Luciano da F. Costa

Giovana D. da Silva, Filipi N. Silva, Henrique F. de Arruda et al.

Artistic pieces can be studied from several perspectives, one example being their reception among readers over time. In the present work, we approach this interesting topic from the standpoint of literary works, particularly assessing the task of predicting whether a book will become a best seller. Dissimilarly from previous approaches, we focused on the full content of books and considered visualization and classification tasks. We employed visualization for the preliminary exploration of the data structure and properties, involving SemAxis and linear discriminant analyses. Then, to obtain quantitative and more objective results, we employed various classifiers. Such approaches were used along with a dataset containing (i) books published from 1895 to 1924 and consecrated as best sellers by the Publishers Weekly Bestseller Lists and (ii) literary works published in the same period but not being mentioned in that list. Our comparison of methods revealed that the best-achieved result - combining a bag-of-words representation with a logistic regression classifier - led to an average accuracy of 0.75 both for the leave-one-out and 10-fold cross-validations. Such an outcome suggests that it is unfeasible to predict the success of books with high accuracy using only the full content of the texts. Nevertheless, our findings provide insights into the factors leading to the relative success of a literary work.

Alexandre Benatti, Luciano da F. Costa

Though performed almost effortlessly by humans, segmenting 2D gray-scale or color images into respective regions of interest (e.g.~background, objects, or portions of objects) constitutes one of the greatest challenges in science and technology as a consequence of several effects including dimensionality reduction(3D to 2D), noise, reflections, shades, and occlusions, among many other possibilities. While a large number of interesting related approaches have been suggested along the last decades, it was mainly thanks to the recent development of deep learning that more effective and general solutions have been obtained, currently constituting the basic comparison reference for this type of operation. Also developed recently, a multiset-based methodology has been described that is capable of encouraging image segmentation performance combining spatial accuracy, stability, and robustness while requiring little computational resources (hardware and/or training and recognition time). The interesting features of the multiset neurons methodology mostly follow from the enhanced selectivity and sensitivity, as well as good robustness to data perturbations and outliers, allowed by the coincidence similarity index on which the multiset approach to supervised image segmentation is founded. After describing the deep learning and multiset neurons approaches, the present work develops comparison experiments between them which are primarily aimed at illustrating their respective main interesting features when applied to the adopted specific type of data and parameter configurations. While the deep learning approach confirmed its potential for performing image segmentation, the alternative multiset methodology allowed for enhanced accuracy while requiring little computational resources.

Alexandre Benatti, Luciano da F. Costa

The subject of features normalization plays an important central role in data representation, characterization, visualization, analysis, comparison, classification, and modeling, as it can substantially influence and be influenced by all of these activities and respective aspects. The selection of an appropriate normalization method needs to take into account the type and characteristics of the involved features, the methods to be used subsequently for the just mentioned data processing, as well as the specific questions being considered. After briefly considering how normalization constitutes one of the many interrelated parts typically involved in data analysis and modeling, the present work addressed the important issue of feature normalization from the perspective of uniform and proportional (right skewed) features and comparison operations. More general right skewed features are also considered in an approximated manner. Several concepts, properties, and results are described and discussed, including the description of a duality relationship between uniform and proportional feature spaces and respective comparisons, specifying conditions for consistency between comparisons in each of the two domains. Two normalization possibilities based on non-centralized dispersion of features are also presented, and also described is a modified version of the Jaccard similarity index which incorporates intrinsically normalization. Preliminary experiments are presented in order to illustrate the developed concepts and methods.

Alexandre Benatti, Luciano da F. Costa

Pattern recognition constitutes a particularly important task underlying a great deal of scientific and technologica activities. At the same time, pattern recognition involves several challenges, including the choice of features to represent the data elements, as well as possible respective transformations. In the present work, the classification potential of the Euclidean distance and a dissimilarity index based on the coincidence similarity index are compared by using the k-neighbors supervised classification method respectively to features resulting from several types of transformations of one- and two-dimensional symmetric densities. Given two groups characterized by respective densities without or with overlap, different types of respective transformations are obtained and employed to quantitatively evaluate the performance of k-neighbors methodologies based on the Euclidean distance an coincidence similarity index. More specifically, the accuracy of classifying the intersection point between the densities of two adjacent groups is taken into account for the comparison. Several interesting results are described and discussed, including the enhanced potential of the dissimilarity index for classifying datasets with right skewed feature densities, as well as the identification that the sharpness of the comparison between data elements can be independent of the respective supervised classification performance.

