Search

Label Ranking (LR) is a non-standard supervised classification method with the aim of ranking a finite collection of labels according to a set of predictor variables. Traditional LR models assume indifference among alternatives. However, misassigning the ranking position of a highly relevant label is frequently regarded as more severe than failing to predict a trivial label. Moreover, switching two similar alternatives should be considered less severe than switching two different ones. Therefore, efficient LR classifiers should be able to take into account the similarities and individual weights of the items to be ranked. The contribution of this paper is to formulate and compare flexible item-weighted Label Ranking algorithms using bagging, random forest, and boosting ensemble methods.

Probabilistic topic models, such as LDA, are standard text analysis algorithms that provide predictive and latent topic representation for a corpus. However, due to the unsupervised training process, it is difficult to verify the assumption that the latent space discovered by these models is generally meaningful and valuable. This paper introduces a two-stage LDA algorithm to estimate latent topics in text documents and use readability scores to link the identified topics to a linguistically motivated latent structure. We define a new interpretative tool called induced topic readability, which is used to rank topics from the one with the most complex linguistic structure to the one with the lowest semantic content readily. The usefulness of our method is shown with an application to real data, using articles from the New York Times.

Probabilistic topic models have become one of the most widespread machine learning technique for textual analysis purpose. In this framework, Latent Dirichlet Allocation (LDA) gained more and more popularity as a text modelling technique. The idea is that documents are represented as random mixtures over latent topics, where a distribution over words characterizes each topic. Unfortunately, topic models do not guarantee the interpretability of their outputs. The topics learned from the model may be characterized by a set of irrelevant or unchained words, being useless for the interpretation. In the framework of topic quality evaluation, the pairwise semantic cohesion among the top-N most probable words (for a given topic) is calculated by measures based on words co-occurrences. Many topic-quality metrics were proposed defining different score measures such as: Pointwise Mutual Information (PMI), also called UCI; an asymmetrical measure called UMass; Normalized Pointwise Mutual Information (NPMI), a measure based on tf-idf scores , and a measure called CV proposed by Roder et al. Although these several measures in the literature have already considered cooccurrence between words as a measure of association, none has undertaken a statistical approach based on hypotheses testing to assess whether the co-occurrence obtained between two words can be attributed to the chance or if these links carry relevant information about the structure of topics. Thus, we propose a new coherence measure based on Statistically Validated Network to evaluate the interpretability of the top words of a topic.

Probabilistic topic models have become one of the most widespread machine learning technique for textual analysis purpose. In this framework, Latent Dirichlet Allocation (LDA) (Blei et al., 2003) gained more and more popularity as a text modelling technique. The idea is that documents are represented as random mixtures over latent topics, where a distribution overwords characterizes each topic. Unfortunately, topic models do not guarantee the interpretability of their outputs. The topics learned from the model may be only characterized by a set of irrelevant or unchained words, being useless for the interpretation. Although many topic-quality metrics were proposed (Newman et al., 2009; Aletras and Stevenson,2013; Roder et al., 2015; Nikolenko et al., 2017), the automatic evaluation of the coherence of topics remains an open research area. The main contributions of this paper are: i) to define a coherence measure (SVN-Coherence) based on a rigorous statistical model that approximates human ratings better than state-of-the-art methods, and ii) to filter out marginal associations of words and facilitate the graphical representation and interpretation of the obtained topics through Statically Validated Networks (SVN) (Tumminello et al., 2011). Specifically, the method builds a co-occurrence network for each topic whose most probable words are the nodes. We set a link between two nodes (words) in each network if their co-occurrences are statistically significant. The Hypergeometric distribution describes the probability mass function under the null hypothesis and it models the probability of co-occurrence between words conditionally to their marginals. Indeed, it allows taking into account the heterogeneity of the vocabulary on a collection of texts. Finally, we derive a global measure of coherence for each topic by considering the number of statistically validated links, the strength of the association between word pairs, and the relative relevance of each word in the topic. We claim that these links carry relevant information about the structure of topics, i.e., the more connected the network, the more semantically coherent the corresponding topic. The new measure provides a coherence-based ranking that distinguishes between high-quality and low-quality topics. We designed a survey to obtain human judgment, which we use as ground truth, to compare our method with the state-of-art coherence measures. Specifically, we asked 222 PhD students to evaluate the coherence of 32 topics (extracted from the New York Times articles dataset) on a 4-point scale. The results show that the proposed SVN-Coherence substantially outperforms all the state-of-art coherence metrics.

