability was achieved using IDA-Cu(II) as extraction procedure. The identification of the selected proteins by MALDITOF/ TOF MS analysis or by their selective enrichment followed by enzymatic digestion and MS/MS analysis may give useful information in order to identify new biomarkers involved in the diseases. The second mass spectrometry-based protein profiling strategy developed was based on a label-free liquid chromatography electrospray ionization quadrupole - time of flight differential analysis approach (LC ESI-QTOF MS), combined with targeted MS/MS analysis of only identified differences. The strategy was used for biomarker discovery in IBDs, and in particular of Crohn’s disease. The enriched serum peptidome and the subcellular fractions of intestinal epithelial cells (IECs) from healthy donors and Crohn’s disease patients were analysed. The combining of the low molecular weight serum proteins enrichment step and the LCMS approach allowed to evaluate a pattern of peptides derived from specific exoprotease activity in the coagulation and complement activation pathways. Among these peptides, particularly interesting was the discovery of clusters of peptides from fibrinopeptide A, Apolipoprotein E and A4, and complement C3 and C4. Further studies need to be performed to evaluate the specificity of these clusters and validate the results, in order to develop a rapid serum diagnostic test. The analysis by label-free LC ESI-QTOF MS differential analysis of the subcellular fractions of IECs from Crohn’s disease patients and healthy donors permitted to find many proteins that could be involved in the inflammation process. Among them heat shock protein 70, tryptase alpha-1 precursor and proteins whose upregulation can be explained by the increased activity of IECs in Crohn’s disease were identified. Follow-up studies for the validation of the results and the in-depth investigation of the inflammation pathways involved in the disease will be performed. Both the developed mass spectrometry-based protein profiling strategies have been proved to be useful tools for the discovery of disease biomarkers that need to be validated in further studies.

When the Practice of Theorizing Meets the Theorizing of Practice. Social Knowledge Making in Organization Science Academia and Managerial Communities

The aim of the present work is to contribute to a better understanding of the relation between organization theory and management practice. It is organized as a collection of two papers, a theoretical and conceptual contribution and an ethnographic study. The first paper is concerned with systematizing different literatures inside and outside the field of organization studies that deal with the theory-practice relation. After identifying a series of positions to the theory-practice debate and unfolding some of their implicit assumptions and limitations, a new position called entwinement is developed in order to overcome status quo through reconciliation and integration. Accordingly, the paper proposes to reconceptualize theory and practice as a circular iterative process of action and cognition, science and common-sense enacted in the real world both by organization scholars and practitioners according to purposes at hand. The second paper is the ethnographic study of an encounter between two groups of expert academics and practitioners occasioned by a one-year executive business master in an international business school. The research articulates a process view of the knowledge exchange between management academics and practitioners in particular and between individuals belonging to different communities of practice, in general, and emphasizes its dynamic, relational and transformative mechanisms. Findings show that when they are given the chance to interact, academics and practitioners set up local provisional relations that enable them to act as change intermediaries vis-a-vis each other’s worlds, without tying themselves irremediably to each other and to the scenarios they conjointly projected during the master’s experience. Finally, the study shows that provisional relations were accompanied by a recursive shift in knowledge modes. While interacting, academics passed from theory to practical theorizing, practitioners passed from an involved practical mode to a reflexive and quasi-theoretical one, and then, as exchanges proceeded, the other way around.

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.

Supporting requirement elicitation and ontology testing in knowledge graph engineering

Knowledge graphs and ontologies are closely related concepts in the field of knowledge representation. In recent years, knowledge graphs have gained increasing popularity and are serving as essential components in many knowledge engineering projects that view them as crucial to their success. The conceptual foundation of the knowledge graph is provided by ontologies. Ontology modeling is an iterative engineering process that consists of steps such as the elicitation and formalization of requirements, the development, testing, refactoring, and release of the ontology. The testing of the ontology is a crucial and occasionally overlooked step of the process due to the lack of integrated tools to support it. As a result of this gap in the state-of-the-art, the testing of the ontology is completed manually, which requires a considerable amount of time and effort from the ontology engineers. The lack of tool support is noticed in the requirement elicitation process as well. In this aspect, the rise in the adoption and accessibility of knowledge graphs allows for the development and use of automated tools to assist with the elicitation of requirements from such a complementary source of data. Therefore, this doctoral research is focused on developing methods and tools that support the requirement elicitation and testing steps of an ontology engineering process. To support the testing of the ontology, we have developed XDTesting, a web application that is integrated with the GitHub platform that serves as an ontology testing manager. Concurrently, to support the elicitation and documentation of competency questions, we have defined and implemented RevOnt, a method to extract competency questions from knowledge graphs. Both methods are evaluated through their implementation and the results are promising.