Bárbara C. e Souza, Filipi N. Silva, Henrique F. de Arruda et al.

Several complex systems are characterized by presenting intricate characteristics taking place at several scales of time and space. These multiscale characterizations are used in various applications, including better understanding diseases, characterizing transportation systems, and comparison between cities, among others. In particular, texts are also characterized by a hierarchical structure that can be approached by using multi-scale concepts and methods. The multiscale properties of texts constitute a subject worth further investigation. In addition, more effective approaches to text characterization and analysis can be obtained by emphasizing words with potentially more informational content. The present work aims at developing these possibilities while focusing on mesoscopic representations of networks. More specifically, we adopt an extension to the mesoscopic approach to represent text narratives, in which only the recurrent relationships among tagged parts of speech (subject, verb and direct object) are considered to establish connections among sequential pieces of text (e.g., paragraphs). The characterization of the texts was then achieved by considering scale-dependent complementary methods: accessibility, symmetry and recurrence signatures. In order to evaluate the potential of these concepts and methods, we approached the problem of distinguishing between literary genres (fiction and non-fiction). A set of 300 books organized into the two genres was considered and were compared by using the aforementioned approaches. All the methods were capable of differentiating to some extent between the two genres. The accessibility and symmetry reflected the narrative asymmetries, while the recurrence signature provided a more direct indication about the non-sequential semantic connections taking place along the narrative.

Luciano da F. Costa

Multisets are an intuitive extension of the traditional concept of sets that allow repetition of elements, with the number of times each element appears being understood as the respective multiplicity. Recent generalizations of multisets to real-valued functions, accounting for possibly negative values, have paved the way to a number of interesting implications and applications, including respective implementations as electronic systems. The basic multiset operations include the set complementation (sign change), intersection (minimum between two values), union (maximum between two values), difference and sum (identical to the algebraic counterparts). When applied to functions or signals, the sign and conjoint sign functions are also required. Given that signals are functions, it becomes possible to effectively translate the multiset and multifunction operations to analog electronics, which is the objective of the present work. It is proposed that effective multiset operations capable of high performance self and cross-correlation can be obtained with relative simplicity in either discrete or integrated circuits. The problem of switching noise is also briefly discussed. The present results have great potential for applications and related developments in analog and digital electronics, as well as for pattern recognition, signal processing, and deep learning.

Luciano da F. Costa

The present work reports a comparative performance of artificial neurons obtained in terms of the real-valued Jaccard and coincidence similarity indices and respectively derived functionals. The interiority index and classic cross-correlation are also included for comparison purposes. After presenting the basic concepts related to real-valued multisets and the adopted similarity metrics, including the generalization of the real-valued Jaccard and coincidence indices to higher orders, we proceed to studying the response of a single neuron, not taking into account the output non-linearity (e.g.~sigmoid), respectively to the detection of gaussian two-dimensional stimulus in presence of displacement, magnification, intensity variation, noise and interference from additional patterns. It is shown that the real-valued Jaccard and coincidence approaches are substantially more robust and effective than the interiority index and the classic cross-correlation. The coincidence-based neurons are shown to have the best overall performance respectively to the considered type of data and perturbations. The potential of the multiset neurons is further illustrated with respect to the challenging problem of image segmentation, leading to impressive cost/benefit performance. The reported concepts, methods, and results, have substantial implications not only for pattern recognition and machine learning, but also regarding neurobiology and neuroscience.

Luciano da F. Costa

The real-valued Jaccard and coincidence indices, in addition to their conceptual and computational simplicity, have been verified to be able to provide promising results in tasks such as template matching, tending to yield peaks that are sharper and narrower than those typically obtained by standard cross-correlation, while also attenuating substantially secondary matchings. In this work, the multiset-based correlations based on the real-valued multiset Jaccard and coincidence indices are compared from the perspective of template matching, with encouraging results which have implications for pattern recognition, deep learning, and scientific modeling in general. The multiset-based correlation methods, and especially the coincidence index, presented remarkable performance characterized by sharper and narrower peaks while secondary peaks were attenuated, which was maintained even in presence of intense levels of noise. In particular, the two methods derived from the coincidence index led to particularly interesting results. The cross correlation, however, presented the best robustness to symmetric additive noise, which suggested a new combination of the considered approaches. After a preliminary investigation of the relative performance of the multiset approaches, as well as the classic cross-correlation, a systematic comparison framework is proposed and applied for the study of the aforementioned methods. Several results are reported, including the confirmation, at least for the considered type of data, of the coincidence correlation as providing enhanced performance regarding detection of narrow, sharp peaks while secondary matches are duly attenuated. The combined method also resulted promising for dealing with signals in presence of intense additive noise.