Label Ranking (LR), an emerging non-standard supervised classification problem, aims at training preference models that order a finite set of labels based on a set of predictor features. Traditional LR models regard all labels as equally important. However, in many cases, failing to predict the ranking position of a highly relevant label can be considered more severe than failing to predict a trivial one. Moreover, an efficient LR classifier should be able to take into account the similarity between the items to be ranked. Indeed, swapping two similar elements should be less penalized than swapping two dissimilar ones. The contribution of the present paper is to formulate more flexible item-weighted label ranking models that make use of well-known decision tree ensemble models; respectively: bagging, random forest and boosting. The three proposed weighted LR classifiers encode the similarity structure and the individual label importance provided by a domain expert. The predictive performances of the three algorithms are compared, through simulations, to determine which ensemble procedure produces the best results for different noise levels and weight sets.

The task of combining preference rankings and approval voting is a relevant issue in social choice theory. The preference-approval voting (PAV) analyses the preferences of a group of individuals over a set of items. The main difference with the classical approaches for preference data consists in introducing, in addition to the ranking of candidates, a further distinction; candidates are subsetted in “acceptable” and “unacceptable”, or also in “good set” and “bad set” (a way to express the approval/disapproval). This work introduces the definition of a new measure to quantify disagreement between preference-approval profiles. For each pair of alternatives, we consider the two possible disagreements in approvals and rankings and merge them through a function h(·) increasing in each component. We show that our approach allows to emphasize particularly those cases in which both ranking and approval show simultaneously the maximum discordance.

Probabilistic topic models are machine learning tools for processing and understanding large text document collections. Among the different models in the literature, Latent Dirichlet Allocation (LDA) has turned out to be the benchmark of the topic modelling community. The key idea is to represent text documents as random mixtures over latent semantic structures called topics. Each topic follows a multinomial distribution over the vocabulary words. In order to understand the result of a topic model, researchers usually select the top-n (essential words) words with the highest probability given a topic and look for meaningful and interpretable semantic themes. This work proposes a new method for exploring topics in LDA models, using Statistically Validated Networks (SVNs). The main idea of the proposed method is to consider co-occurrence between essential words as a measure of association. Two different approaches, called undirected and directed are proposed. Firstly, the symmetrical asso- ciation between two words is taken into account, i.e. how many times two words are found in the same sentence. Conversely, in the directed approach, the order in which the words are in the sentence is also considered. We use hypothesis testing to assess whether the co-occurrence between two words can be attributed to the chance or if these links carry relevant information about the structure of topics. Specifically, textual data is represented as a bipartite network in which one set of nodes is made by sentences, and the other set of nodes is made by a list of essential words associated with a given topic. A link between a word and a sentence is set if the word belongs to that sentence. Therefore, the projection of the bipartite network on the set of words results in a word-co-occurrence network. Note that the directed approach produces a directed network while the undirected one an undirected network. Indeed, a directed link from one word to another may be val- idated, but not the other way around. The two methods are applied to a real dataset, highlighting the differences.

Probabilistic topic models have become one of the most widespread machine learning techniques in textual analysis. Topic discovering is an unsupervised process that does not guarantee the interpretability of its output. Hence, the automatic evaluation of topic coherence has attracted the interest of many researchers over the last decade, and it is an open research area. This article offers a new quality evaluation method based on statistically validated networks (SVNs). The proposed probabilistic approach consists of representing each topic as a weighted network of its most probable words. The presence of a link between each pair of words is assessed by statistically validating their co-occurrence in sentences against the null hypothesis of random co-occurrence. The proposed method allows one to distinguish between high-quality and low-quality topics, by making use of a battery of statistical tests. The statistically significant pairwise associations of words represented by the links in the SVN might reasonably be expected to be strictly related to the semantic coherence and interpretability of a topic. Therefore, the more connected the network, the more coherent the topic in question. We demonstrate the effectiveness of the method through an analysis of a real text corpus, which shows that the proposed measure is more correlated with human judgement than the state-of-the-art coherence measures.

