Search

This paper describes two different approaches to sentiment analysis. The first is a form of symbolic approach that exploits a sentiment lexicon together with a set of shifter patterns and rules. The sentiment lexicon includes single words (unigrams) and is developed automatically by exploiting labeled examples. The shifter patterns include intensification, attenuation/downtoning and inversion/reversal and are developed manually. The second approach exploits a deep neural network, which uses a pre-trained language model. Both approaches were applied to texts on economics and finance domains from newspapers in European Portuguese. We show that the symbolic approach achieves virtually the same performance as the deep neural network. In addition, the symbolic approach provides understandable explanations, and the acquired knowledge can be communicated to others. We release the shifter patterns to motivate future research in this direction. [ABSTRACT FROM AUTHOR]

Angola is characterized by many different languages and social, cultural and political realities, which had a marked effect on Angolan Portuguese (AP). Consequently, AP is characterized by diatopic variation. One of the marked effects is the loanwords imported from other Angolan languages. Our objective is to analyze different Angolan texts, analyze the lexical forms used and conduct a comparative study with European Portuguese, aiming at identifying the possible loanwords in Angolan Portuguese. This process was automated, as well as the identification of all loanwords’ cotexts. In addition, we determine the lexical class of each loanword and the Angolan language of its origin. Most lexical loanwords come from the Kimbundu, although AP includes loanwords from some other Angolan languages too. Our study serves as a basis for preparing an Angolan regionalism dictionary. We noticed that more than 700 identified loanwords do not figure in the existing dictionaries. [ABSTRACT FROM AUTHOR]

Building a researchers affinity network through the automatic processing of their publications allows us to gain a perspective that goes beyond the networks established through co-authorship. The definition of the importance of each researcher is defined upon their bibliographic production volume, i.e., number of publications, and also upon their centrality in the general network of researchers. In fact, the centrality of a researcher in a network reveals its importance in communication flows with other researchers, thus assuming that communication between researchers is itself a relevant factor for organizational life and in its production. Both network and centrality concepts are better interpreted in a graphical way. In this study, we explore the workflow that will provide these visualizations and focus in the empirical selection of the most appropriate centrality measure. We also propose a centrality visualization method that facilitates the interpretation of the selected measures. [ABSTRACT FROM AUTHOR]

Most research on multi-document summarization explores methods that generate summaries based on queries regardless of the users' preferences. We note that, different users can generate somewhat different summaries on the basis of the same source data and query. This paper presents our study on how to exploit the information regards how users summarized their texts. Models of different users can be used either separately, or in an ensemble-like fashion. Machine learning methods are explored in the construction of the individual models. However, we explore yet another hypothesis. We believe that the sentences selected into the summary should be coherent and supplement each other in their meaning. One method to model this relationship between sentences is by detecting actor-object relationship (AOR). The sentences that satisfy this relationship have their importance value enhanced. This paper combines ensemble summarizing system and AOR to generate summaries. We have evaluated this method on DUC 2006 and DUC 2007 using ROUGE measure. Experimental results show the supervised method that exploits the ensemble summarizing system combined with AOR outperforms previous models when considering performance in query-based multi-document summarization tasks. [ABSTRACT FROM AUTHOR]

Several algorithms based on PageRank algorithm have been proposed to rank the document sentences in the multidocument summarization field and LexRank and T-LexRank algorithms are well known examples. In literature different concepts such as weighted inter-cluster edge, cluster-sensitive graph model and document-sensitive graph model have been proposed to improve LexRank and T-LexRank algorithms (e.g. DsR-G, DsR-Q) for multi-document summarization. In this paper, a density-based graph model for multi-document summarization is proposed by adding the concept of density to LexRank and T-LexRank algorithms. The resulting generic multi-document summarization systems, DensGS and DensGSD were evaluated on DUC 2004 while the query-based variants, DensQS, DensQSD were evaluated on DUC 2006, DUC 2007 and TAC 2010 task A. ROUGE measure was used in the evaluation. Experimental results show that density concept improves LexRank and T-LexRank algorithms and outperforms previous graph-based models (DsR-G and DsR-Q) in generic and query-based multi-document summarization tasks. Furthermore, the comparison of the number of iterations indicates that the density-based algorithm is faster than the other algorithms based on PageRank. [ABSTRACT FROM AUTHOR]