Advancing digital healthcare research and machine learning-aided knowledge extraction amidst the COVID-19 pandemic

The rapid progression of biomedical research coupled with the explosion of scientific literature has generated an exigent need for efficient and reliable systems of knowledge extraction. This dissertation contends with this challenge through a concentrated investigation of digital health, Artificial Intelligence, and specifically Machine Learning and Natural Language Processing's (NLP) potential to expedite systematic literature reviews and refine the knowledge extraction process. The surge of COVID-19 complicated the efforts of scientists, policymakers, and medical professionals in identifying pertinent articles and assessing their scientific validity. This thesis presents a substantial solution in the form of the COKE Project, an initiative that interlaces machine reading with the rigorous protocols of Evidence-Based Medicine to streamline knowledge extraction. In the framework of the COKE (“COVID-19 Knowledge Extraction framework for next-generation discovery science”) Project, this thesis aims to underscore the capacity of machine reading to create knowledge graphs from scientific texts. The project is remarkable for its innovative use of NLP techniques such as a BERT + bi-LSTM language model. This combination is employed to detect and categorize elements within medical abstracts, thereby enhancing the systematic literature review process. The COKE project's outcomes show that NLP, when used in a judiciously structured manner, can significantly reduce the time and effort required to produce medical guidelines. These findings are particularly salient during times of medical emergency, like the COVID-19 pandemic, when quick and accurate research results are critical.

Body ares networks for human motor assessment

Healthcare, Human Computer Interfaces (HCI), Security and Biometry are the most promising application scenario directly involved in the Body Area Networks (BANs) evolution. Both wearable devices and sensors directly integrated in garments envision a word in which each of us is supervised by an invisible assistant monitoring our health and daily-life activities. New opportunities are enabled because improvements in sensors miniaturization and transmission efficiency of the wireless protocols, that achieved the integration of high computational power aboard independent, energy-autonomous, small form factor devices. Application’s purposes are various: (I) data collection to achieve off-line knowledge discovery; (II) user notification of his/her activities or in case a danger occurs; (III) biofeedback rehabilitation; (IV) remote alarm activation in case the subject need assistance; (V) introduction of a more natural interaction with the surrounding computerized environment; (VI) users identification by physiological or behavioral characteristics. Telemedicine and mHealth [1] are two of the leading concepts directly related to healthcare. The capability to borne unobtrusiveness objects supports users’ autonomy. A new sense of freedom is shown to the user, not only supported by a psychological help but a real safety improvement. Furthermore, medical community aims the introduction of new devices to innovate patient treatments. In particular, the extension of the ambulatory analysis in the real life scenario by proving continuous acquisition. The wide diffusion of emerging wellness portable equipment extended the usability of wearable devices also for fitness and training by monitoring user performance on the working task. The learning of the right execution techniques related to work, sport, music can be supported by an electronic trainer furnishing the adequate aid. HCIs made real the concept of Ubiquitous, Pervasive Computing and Calm Technology introduced in the 1988 by Marc Weiser and John Seeley Brown. They promotes the creation of pervasive environments, enhancing the human experience. Context aware, adaptive and proactive environments serve and help people by becoming sensitive and reactive to their presence, since electronics is ubiquitous and deployed everywhere. In this thesis we pay attention to the integration of all the aspects involved in a BAN development. Starting from the choice of sensors we design the node, configure the radio network, implement real-time data analysis and provide a feedback to the user. We present algorithms to be implemented in wearable assistant for posture and gait analysis and to provide assistance on different walking conditions, preventing falls. Our aim, expressed by the idea to contribute at the development of a non proprietary solutions, driven us to integrate commercial and standard solutions in our devices. We use sensors available on the market and avoided to design specialized sensors in ASIC technologies. We employ standard radio protocol and open source projects when it was achieved. The specific contributions of the PhD research activities are presented and discussed in the following. • We have designed and build several wireless sensor node providing both sensing and actuator capability making the focus on the flexibility, small form factor and low power consumption. The key idea was to develop a simple and general purpose architecture for rapid analysis, prototyping and deployment of BAN solutions. Two different sensing units are integrated: kinematic (3D accelerometer and 3D gyroscopes) and kinetic (foot-floor contact pressure forces). Two kind of feedbacks were implemented: audio and vibrotactile. • Since the system built is a suitable platform for testing and measuring the features and the constraints of a sensor network (radio communication, network protocols, power consumption and autonomy), we made a comparison between Bluetooth and ZigBee performance in terms of throughput and energy efficiency. Test in the field evaluate the usability in the fall detection scenario. • To prove the flexibility of the architecture designed, we have implemented a wearable system for human posture rehabilitation. The application was developed in conjunction with biomedical engineers who provided the audio-algorithms to furnish a biofeedback to the user about his/her stability. • We explored off-line gait analysis of collected data, developing an algorithm to detect foot inclination in the sagittal plane, during walk. • In collaboration with the Wearable Lab – ETH, Zurich, we developed an algorithm to monitor the user during several walking condition where the user carry a load. The remainder of the thesis is organized as follows. Chapter I gives an overview about Body Area Networks (BANs), illustrating the relevant features of this technology and the key challenges still open. It concludes with a short list of the real solutions and prototypes proposed by academic research and manufacturers. The domain of the posture and gait analysis, the methodologies, and the technologies used to provide real-time feedback on detected events, are illustrated in Chapter II. The Chapter III and IV, respectively, shown BANs developed with the purpose to detect fall and monitor the gait taking advantage by two inertial measurement unit and baropodometric insoles. Chapter V reports an audio-biofeedback system to improve balance on the information provided by the use centre of mass. A walking assistant based on the KNN classifier to detect walking alteration on load carriage, is described in Chapter VI.