The outbreak of coronavirus disease 2019 (COVID-19) was highly stressful for people. In general, fear and anxiety about a disease can be overwhelming and cause strong emotions in adults and children. One way to cope with this stress consists in listening to music. Aim of this work is to understand if the music heard during the lock-down reflects the emotions generated by the pandemic on each of us. So, the primary goal of this work is to build two indices for measuring the anger and joy levels of the top streamed songs by Italian Spotify users (during the SARS-CoV-2 pandemic), and study their evolution over time. A Hierarchical Cluster Analysis has been applied in order to identify groups of weeks reflecting common musical sentiments, and a Beta regression model is used to validate the results of cluster analysis.

Label Ranking (LR) is an emerging non-standard supervised classification problem with practical applications in different research fields. The Label Ranking task aims at building preference models that learn to order a finite set of labels based on a set of predictor features. One of the most successful approaches to tackling the LR problem consists of using decision tree ensemble models, such as bagging, random forest, and boosting. However, these approaches, coming from the classical unweighted rank correlation measures, are not sensitive to label importance. Nevertheless, in many settings, failing to predict the ranking position of a highly relevant label should be considered more serious than failing to predict a negligible one. Moreover, an efficient classifier should be able to take into account the similarity between the elements to be ranked. The main contribution of this paper is to formulate, for the first time, a more flexible label ranking ensemble model which encodes the similarity structure and a measure of the individual label importance. Precisely, the proposed method consists of three item-weighted versions of the AdaBoost boosting algorithm for label ranking. The predictive performance of our proposal is investigated both through simulations and applications to three real datasets.

Context Functional hypothalamic amenorrhea (HA) is a common, acquired form of hypogonadotropic hypogonadism that occurs in the setting of energy deficits and/or stress. Variability in individual susceptibility to these stressors, HA heritability, and previous identification of several rare sequence variants (RSVs) in genes associated with the rare disorder, isolated hypogonadotropic hypogonadism (IHH), in individuals with HA suggest a possible genetic contribution to HA susceptibility. Objective We sought to determine whether the burden of RSVs in IHH-related genes is greater in women with HA than controls. Design We compared patients with HA to control women. Setting The study was conducted at secondary referral centers. Patients and Other Participants Women with HA (n = 106) and control women (ClinSeq study; n = 468). Interventions We performed exome sequencing in all patients and controls. Main Outcome Measure(s) The frequency of RSVs in 53 IHH-associated genes was determined using rare variant burden and association tests. Results RSVs were overrepresented in women with HA compared with controls (P = .007). Seventy-eight heterozygous RSVs in 33 genes were identified in 58 women with HA (36.8% of alleles) compared to 255 RSVs in 41 genes among 200 control women (27.2%). Conclusions Women with HA are enriched for RSVs in genes that cause IHH, suggesting that variation in genes associated with gonadotropin-releasing hormone neuronal ontogeny and function may be a major determinant of individual susceptibility to developing HA in the face of diet, exercise, and/or stress.

Context Loss-of-function mutations in the imprinted genes MKRN3 and DLK1 cause central precocious puberty (CPP) but whole gene deletions have not been reported. Larger deletions of the chromosome 15q11-13 imprinted locus, including MKRN3, cause Prader-Willi syndrome (PWS). CPP has been reported in PWS but is not common, and the role of MKRN3 in PWS has not been fully elucidated. Objective To identify copy number variants in puberty-related, imprinted genes to determine their role in CPP. Methods Probands with idiopathic CPP had chromosomal microarray (CMA) and targeted deletion/duplication testing for MKRN3 and DLK1. Results Sixteen female probands without MKRN3 or DLK1 variants identified by Sanger sequencing were studied. Whole gene deletions of MKRN3 were identified in 2 subjects (13%): a complete deletion of MKRN3 in Patient A (pubertal onset at 7 years) and a larger deletion involving MAGEL2, MKRN3, and NDN in Patient B (pubertal onset 5.5 years). Both were paternally inherited. Patient B had no typical features of PWS, other than obesity, which was also present in her unaffected family. Conclusions We identified 2 cases of whole gene deletions of MKRN3 causing isolated CPP without PWS. This is the first report of complete deletions of MKRN3 in patients with CPP, emphasizing the importance of including copy number variant analysis for MKRN3 mutation testing when a genetic diagnosis is suspected. We speculate that there is a critical region of the PWS locus beyond MKRN3, MAGEL2, and NDN that is responsible for the PWS phenotype.