Data Mining (DM) researchers often focus on the development and testing of models for a single decision (e.g., direct mailing, churn detection, etc.). In practice, however, multiple decisions have often to be made simultaneously which are not independent and the best global solution is often not the combination of the best individual solutions. This problem can be addressed by searching for the overall best solution by using optimization methods based on the predictions made by the DM models. We describe one case study were this approach was used to optimize the layout of a retail store in order to maximize predicted sales. A metaheuristic is used to search different hypothesis of space allocations for multiple product categories, guided by the predictions made by regression models that estimate the sales for each category based on the assigned space. We test three metaheuristics and three regression algorithms on this task. Results show that the Particle Swam Optimization method guided by the models obtained with Random Forests and Support Vector Machines models obtain good results. We also provide insights about the relationship between the correctness of the regression models and the metaheuristics performance. [ABSTRACT FROM AUTHOR]

The present study, which is developed in the interface between linguistics and computer science within the framework of sentiment analysis, aims at making a computational analysis of opinion articles in the area of economics and finance. The main objectives of the study are: i) to determine the semantic orientation of text segments that express opinion by annotating the polarity (positive or negative) and the strength (scale from -3 to 3) of nouns and adjectives, and ii) to verify if a specific lexicon for the area of economics and finance has advantages in automatic annotation of sentiment over a general lexicon. To achieve these objectives, a corpus of 45 texts was selected and analyzed in 2 phases, by annotators with different training. First, a sample of 10 texts was annotated by linguists, co-authors of this paper, with the objective of developing a linguistic annotation model to ascertain the polarity and strength of words in opinion articles and extract the relevant words for this area of study. Then, a set of 35 texts was annotated by university students, replicating the annotation model developed during the first phase. Based on the linguistic annotation, the computer science team tried to establish to what extent a general sentiment lexicon for Portuguese - SentiLex - was sufficient to extract the sentiment of a sentence in a satisfactory manner or whether EconoLex, a specific sentiment lexicon, would be more efficient. The specific lexicon includes terms and multiword expressions that are relevant to the area of economics and finance and to Portuguese language, and it was developed by the authors of this study. The data was analyzed according to a blending methodology, qualitative and quantitative. The results of the analysis allow us to consider the following items as contributes of this study: i) the development of a linguistic annotation model for the analysis of the polarity and strength of the lexicon, especially of nouns and adjectives; ii) the key role, though not exclusive, of the adjectives to determine the polarity of opinion segments of the corpus articles; iii) the creation of a new specific sentiment lexicon for Portuguese in the area of economics and finance; iv) the improvement of the computational performance of EconoLex⨁SentiLex in relation to SentiLex regarding the performance in automatic annotation of sentiment. In spite of these positive results, there are some limitations, which we intend to overcome in the continuity of this interdisciplinary work, namely a more detailed linguistic analysis of the word classes that we studied, the consideration of other elements/ linguistic structures that are essential to ascertain the sentiment in NP/sentence, the extension of the corpus, the expansion of the specific lexicon of the area of economics and finance and the improvement of automatic methods for identifying evaluative words in texts of opinion and for assigning them polarity and strength. [ABSTRACT FROM AUTHOR]

The Traveling Salesman Problem (TSP) is one of the most studied optimization problems. Various meta-heuristics (MHs) have been proposed and investigated on many instances of this problem. It is widely accepted that the best MH varies for different instances. Ideally, one should be able to recommend the best MHs for a new TSP instance without having to execute them. However, this is a very difficult task. We address this task by using a meta-learning approach based on label ranking algorithms. These algorithms build a mapping that relates the characteristics of those instances (i.e., the meta-features) with the relative performance (i.e., the ranking) of MHs, based on (meta-)data extracted from TSP instances that have been already solved by those MHs. The success of this approach depends on the quality of the meta-features that describe the instances. In this work, we investigate four different sets of meta-features based on different measurements of the properties of TSP instances: edge and vertex measures, complex network measures, properties from the MHs, and subsampling landmarkers properties. The models are investigated in four different TSP scenarios presenting symmetry and connection strength variations. The experimental results indicate that meta-learning models can accurately predict rankings of MHs for different TSP scenarios. Good solutions for the investigated TSP instances can be obtained from the prediction of rankings of MHs, regardless of the learning algorithm used at the meta-level. The experimental results also show that the definition of the set of meta-features has an important impact on the quality of the solutions obtained. [ABSTRACT FROM AUTHOR]