Genomic and transcriptional analysis of allergen genes in apple (Malus x domestica)

Apple consumption is highly recomended for a healthy diet and is the most important fruit produced in temperate climate regions. Unfortunately, it is also one of the fruit that most ofthen provoks allergy in atopic patients and the only treatment available up to date for these apple allergic patients is the avoidance. Apple allergy is due to the presence of four major classes of allergens: Mal d 1 (PR-10/Bet v 1-like proteins), Mal d 2 (Thaumatine-like proteins), Mal d 3 (Lipid transfer protein) and Mal d 4 (profilin). In this work new advances in the characterization of apple allergen gene families have been reached using a multidisciplinary approach. First of all, a genomic approach was used for the characterization of the allergen gene families of Mal d 1 (task of Chapter 1), Mal d 2 and Mal d 4 (task of Chapter 5). In particular, in Chapter 1 the study of two large contiguos blocks of DNA sequences containing the Mal d 1 gene cluster on LG16 allowed to acquire many new findings on number and orientation of genes in the cluster, their physical distances, their regulatory sequences and the presence of other genes or pseudogenes in this genomic region. Three new members were discovered co-localizing with the other Mal d 1 genes of LG16 suggesting that the complexity of the genetic base of allergenicity will increase with new advances. Many retrotranspon elements were also retrieved in this cluster. Due to the developement of molecular markers on the two sequences, the anchoring of the physical and the genetic map of the region has been successfully achieved. Moreover, in Chapter 5 the existence of other loci for the Thaumatine-like protein family in apple (Mal d 2.03 on LG4 and Mal d 2.02 on LG17) respect the one reported up to now was demonstred for the first time. Also one new locus for profilins (Mal d 4.04) was mapped on LG2, close to the Mal d 4.02 locus, suggesting a cluster organization for this gene family, as is well reported for Mal d 1 family. Secondly, a methodological approach was used to set up an highly specific tool to discriminate and quantify the expression of each Mal d 1 allergen gene (task of Chapter 2). In aprticular, a set of 20 Mal d 1 gene specific primer pairs for the quantitative Real time PCR technique was validated and optimized. As a first application, this tool was used on leaves and fruit tissues of the cultivar Florina in order to identify the Mal d 1 allergen genes that are expressed in different tissues. The differential expression retrieved in this study revealed a tissue-specificity for some Mal d 1 genes: 10/20 Mal d 1 genes were expressed in fruits and, indeed, probably more involved in the allergic reactions; while 17/20 Mal d 1 genes were expressed in leaves challenged with the fungus Venturia inaequalis and therefore probably interesting in the study of the plant defense mechanism. In Chapter 3 the specific expression levels of the 10 Mal d 1 isoallergen genes, found to be expressed in fruits, were studied for the first time in skin and flesh of apples of different genotypes. A complex gene expression profile was obtained due to the high gene-, tissue- and genotype-variability. Despite this, Mal d 1.06A and Mal d 1.07 expression patterns resulted particularly associated with the degree of allergenicity of the different cultivars. They were not the most expressed Mal d 1 genes in apple but here it was hypotized a relevant importance in the determination of allergenicity for both qualitative and quantitative aspects of the Mal d 1 gene expression levels. In Chapter 4 a clear modulation for all the 17 PR-10 genes tested in young leaves of Florina after challenging with the fungus V. inaequalis have been reported but with a peculiar expression profile for each gene. Interestingly, all the Mal d 1 genes resulted up-regulated except Mal d 1.10 that was down-regulated after the challenging with the fungus. The differences in direction, timing and magnitude of induction seem to confirm the hypothesis of a subfunctionalization inside the gene family despite an high sequencce and structure similarity. Moreover, a modulation of PR-10 genes was showed both in compatible (Gala-V. inaequalis) and incompatible (Florina-V. inaequalis) interactions contribute to validate the hypothesis of an indirect role for at least some of these proteins in the induced defense responses. Finally, a certain modulation of PR-10 transcripts retrieved also in leaves treated with water confirm their abilty to respond also to abiotic stress. To conclude, the genomic approach used here allowed to create a comprehensive inventory of all the genes of allergen families, especially in the case of extended gene families like Mal d 1. This knowledge can be considered a basal prerequisite for many further studies. On the other hand, the specific transcriptional approach make it possible to evaluate the Mal d 1 genes behavior on different samples and conditions and therefore, to speculate on their involvement on apple allergenicity process. Considering the double nature of Mal d 1 proteins, as apple allergens and as PR-10 proteins, the gene expression analysis upon the attack of the fungus created the base for unravel the Mal d 1 biological functions. In particular, the knowledge acquired in this work about the PR-10 genes putatively more involved in the specific Malus-V. inaequalis interaction will be helpful, in the future, to drive the apple breeding for hypo-allergenicity genotype without compromise the mechanism of response of the plants to stress conditions. For the future, the survey of the differences in allergenicity among cultivars has to be be thorough including other genotypes and allergic patients in the tests. After this, the allelic diversity analysis with the high and low allergenic cultivars on all the allergen genes, in particular on the ones with transcription levels correlated to allergencity, will provide the genetic background of the low ones. This step from genes to alleles will allow the develop of molecular markers for them that might be used to effectively addressed the apple breeding for hypo-allergenicity. Another important step forward for the study of apple allergens will be the use of a specific proteomic approach since apple allergy is a multifactor-determined disease and only an interdisciplinary and integrated approach can be effective for its prevention and treatment.