Luciano da F. Costa

The objective quantification of similarity between two mathematical structures constitutes a recurrent issue in science and technology. In the present work, we developed a principled approach that took the Kronecker's delta function of two scalar values as the prototypical reference for similarity quantification and then derived for more yielding indices, three of which bound between 0 and 1. Generalizations of these indices to take into account the sign of the scalar values were then presented and developed to multisets, vectors, and functions in real spaces. Several important results have been obtained, including the interpretation of the Jaccard index as a yielding implementation of the Kronecker's delta function. When generalized to real functions, the four described similarity indices become respective functionals, which can then be employed to obtain associated operations of convolution and correlation.

Luciano da F. Costa

Quantifying the similarity between two mathematical structures or datasets constitutes a particularly interesting and useful operation in several theoretical and applied problems. Aimed at this specific objective, the Jaccard index has been extensively used in the most diverse types of problems, also motivating some respective generalizations. The present work addresses further generalizations of this index, including its modification into a coincidence index capable of accounting also for the level of relative interiority between the two compared entities, as well as respective extensions for sets in continuous vector spaces, the generalization to multiset addition, densities and generic scalar fields, as well as a means to quantify the joint interdependence between two random variables. The also interesting possibility to take into account more than two sets has also been addressed, including the description of an index capable of quantifying the level of chaining between three structures. Several of the described and suggested eneralizations have been illustrated with respect to numeric case examples. It is also posited that these indices can play an important role while analyzing and integrating datasets in modeling approaches and pattern recognition activities, including as a measurement of clusters similarity or separation and as a resource for representing and analyzing complex networks.

Luciano da F. Costa

In the present work, we describe a framework for modeling how models can be built that integrates concepts and methods from a wide range of fields. The information schism between the real-world and that which can be gathered and considered by any individual information processing agent is characterized and discussed, followed by the presentation of a series of the adopted requisites while developing the modeling approach. The issue of mapping from datasets into models is subsequently addressed, as well as some of the respectively implied difficulties and limitations. Based on these considerations, an approach to meta modeling how models are built is then progressively developed. First, the reference M* meta model framework is presented, which relies critically in associating whole datasets and respective models in terms of a strict equivalence relation. Among the interesting features of this model are its ability to bridge the gap between data and modeling, as well as paving the way to an algebra of both data and models which can be employed to combine models into hierarchical manner. After illustrating the M* model in terms of patterns derived from regular lattices, the reported modeling approach continues by discussing how sampling issues, error and overlooked data can be addressed, leading to the $M^{<ε>}$ variant, illustrated respectively to number theory. The situation in which the data needs to be represented in terms of respective probability densities is treated next, yielding the $M^{<σ>}$ meta model, which is then illustrated respectively to a real-world dataset (iris flowers data). Several considerations about how the developed framework can provide insights about data clustering, complexity, collaborative research, deep learning, and creativity are then presented, followed by overall conclusions.

Henrique F. de Arruda, Sandro M. Reia, Filipi N. Silva et al.

Poetry and prose are written artistic expressions that help us to appreciate the reality we live. Each of these styles has its own set of subjective properties, such as rhyme and rhythm, which are easily caught by a human reader's eye and ear. With the recent advances in artificial intelligence, the gap between humans and machines may have decreased, and today we observe algorithms mastering tasks that were once exclusively performed by humans. In this paper, we propose an automated method to distinguish between poetry and prose based solely on aural and rhythmic properties. In other to compare prose and poetry rhythms, we represent the rhymes and phones as temporal sequences and thus we propose a procedure for extracting rhythmic features from these sequences. The classification of the considered texts using the set of features extracted resulted in a best accuracy of 0.78, obtained with a neural network. Interestingly, by using an approach based on complex networks to visualize the similarities between the different texts considered, we found that the patterns of poetry vary much more than prose. Consequently, a much richer and complex set of rhythmic possibilities tends to be found in that modality.

