This paper presents MOD-kt, a modular framework designed to bridge the gap between modern language models and key-term-based document clustering. One of the main challenges of using neural language models for key-term-based clustering is the mismatch between the interpretability of the underlying document representation (i.e. document embeddings) and the more intuitive semantic elements that allow the user to guide the clustering process (i.e. key-terms). Our framework acts as a communication layer between word and document models, enabling key-term-based clustering in the context of document and word models with a flexible and adaptable architecture. We report a comparison of the performance of multiple neural language models on clustering, considering a selected range of relevance metrics. Additionally, a qualitative user study was conducted to illustrate the framework's potential for intuitive user-guided quality clustering of document collections.

Abstract Retrieving information from document collections is necessary in many contexts, e.g. researchers search for papers on a topic, physicians search for records of patients with a certain condition and police investigators seek relationships between different criminal reports. Finding relevant textual content in a corpus can be challenging in scenarios where the users expect a retrieval process with high recall. Visual Analytics (VA) systems that integrate interactive visualizations and machine learning algorithms are often advocated to support retrieval tasks in such complex scenarios. However, few studies report an end-user perspective on the utility of such systems. We present results from observational studies on VA-supported information retrieval conducted with graduate students and researchers using a system to explore collections of scientific papers. While users have, in general, positive views of the system’s potential to facilitate their retrieval tasks, some faced practical difficulties in using it effectively, and we found considerable variation in their assessment of specific functionalities. Our findings reinforce the potential of VA systems and also the importance of carefully informing users of the underlying conceptual models in such systems and their limitations.

A multilevel method is a scalable strategy to solve optimization problems in large bipartite networks, which operates in three stages. Initially the input network is iteratively coarsened into a hierarchy of gradually smaller networks. Coarsening implies in collapsing vertices into so-called super-vertices which inherit properties of their originating vertices. An initial solution is obtained executing the target algorithm in the coarsest network. Finally, this solution is successively projected back over the inverse sequence of coarsened networks, up to the initial one, yielding an approximate final solution. Despite its potential applicability, the strategy faces several theoretical and practical limitations. Coarsening is usually attained following a user-defined policy to match vertices pairwise. However, the network reduction process is extremely slow and may yield degraded solutions due to propagation of poor matches. Additionally, proper parameterization of coarsening algorithms is difficult, as well as ensuring the super-vertices preserve the relevant properties. We address these issues with a near-linear complexity coarsening strategy based on weight-constrained label propagation. Our strategy collapses groups of vertices, rather than pairs, yielding faster and more extensive network reduction. Moreover, users may specify the desired size of the coarsest network and control super-vertex weights. The applicability of our solution is illustrated in multiple scenarios, namely: multilevel implementation of an existing high-cost community detection algorithm; as a direct community detection algorithm; finally, network visualization, in connection with force-directed graph drawing algorithms. Results provide empirical evidence on the potential of our proposal to foster novel applications of the multilevel method in bipartite networks.

In this paper, we propose TRIVIR, a novel interactive visualization tool powered by an Information Retrieval (IR) engine that implements an active learning protocol to support IR with high recall. The system integrates multiple graphical views in order to assist the user identifying the relevant documents in a collection, including a content-based similarity map obtained with multidimensional projection techniques. Given representative documents as queries, users can interact with the views to label documents as relevant/not relevant, and this information is used to train a machine learning (ML) algorithm which suggests other potentially relevant documents on demand. TRIVIR offers two major advantages over existing visualization systems for IR. First, it merges the ML algorithm output into the visualization, while supporting several user interactions in order to enhance and speed up its convergence. Second, it tackles the problem of vocabulary mismatch, by providing term's synonyms and a view that conveys how the terms are used within the collection. Besides, TRIVIR has been developed as a flexible front-end interface that can be associated with distinct text representations and multidimensional projection techniques. We describe two use cases conducted with collaborators who are potential users of TRIVIR. Results show that the system simplified the search for relevant documents in large collections, based on the context in which the terms occur.

Studies in soundscape ecology can generate large volumes of audio recordings collected over extensive time intervals. Extracting information from such data is challenging and time demanding. Important tasks, in this context, are to identify occurrences of acoustic events of interest and find out which combination of audio features are suitable for characterizing specific events or describing a particular soundscape. Researchers in soundscape ecology have been investigating approaches to accomplish such tasks effectively, and there is a demand for tools capable of assisting analysts in investigating large databases of ecological recordings. In this paper we describe a visualization framework for this purpose. The system includes multiple functionalities for soundscape analysis, comprising audio feature extraction, identification of relevant acoustic events by means of visualizations associated with audio playbacks, and event characterization by means of subspace feature analysis, also assisted by visualizations. The system implements a user-driven iterative pipeline that gives domain experts means to search for, identify and characterize acoustic events, gathering insight on which features better describe them and their originating soundscape.