From core rigidities to dynamic capabilities: the role of external knowledge. A multiple case study

This study focuses on the processes of change that firms undertake to overcome conditions of organizational rigidity and develop new dynamic capabilities, thanks to the contribution of external knowledge. When external contingencies highlight firms’ core rigidities, external actors can intervene in change projects, providing new competences to firms’ managers. Knowledge transfer and organizational learning processes can lead to the development of new dynamic capabilities. Existing literature does not completely explain how these processes develop and how external knowledge providers, as management consultants, influence them. Dynamic capabilities literature has become very rich in the last years; however, the models that explain how dynamic capabilities evolve are not particularly investigated. Adopting a qualitative approach, this research proposes four relevant case studies in which external actors introduce new knowledge within organizations, activating processes of change. Each case study consists of a management consulting project. Data are collected through in-depth interviews with consultants and managers. A large amount of documents supports evidences from interviews. A narrative approach is adopted to account for change processes and a synthetic approach is proposed to compare case studies along relevant dimensions. This study presents a model of capabilities evolution, supported by empirical evidence, to explain how external knowledge intervenes in capabilities evolution processes: first, external actors solve gaps between environmental demands and firms’ capabilities, changing organizational structures and routines; second, a knowledge transfer between consultants and managers leads to the creation of new ordinary capabilities; third, managers can develop new dynamic capabilities through a deliberate learning process that internalizes new tacit knowledge from consultants. After the end of the consulting project, two elements can influence the deliberate learning process: new external contingencies and changes in the perceptions about external actors.