Eric K. Tokuda, Cesar H. Comin, Luciano da F. Costa

An important issue in clustering concerns the avoidance of false positives while searching for clusters. This work addressed this problem considering agglomerative methods, namely single, average, median, complete, centroid and Ward's approaches applied to unimodal and bimodal datasets obeying uniform, gaussian, exponential and power-law distributions. A model of clusters was also adopted, involving a higher density nucleus surrounded by a transition, followed by outliers. This paved the way to defining an objective means for identifying the clusters from dendrograms. The adopted model also allowed the relevance of the clusters to be quantified in terms of the height of their subtrees. The obtained results include the verification that many methods detect two clusters in unimodal data. The single-linkage method was found to be more resilient to false positives. Also, several methods detected clusters not corresponding directly to the nucleus. The possibility of identifying the type of distribution was also investigated.

Luciano da F. Costa

After generalizing the concept of clusters to incorporate clusters that are linked to other clusters through some relatively narrow bridges, an approach for detecting patches of separation between these clusters is developed based on an agglomerative clustering, more specifically the single-linkage, applied to one-dimensional slices obtained from respective feature spaces. The potential of this method is illustrated with respect to the analyses of clusterless uniform and normal distributions of points, as well as a one-dimensional clustering model characterized by two intervals with high density of points separated by a less dense interstice. This partial clustering method is then considered as a means of feature selection and cluster identification, and two simple but potentially effective respective methods are described and illustrated with respect to some hypothetical situations.

Caroline Ceribeli, Henrique F. de Arruda, Luciano da F. Costa

The understanding of how science works can contribute to making scientific development more effective. In this paper, we report an analysis of the organization and interconnection between two important issues in chemistry, namely mass spectrometry (MS) and capillary electrophoresis (CE). For that purpose, we employed science of science techniques based on complex networks. More specifically, we considered a citation network in which the nodes and connections represent papers and citations, respectively. Interesting results were found, including a good separation between some clusters of articles devoted to instrumentation techniques and applications. However, the papers that describe CE-MS did not lead to a well-defined cluster. In order to better understand the organization of the citation network, we considered a multi-scale analysis, in which we used the information regarding sub-clusters. Firstly, we analyzed the sub-cluster of the first article devoted to the coupling between CE and MS, which was found to be a good representation of its sub-cluster. The second analysis was about the sub-cluster of a seminal paper known to be the first that dealt with proteins by using CE-MS. By considering the proposed methodologies, our paper paves the way for researchers working with both techniques, since it elucidates the knowledge organization and can therefore lead to better literature reviews.

Thomas Peron, Francisco A. Rodrigues, Luciano da F. Costa

Since the landmarks established by the Cremonese school in the 16th century, the history of violin design has been marked by experimentation. While great effort has been invested since the early 19th century by the scientific community on researching violin acoustics, substantially less attention has been given to the statistical characterization of how the violin shape evolved over time. In this paper we study the morphology of violins retrieved from the Musical Instrument Museums Online (MIMO) database -- the largest freely accessible platform providing information about instruments held in public museums. From the violin images, we derive a set of measurements that reflect relevant geometrical features of the instruments. The application of Principal Component Analysis (PCA) uncovered similarities between violin makers and their respective copyists, as well as among luthiers belonging to the same family lineage, in the context of historical narrative. Combined with a time-windowed approach, thin plate splines visualizations revealed that the average violin outline has remained mostly stable over time, not adhering to any particular trends of design across different periods in music history.

Henrique F. de Arruda, Vanessa Q. Marinho, Luciano da F. Costa et al.

With the increasing number of texts made available on the Internet, many applications have relied on text mining tools to tackle a diversity of problems. A relevant model to represent texts is the so-called word adjacency (co-occurrence) representation, which is known to capture mainly syntactical features of texts.In this study, we introduce a novel network representation that considers the semantic similarity between paragraphs. Two main properties of paragraph networks are considered: (i) their ability to incorporate characteristics that can discriminate real from artificial, shuffled manuscripts and (ii) their ability to capture syntactical and semantic textual features. Our results revealed that real texts are organized into communities, which turned out to be an important feature for discriminating them from artificial texts. Interestingly, we have also found that, differently from traditional co-occurrence networks, the adopted representation is able to capture semantic features. Additionally, the proposed framework was employed to analyze the Voynich manuscript, which was found to be compatible with texts written in natural languages. Taken together, our findings suggest that the proposed methodology can be combined with traditional network models to improve text classification tasks.