Preference data are a particular type of ranking data that arise when several individuals express their preferences over a finite set of items. Within this framework, the main issue concerns the aggregation of the preferences to identify a compromise or a “consensus”, defined as the closest ranking (i.e. with the minimum distance or maximum correlation) to the whole set of preferences. Many approaches have been proposed, but they are not sensitive to the importance of items: i.e. changing the rank of a highly-relevant element should result in a higher penalty than changing the rank of a negligible one. The goal of this paper is to investigate the consensus between rankings taking into account the importance of items (element weights). For this purpose, we present: i) an element weighted rank correlation coefficient as an extension of the Emond and Mason’s one, and ii) an element weighted rank distance as an extension of the Kemeny distance. The one-to-one correspondence between the weighted distance and the rank correlation coefficient is analytically proved. Moreover, a procedure to obtain the consensus ranking among several individuals is described and its performance is studied both by simulation and by the application to real datasets.

Gli alberi decisionali sono una tecnica predittiva di machine learning particolarmente diffusa, utilizzata per prevedere delle variabili discrete (classificazione) o continue (regressione). Gli algoritmi alla base di queste tecniche sono intuitivi e interpretabili, ma anche instabili. Infatti, per rendere la classificazione più affidabile si `e soliti combinare l’output di più alberi. In letteratura, sono stati proposti diversi approcci per classificare ranking data attraverso gli alberi decisionali, ma nessuno di questi tiene conto ne dell’importanza, ne delle somiglianza dei singoli elementi di ogni ranking. L’obiettivo di questo articolo `e di proporre un’estensione ponderata del metodo boosting per ranking, che tenga conto della struttura di similarità e dell’importanza dei singoli elementi. I vantaggi di questa procedura sono mostrati con un esempio su un dataset reale. Decision tree learning is one of the most popular families of machine learning algorithms. These techniques are quite intuitive and interpretable but also unstable. It is necessary to use ensemble methods that combine the output of multiple trees, to make the procedure more reliable and stable. Many approaches have been proposed for ranking data, but they are not sensitive to the importance of items. For example, changing the rank of a highly-relevant element should result in a higher penalty than changing a negligible one. Likewise, swapping two similar elements should be less penalized than swapping two dissimilar ones. This paper extends the boosting ensemble method to weighted ranking data, proposing a theoretical and computational definition of item-weighted boosting. The advantages of this procedure are shown through an example on a real data set.

Topic modeling is a type of statistical modeling for discovering the abstract ``topics'' that occur in a collection of documents. Latent Dirichlet Allocation (LDA) is an example of topic model and is used to classify text in a document to a particular topic. It builds a fixed number of topics starting from words in each document modeled according to a Dirichlet distribution. In this work we are going to apply LDA to a set of songs from four famous Italian songwriters and split them into topics. This work studies the use of themes in lyrics using statistical analysis to detect topics. Aim of the work is to underline the main limits of the standard unsupervised LDA and to propose a supervised extension based on the Correspondence Analysis (CA) association theory.

Topic models arise from the need of understanding and exploring large text document collections and predicting their underlying structure. Latent Dirichlet Allocation (LDA) (Blei et al., 2003) has quickly become one of the most popular text modelling techniques. The idea is that documents are represented as random mixtures over latent topics, where a distribution over words characterizes each topic. Unfortunately, topic models give no guaranty on the interpretability of their outputs. The topics learned from texts may be characterized by a set of irrelevant or unchained words. Therefore, topic models require validation of the coherence of estimated topics. However, the automatic evaluation of the latent space of a topic model is a difficult task. Formerly, the most used metric for evaluating the quality of a topic model was the held-out likelihood. Still, the literature has shown that this method emphasizes complexity rather than interpretability. Although many procedures were recently proposed (Röder et al., 2015), the automatic evaluation of topic coherence remains an open research area. Our work aims to provide a new technique based on Statistically Validated Network (Tumminello et al., 2011). Our approach consists in representing each topic as a network of its most probable words. The presence of a link between each pair of words is assessed by statistically validating their co-occurrences in sentences against the null hypothesis of random co-occurrence. Thus, we propose a new coherence measure based on the structure of the statistically validated network. Furthermore, the new measure provides a ranking of topics and distinguishes high-quality from low-quality topics. The intuition is that the pairwise associations of words is strictly related to the semantic coherence and interpretability of a topic.