Background Transmission models can aid understanding of disease dynamics and are useful in testing the efficiency of control measures. The aim of this study was to formulate an appropriate stochastic Susceptible-Infectious-Resistant/Carrier (SIR) model for Salmonella Typhimurium in pigs and thus estimate the transmission parameters between states. Results The transmission parameters were estimated using data from a longitudinal study of three Danish farrow-to-finish pig herds known to be infected. A Bayesian model framework was proposed, which comprised Binomial components for the transition from susceptible to infectious and from infectious to carrier; and a Poisson component for carrier to infectious. Cohort random effects were incorporated into these models to allow for unobserved cohortspecific variables as well as unobserved sources of transmission, thus enabling a more realistic estimation of the transmission parameters. In the case of the transition from susceptible to infectious, the cohort random effects were also time varying. The number of infectious pigs not detected by the parallel testing was treated as unknown, and the probability of non-detection was estimated using information about the sensitivity and specificity of the bacteriological and serological tests. The estimate of the transmission rate from susceptible to infectious was 0.33 [0.06, 1.52], from infectious to carrier was 0.18 [0.14, 0.23] and from carrier to infectious was 0.01 [0.0001, 0.04]. The estimate for the basic reproduction ration (R0) was 1.91 [0.78, 5.24]. The probability of non-detection was estimated to be 0.18 [0.12, 0.25]. Conclusions The proposed framework for stochastic SIR models was successfully implemented to estimate transmission rate parameters for Salmonella Typhimurium in swine field data. R0 was 1.91, implying that there was dissemination of the infection within pigs of the same cohort. There was significant temporal-cohort variability, especially at the susceptible to infectious stage. The model adequately fitted the data, allowing for both observed and unobserved sources of uncertainty (cohort effects, diagnostic test sensitivity), so leading to more reliable estimates of transmission parameters. [ABSTRACT FROM AUTHOR]

Background: The study of length of stay (LOS) outliers is important for the management and financing of hospitals. Our aim was to study variables associated with high LOS outliers and their evolution over time. Methods: We used hospital administrative data from inpatient episodes in public acute care hospitals in the Portuguese National Health Service (NHS), with discharges between years 2000 and 2009, together with some hospital characteristics. The dependent variable, LOS outliers, was calculated for each diagnosis related group (DRG) using a trim point defined for each year by the geometric mean plus two standard deviations. Hospitals were classified on the basis of administrative, economic and teaching characteristics. We also studied the influence of comorbidities and readmissions. Logistic regression models, including a multivariable logistic regression, were used in the analysis. All the logistic regressions were fitted using generalized estimating equations (GEE). Results: In near nine million inpatient episodes analysed we found a proportion of 3.9% high LOS outliers, accounting for 19.2% of total inpatient days. The number of hospital patient discharges increased between years 2000 and 2005 and slightly decreased after that. The proportion of outliers ranged between the lowest value of 3.6% (in years 2001 and 2002) and the highest value of 4.3% in 2009. Teaching hospitals with over 1,000 beds have significantly more outliers than other hospitals, even after adjustment to readmissions and several patient characteristics. Conclusions: In the last years both average LOS and high LOS outliers are increasing in Portuguese NHS hospitals. As high LOS outliers represent an important proportion in the total inpatient days, this should be seen as an important alert for the management of hospitals and for national health policies. As expected, age, type of admission, and hospital type were significantly associated with high LOS outliers. The proportion of high outliers does not seem to be related to their financial coverage; they should be studied in order to highlight areas for further investigation. The increasing complexity of both hospitals and patients may be the single most important determinant of high LOS outliers and must therefore be taken into account by health managers when considering hospital costs. [ABSTRACT FROM AUTHOR]