Henrique F. de Arruda, Vanessa Q. Marinho, Thales S. Lima et al.

Text network analysis has received increasing attention as a consequence of its wide range of applications. In this work, we extend a previous work founded on the study of topological features of mesoscopic networks. Here, the geometrical properties of visualized networks are quantified in terms of several image analysis techniques and used as subsidies for authorship attribution. It was found that the visual features account for performance similar to that achieved by using topological measurements. In addition, the combination of these two types of features improved the performance.

Mayra Z. Rodriguez, Cesar H. Comin, Dalcimar Casanova et al.

Many real-world systems can be studied in terms of pattern recognition tasks, so that proper use (and understanding) of machine learning methods in practical applications becomes essential. While a myriad of classification methods have been proposed, there is no consensus on which methods are more suitable for a given dataset. As a consequence, it is important to comprehensively compare methods in many possible scenarios. In this context, we performed a systematic comparison of 7 well-known clustering methods available in the R language. In order to account for the many possible variations of data, we considered artificial datasets with several tunable properties (number of classes, separation between classes, etc). In addition, we also evaluated the sensitivity of the clustering methods with regard to their parameters configuration. The results revealed that, when considering the default configurations of the adopted methods, the spectral approach usually outperformed the other clustering algorithms. We also found that the default configuration of the adopted implementations was not accurate. In these cases, a simple approach based on random selection of parameters values proved to be a good alternative to improve the performance. All in all, the reported approach provides subsidies guiding the choice of clustering algorithms.

Henrique F. de Arruda, Filipi N. Silva, Vanessa Q. Marinho et al.

Statistical techniques that analyze texts, referred to as text analytics, have departed from the use of simple word count statistics towards a new paradigm. Text mining now hinges on a more sophisticated set of methods, including the representations in terms of complex networks. While well-established word-adjacency (co-occurrence) methods successfully grasp syntactical features of written texts, they are unable to represent important aspects of textual data, such as its topical structure, i.e. the sequence of subjects developing at a mesoscopic level along the text. Such aspects are often overlooked by current methodologies. In order to grasp the mesoscopic characteristics of semantical content in written texts, we devised a network model which is able to analyze documents in a multi-scale fashion. In the proposed model, a limited amount of adjacent paragraphs are represented as nodes, which are connected whenever they share a minimum semantical content. To illustrate the capabilities of our model, we present, as a case example, a qualitative analysis of "Alice's Adventures in Wonderland". We show that the mesoscopic structure of a document, modeled as a network, reveals many semantic traits of texts. Such an approach paves the way to a myriad of semantic-based applications. In addition, our approach is illustrated in a machine learning context, in which texts are classified among real texts and randomized instances.

Cesar H. Comin, Thomas K. DM. Peron, Filipi N. Silva et al.

The increasing interest in complex networks research has been a consequence of several intrinsic features of this area, such as the generality of the approach to represent and model virtually any discrete system, and the incorporation of concepts and methods deriving from many areas, from statistical physics to sociology, which are often used in an independent way. Yet, for this same reason, it would be desirable to integrate these various aspects into a more coherent and organic framework, which would imply in several benefits normally allowed by the systematization in science, including the identification of new types of problems and the cross-fertilization between fields. More specifically, the identification of the main areas to which the concepts frequently used in complex networks can be applied paves the way to adopting and applying a larger set of concepts and methods deriving from those respective areas. Among the several areas that have been used in complex networks research, pattern recognition, optimization, linear algebra, and time series analysis seem to play a more basic and recurrent role. In the present manuscript, we propose a systematic way to integrate the concepts from these diverse areas regarding complex networks research. In order to do so, we start by grouping the multidisciplinary concepts into three main groups, namely features, similarity, and network connectivity. Then we show that several of the analysis and modeling approaches to complex networks can be thought as a composition of maps between these three groups, with emphasis on nine main types of mappings, which are presented and illustrated. Such a systematization of principles and approaches also provides an opportunity to review some of the most closely related works in the literature, which is also developed in this article.