Negli ultimi anni si è assistito ad un incremento della competizione tra gli atenei per “accaparrarsi” gli studenti, a cui si aggiunge una sempre maggiore attività di promozione e di reclutamento degli studenti delle università non statali (telematiche e non). Le università non statali, altrimenti denominate “libere Università”, sono promosse sia da enti di diritto privato che da enti pubblici (regioni, province, comuni). Esse sono legalmente riconosciute dal Ministero dell'Istruzione dell'Università e della Ricerca, e autorizzate a rilasciare titoli accademici, relativi all’ordinamento universitario, di valore legale identico a quelli rilasciati dalle università statali. La letteratura ha già mostrato quali sono le determinanti del successo universitario, come il tipo di scuola, il voto alla maturità, il corso di studi, la macroregione di residenza, il genere ma non ancora in relazione alle differenze tra le università statali e non statali. Infatti, non sono ancora stati condotti studi sulle carriere universitarie in termini di successo degli studenti iscritti negli atenei italiani, distinti tra: università statali e università non statali, che, a loro volta vista la grande differenza al loro interno, vanno distinte in telematiche (NS_Tel) e non telematiche (NS_NonTel).

An analysis of italian university science students’ careers in the last decade · This paper deals with the study of Italian university science careers by analyzing administrative longitudinal data from the Italian Ministry of Education. Three freshmen cohorts enrolled in a three-year degree course 2011/12, 2014/15, and 2016/17 are analyzed in three time points : at enrolment, in order to assess their choices with respect to their individual characteristics ; at the beginning of the second year, in order to assess who moves to another course and who drops out ; at the fourth year, in order to determine the “best” students’ profiles. The students’ variables involved are gender, type of school, school mark, age, residence region, degree course and all the covariates of their university career.

Background: OGTT is still considered the gold standard test to detect prediabetes and /or Type 2 diabetes (T2D). American Diabetes Association criteria for prediabetes: a) Hba1c 5.7- 6.4% b) fasting plasma glucose (FPG) ≥ 100 mg/dl and/or post-prandial PG ≥ 140, Impaired glucose tolerance (IGT) during an OGTT. In adults the 1-hour(1hr) glucose level (≥ 155 mg/dl) is a strong predictor of future T2D risk than the two-hour level and is associated with diabetes complication. The ideal cut-off for pediatrics is not established though studies have found 1hPG ≥ 132.5 mg/dl, as predictive for risk of T2D (1) Objective: a. To study the dynamic profile of Plasma Glucose (PG) and plasma Insulin (PI) values at time 0,1 and 2 hour during an OGTT b. to assess whether degree of insulin resistance in Hispanic children and adolescents can be predict an abnormal I hr glucose level. Methods: We reviewed OGTT results of 43 obese Hispanic youths; 7-18 years of age with prediabetes. PG and PI values were obtained at 0, 1 and 2hr during OGTT (glucola: dose of 1.75 g/kg body weight up to a maximum of 75 g). The Homeostasis Model Assessment of fasting insulin resistance (HOMA-IR), an index of insulin resistance was calculated using (fasting glucose (mg/dl) X fasting insulin(µIU/ml)/405) and values ≥3.4 were taken as insulin resistance(2). Independent T test was used to study differences between means for group1: HOMA-IR< 3.4 and group 2: HOMA-IR≥ 3.4. Results: Forty-three obese Hispanic youths; 7-18 years of age; mean age of 11.5 ± 0.7; BMI=42.2 ± 4.9; 47% male and 53% female. a) OGTT results: Only one subject had abnormal fasting plasma glucose, 3 subjects had IGT (7%), and 11(26%) had an abnormal 1 h PG during the OGTT b) 1hr glucose and 1hr insulin was different between HOMA-IR groups (p=0.001) even though 2-hr was not. PG: grp#1: 1hr=108 ± 27, 2hr=107 ± 33 mg/dl; grp #2: 1hr=136 ± 33, 2hr=120 ± 32. PI: grp#1: 1hr= 80 ± 61, 2hr= 78 ± 70; grp#2: 1hr= 213 ±171, 2hr= 99 ± 375. Conclusion: In our Hispanic children and adolescents, 1& 2-hr plasma insulin and plasma glucose were clearly abnormal, more so, in the HOMA- IR group ≥ 3.4. This demonstrate that at least in the IR children and adolescents, 1-hour values add value to the interpretation of the OGTT. 26 % of Hispanic children and adolescents had an abnormal 1-hr glucose which is a novel finding of our study. These results validate the recent reports of the plasma 1-hr glucose threshold ≥132.5 mg/dl in Pediatrics and prospective follow up of these Hispanic patients will be able to demonstrate the predictive value of 1 hr values of insulin and glucose to development of T2D.Reference: ADDIN EN.REFLIST 1. Manco M, Miraglia Del Giudice E, et al. 1-Hour plasma glucose in obese youth. Acta diabetologica. 2012;49(6):435-43. 2. Brar PC, Screening obese children and adolescents for prediabetes and/or type 2 diabetes in pediatric practices: a validation study. Clinical pediatrics. 2014;53(8):771-6.