Data Mining in Clinical Practice for the Quantification of Motor Impairment in Parkinson's Disease

Advances in biomedical signal acquisition systems for motion analysis have led to lowcost and ubiquitous wearable sensors which can be used to record movement data in different settings. This implies the potential availability of large amounts of quantitative data. It is then crucial to identify and to extract the information of clinical relevance from the large amount of available data. This quantitative and objective information can be an important aid for clinical decision making. Data mining is the process of discovering such information in databases through data processing, selection of informative data, and identification of relevant patterns. The databases considered in this thesis store motion data from wearable sensors (specifically accelerometers) and clinical information (clinical data, scores, tests). The main goal of this thesis is to develop data mining tools which can provide quantitative information to the clinician in the field of movement disorders. This thesis will focus on motor impairment in Parkinson's disease (PD). Different databases related to Parkinson subjects in different stages of the disease were considered for this thesis. Each database is characterized by the data recorded during a specific motor task performed by different groups of subjects. The data mining techniques that were used in this thesis are feature selection (a technique which was used to find relevant information and to discard useless or redundant data), classification, clustering, and regression. The aims were to identify high risk subjects for PD, characterize the differences between early PD subjects and healthy ones, characterize PD subtypes and automatically assess the severity of symptoms in the home setting.

Self-Assembled Monolayers (SAMs) in Organic Field-Effect Transistors

Organic printed electronics is attracting an ever-growing interest in the last decades because of its impressive breakthroughs concerning the chemical design of π-conjugated materials and their processing. This has an impact on novel applications, such as flexible-large-area displays, low- cost printable circuits, plastic solar cells and lab-on-a-chip devices. The organic field-effect transistor (OFET) relies on a thin film of organic semiconductor that bridges source and drain electrodes. Since its first discovery in the 80s, intensive research activities were deployed in order to control the chemico-physical properties of these electronic devices and consequently their charge. Self-assembled monolayers (SAMs) are a versatile tool for tuning the properties of metallic, semi-conducting, and insulating surfaces. Within this context, OFETs represent reliable instruments for measuring the electrical properties of the SAMs in a Metal/SAM/OS junction. Our experimental approach, named Charge Injection Organic-Gauge (CIOG), uses OTFT in a charge-injection controlled regime. The CIOG sensitivity has been extensively demonstrated on different homologous self-assembling molecules that differ in either chain length or in anchor/terminal group. One of the latest applications of organic electronics is the so-called “bio-electronics” that makes use of electronic devices to encompass interests of the medical science, such as biosensors, biotransducers etc… As a result, thee second part of this thesis deals with the realization of an electronic transducer based on an Organic Field-Effect Transistor operating in aqueous media. Here, the conventional bottom gate/bottom contact configuration is replaced by top gate architecture with the electrolyte that ensures electrical contact between the top gold electrode and the semiconductor layer. This configuration is named Electrolyte-Gated Field-Effect Transistor (EGOFET). The functionalization of the top electrode is the sensing core of the device allowing the detection of dopamine as well as of protein biomarkers with ultra-low sensitivity.

Topics in Local Economic Development

This thesis contributes to the current debate in literature about local economic development by considering two different topics: quality of institutions, and the role of clusters in innovation and productivity growth. The research is built upon three papers. The first paper deals with the analysis of the effect of administrative continuity on administrative efficiency. The analysis underlines the importance of different typologies of social capital. Findings reveal a positive impact on administrative efficiency (AE) by administrative continuity (AC) when it is coupled by bridging and linking social capital. On the contrary, bonding social capital influences negatively the effect by AC on AE. The second paper investigates the spatial interaction in levels of quality of government (QoG) among European regions. Notwithstanding the largely recognised role by institutions in the design of regional policies, no study has been conducted about the mechanisms of interaction and diffusion of QoG at regional level. This research wants to overcome this knowledge gap in literature. Findings reveal a heterogeneity in spatial interaction among groups of regions, i.e. ‘leader regions’ (Northern regions) and ‘lagging regions’ (Southern regions), when considering different mechanisms of interaction (learning / imitating competition and pure competition). Moreover, the effect of wealth on the levels of QoG is nonlinear. Finally, the third paper analyses the relation among specialization and productivity within the agricultural sector. In literature, the study of clusters dynamics has long neglected agriculture. The analysis describes the changes in sectorial specialization for eight main crop groups in Italian regions (NUTS 3), assessing the existence of spatial autocorrelations by using an exploratory data analysis. Furthermore, the effect of specialization on productivity is analysed within the main crop groups using a spatial panel data model. Findings reveal a marked tendency to specialization in the Italian agriculture, and a heterogeneous effect by specialization on productivity.