Henrique F. de Arruda, Luciano da F. Costa, Diego R. Amancio

Many real systems have been modelled in terms of network concepts, and written texts are a particular example of information networks. In recent years, the use of network methods to analyze language has allowed the discovery of several interesting findings, including the proposition of novel models to explain the emergence of fundamental universal patterns. While syntactical networks, one of the most prevalent networked models of written texts, display both scale-free and small-world properties, such representation fails in capturing other textual features, such as the organization in topics or subjects. In this context, we propose a novel network representation whose main purpose is to capture the semantical relationships of words in a simple way. To do so, we link all words co-occurring in the same semantic context, which is defined in a threefold way. We show that the proposed representations favours the emergence of communities of semantically related words, and this feature may be used to identify relevant topics. The proposed methodology to detect topics was applied to segment selected Wikipedia articles. We have found that, in general, our methods outperform traditional bag-of-words representations, which suggests that a high-level textual representation may be useful to study semantical features of texts.

Henrique F. de Arruda, Luciano da F. Costa, Diego R. Amancio

Statistical methods have been widely employed in recent years to grasp many language properties. The application of such techniques have allowed an improvement of several linguistic applications, which encompasses machine translation, automatic summarization and document classification. In the latter, many approaches have emphasized the semantical content of texts, as it is the case of bag-of-word language models. This approach has certainly yielded reasonable performance. However, some potential features such as the structural organization of texts have been used only on a few studies. In this context, we probe how features derived from textual structure analysis can be effectively employed in a classification task. More specifically, we performed a supervised classification aiming at discriminating informative from imaginative documents. Using a networked model that describes the local topological/dynamical properties of function words, we achieved an accuracy rate of up to 95%, which is much higher than similar networked approaches. A systematic analysis of feature relevance revealed that symmetry and accessibility measurements are among the most prominent network measurements. Our results suggest that these measurements could be used in related language applications, as they play a complementary role in characterizing texts.

Diego R. Amancio, Filipi N. Silva, Luciano da F. Costa

Several characteristics of written texts have been inferred from statistical analysis derived from networked models. Even though many network measurements have been adapted to study textual properties at several levels of complexity, some textual aspects have been disregarded. In this paper, we study the symmetry of word adjacency networks, a well-known representation of text as a graph. A statistical analysis of the symmetry distribution performed in several novels showed that most of the words do not display symmetric patterns of connectivity. More specifically, the merged symmetry displayed a distribution similar to the ubiquitous power-law distribution. Our experiments also revealed that the studied metrics do not correlate with other traditional network measurements, such as the degree or betweenness centrality. The effectiveness of the symmetry measurements was verified in the authorship attribution task. Interestingly, we found that specific authors prefer particular types of symmetric motifs. As a consequence, the authorship of books could be accurately identified in 82.5% of the cases, in a dataset comprising books written by 8 authors. Because the proposed measurements for text analysis are complementary to the traditional approach, they can be used to improve the characterization of text networks, which might be useful for related applications, such as those relying on the identification of topical words and information retrieval.

Diego R. Amancio, Osvaldo N. Oliveira, Luciano da F. Costa

There are different ways to define similarity for grouping similar texts into clusters, as the concept of similarity may depend on the purpose of the task. For instance, in topic extraction similar texts mean those within the same semantic field, whereas in author recognition stylistic features should be considered. In this study, we introduce ways to classify texts employing concepts of complex networks, which may be able to capture syntactic, semantic and even pragmatic features. The interplay between the various metrics of the complex networks is analyzed with three applications, namely identification of machine translation (MT) systems, evaluation of quality of machine translated texts and authorship recognition. We shall show that topological features of the networks representing texts can enhance the ability to identify MT systems in particular cases. For evaluating the quality of MT texts, on the other hand, high correlation was obtained with methods capable of capturing the semantics. This was expected because the golden standards used are themselves based on word co-occurrence. Notwithstanding, the Katz similarity, which involves semantic and structure in the comparison of texts, achieved the highest correlation with the NIST measurement, indicating that in some cases the combination of both approaches can improve the ability to quantify quality in MT. In authorship recognition, again the topological features were relevant in some contexts, though for the books and authors analyzed good results were obtained with semantic features as well. Because hybrid approaches encompassing semantic and topological features have not been extensively used, we believe that the methodology proposed here may be useful to enhance text classification considerably, as it combines well-established strategies.