El objetivo de este artículo es estudiar la movilidad ocupacional experimentada por losinmigrantes que completaron sus estudios universitarios (de grado y postgrado) antesde su llegada a España. Para ello hemos comparado la primera ocupación que tuvieronen España con la última que tuvieron antes de dejar su país de origen. Hemos iden-tificado tres tipos diferentes de movilidad: movilidad descendente; movilidad lateraly, finalmente, movilidad ascendente. Por último, hemos usado modelos de regresiónlogística para identificar los predictores más importantes de estos tres tipos de movi-lidad. El análisis empírico se hizo utilizando información aportada por la EncuestaNacional de Inmigrantes (ENI) de 2007, que tiene información de unos 15 000 indi-viduos. Nuestra atención se centra en 2 425 inmigrantes cualificados.

Thermogravimetric data on the devolatilization rate of beech wood are re-examined with the aim of incorporating the effects of high heating rates (up to 108 K min −1 ) in the global kinetics. The mechanism consisting of three independent parallel reactions, first-order in the amount of volatiles released from pseudo-components with chief contributions from hemicellulose, cellulose and lignin, is considered first. It is found that the set of activation energies estimated by Gronli et al. [M.G. Gronli, G. Varhegyi, C. Di Blasi, Ind. Eng. Chem. Res. 41 (2002) 4201–4208] (100, 236 and 46 kJ mol −1 , respectively) for one slow heating rate results in very high deviations between predicted and measured rate curves. The agreement is significantly improved by a new set of data consisting of activation energies of 147, 193 and 181 kJ mol −1 , respectively. In this case, the overlap is reduced between the reaction rates of the three pseudo-components whose chemical composition is also modified. In particular, instead of a slow decomposition rate over a broad range of temperatures, the activity of the third reaction is mainly explicated along the high-temperature (tail) region of the weight loss curves. The performances of more simplified mechanisms are also evaluated. One-step mechanisms, using literature values for the kinetic constants, produce large errors on either the conversion time (activation energy of 103 kJ mol −1 ) or the maximum devolatilization rate (activation energy of 149 kJ mol −1 ). On the other hand, these parameters are well predicted by two parallel reactions, with activation energies of 147 and 149 kJ mol −1 .

Nel saggio vengono analizzati i motivi giuridici, etici e politici a fondamento dell’approvazione della legge sulla tortura.

L'architettura può fare la differenza solo quando assume ruoli e responsabilità, quando riesce a capire e interpretare i bisogni delle persone, a prendersi cura di queste e dei luoghi, un'architettura che guarda al sociale può agire come baluardo contro la marginalità e l'esclusione e divenire motore di nuove visioni, potente mezzo comunicante, strumento attraverso cui le periferie dell'abitare possano rivendicare diritti, progresso, opportunità, inclusione. L'architettura si occupa di dare forma ai luoghi in cui viviamo, e il concetto di qualità della vita si estende dai bisogni fisici primari alle dimensioni più astratte della condizione umana, ma anche alle condizioni più eccezionali, come il carcere.

Atti del convegno "Spazio e libertà negata", organizzato dal Garante Nazionale dei diritti delle persone detenute o private della libertà personale a Roma, presso l'Istituto dell'Enciclopedia Treccani, il 28 ottobre 2019.