Diego R. Amancio, Eduardo G. Altmann, Diego Rybski et al.

While the use of statistical physics methods to analyze large corpora has been useful to unveil many patterns in texts, no comprehensive investigation has been performed investigating the properties of statistical measurements across different languages and texts. In this study we propose a framework that aims at determining if a text is compatible with a natural language and which languages are closest to it, without any knowledge of the meaning of the words. The approach is based on three types of statistical measurements, i.e. obtained from first-order statistics of word properties in a text, from the topology of complex networks representing text, and from intermittency concepts where text is treated as a time series. Comparative experiments were performed with the New Testament in 15 different languages and with distinct books in English and Portuguese in order to quantify the dependency of the different measurements on the language and on the story being told in the book. The metrics found to be informative in distinguishing real texts from their shuffled versions include assortativity, degree and selectivity of words. As an illustration, we analyze an undeciphered medieval manuscript known as the Voynich Manuscript. We show that it is mostly compatible with natural languages and incompatible with random texts. We also obtain candidates for key-words of the Voynich Manuscript which could be helpful in the effort of deciphering it. Because we were able to identify statistical measurements that are more dependent on the syntax than on the semantics, the framework may also serve for text analysis in language-dependent applications.

Diego R. Amancio, Osvaldo N. Oliveira, Luciano da F. Costa

Many features of complex systems can now be unveiled by applying statistical physics methods to treat them as social networks. The power of the analysis may be limited, however, by the presence of ambiguity in names, e.g., caused by homonymy in collaborative networks. In this paper we show that the ability to distinguish between homonymous authors is enhanced when longer-distance connections are considered, rather than looking at only the immediate neighbors of a node in the collaborative network. Optimized results were obtained upon using the 3rd hierarchy in connections. Furthermore, reasonable distinction among authors could also be achieved upon using pattern recognition strategies for the data generated from the topology of the collaborative network. These results were obtained with a network from papers in the arXiv repository, into which homonymy was deliberately introduced to test the methods with a controlled, reliable dataset. In all cases, several methods of supervised and unsupervised machine learning were used, leading to the same overall results. The suitability of using deeper hierarchies and network topology was confirmed with a real database of movie actors, with the additional finding that the distinguishing ability can be further enhanced by combining topology features and long-range connections in the collaborative network.

Diego R. Amancio, Sandra M. Aluisio, Osvaldo N. Oliveira et al.

Methods from statistical physics, such as those involving complex networks, have been increasingly used in quantitative analysis of linguistic phenomena. In this paper, we represented pieces of text with different levels of simplification in co-occurrence networks and found that topological regularity correlated negatively with textual complexity. Furthermore, in less complex texts the distance between concepts, represented as nodes, tended to decrease. The complex networks metrics were treated with multivariate pattern recognition techniques, which allowed us to distinguish between original texts and their simplified versions. For each original text, two simplified versions were generated manually with increasing number of simplification operations. As expected, distinction was easier for the strongly simplified versions, where the most relevant metrics were node strength, shortest paths and diversity. Also, the discrimination of complex texts was improved with higher hierarchical network metrics, thus pointing to the usefulness of considering wider contexts around the concepts. Though the accuracy rate in the distinction was not as high as in methods using deep linguistic knowledge, the complex network approach is still useful for a rapid screening of texts whenever assessing complexity is essential to guarantee accessibility to readers with limited reading ability

Diego R. Amancio, Osvaldo N. Oliveira, Luciano da F. Costa

The automatic disambiguation of word senses (i.e., the identification of which of the meanings is used in a given context for a word that has multiple meanings) is essential for such applications as machine translation and information retrieval, and represents a key step for developing the so-called Semantic Web. Humans disambiguate words in a straightforward fashion, but this does not apply to computers. In this paper we address the problem of Word Sense Disambiguation (WSD) by treating texts as complex networks, and show that word senses can be distinguished upon characterizing the local structure around ambiguous words. Our goal was not to obtain the best possible disambiguation system, but we nevertheless found that in half of the cases our approach outperforms traditional shallow methods. We show that the hierarchical connectivity and clustering of words are usually the most relevant features for WSD. The results reported here shine light on the relationship between semantic and structural parameters of complex networks. They also indicate that when combined with traditional techniques the complex network approach may be useful to enhance the discrimination of senses in large texts