Multilevel approaches aim at reducing the cost of a target algorithm over a given network by applying it to a coarsened (or reduced) version of the original network. They have been successfully employed in a variety of problems, most notably community detection. However, current solutions are not directly applicable to bipartite networks and the literature lacks studies that illustrate their application for solving multilevel optimization problems in such networks. This article addresses this gap and introduces a multilevel optimization approach for bipartite networks and the implementation of a general multilevel framework including novel algorithms for coarsening and uncorsening, applicable to a variety of problems. We analyze how the proposed multilevel strategy affects the topological features of bipartite networks and show that a controlled coarsening strategy can preserve properties such as degree and clustering coefficient centralities. The applicability of the general framework is illustrated in two optimization problems, one for solving the Barber's modularity for community detection and the second for dimensionality reduction in text classification. We show that the solutions thus obtained are statistically equivalent, regarding accuracy, to those of conventional approaches, whilst requiring considerably lower execution times.

We describe a specialized methodology for segmenting 2D microscopy digital images of freshwater green microalgae. The goal is to obtain representative algae shapes to extract morphological features to be employed in a posterior step of taxonomical classification of the species. The proposed methodology relies on the seeded region growing principle and on a fine-tuned filtering preprocessing stage to smooth the input image. A contrast enhancement process then takes place to highlight algae regions on a binary pre-segmentation image. This binary image is also employed to determine where to place the seed points and to estimate the statistical probability distributions that characterize the target regions, i.e., the algae areas and the background, respectively. These preliminary stages produce the required information to set the homogeneity criterion for region growing. We evaluate the proposed methodology by comparing its resulting segmentations with a set of corresponding ground-truth segmentations (provided by an expert biologist) and also with segmentations obtained with existing strategies. The experimental results show that our solution achieves highly accurate segmentation rates with greater efficiency, as compared with the performance of standard segmentation approaches and with an alternative previous solution, based on level-sets, also specialized to handle this particular problem.

The worldwide adoption of Twitter turned it into one of the most popular platforms for content analysis as it serves as a gauge of the public’s feeling and opinion on a variety of topics. This is particularly true of political discussions and lawmakers’ actions and initiatives. Yet, one common but unrealistic assumption is that the data of interest for analysis is readily available in a comprehensive and accurate form. Data need to be retrieved, but due to the brevity and noisy nature of Twitter content, it is difficult to formulate user queries that match relevant posts that use different terminology without introducing a considerable volume of unwanted content. This problem is aggravated when the analysis must contemplate multiple and related topics of interest, for which comments are being concurrently posted. This article presents Active Tweet Retrieval Visualization (ATR-Vis), a user-driven visual approach for the retrieval of Twitter content applicable to this scenario. The method proposes a set of active retrieval strategies to involve an analyst in such a way that a major improvement in retrieval coverage and precision is attained with minimal user effort. ATR-Vis enables non-technical users to benefit from the aforementioned active learning strategies by providing visual aids to facilitate the requested supervision. This supports the exploration of the space of potentially relevant tweets, and affords a better understanding of the retrieval results. We evaluate our approach in scenarios in which the task is to retrieve tweets related to multiple parliamentary debates within a specific time span. We collected two Twitter datasets, one associated with debates in the Canadian House of Commons during a particular week in May 2014, and another associated with debates in the Brazilian Federal Senate during a selected week in May 2015. The two use cases illustrate the effectiveness of ATR-Vis for the retrieval of relevant tweets, while quantitative results show that our approach achieves high retrieval quality with a modest amount of supervision. Finally, we evaluated our tool with three external users who perform searching in social media as part of their professional work.

Technical writing in professional environments, such as user manual authoring for new products, is a task that relies heavily on reuse of content. Therefore, technical content is typically created following a strategy where modular units of text have references to each other. One of the main challenges faced by technical authors is to avoid duplicating existing content, as this adds unnecessary effort, generates undesirable inconsistencies, and dramatically increases maintenance and translation costs. However, there are few computational tools available to support this activity. This paper investigates the use of different similarity methods for the task of identification of reuse opportunities in technical writing. We evaluated our results using existing ground truth as well as feedback from technical authors. Finally, we also propose a tool that combines text similarity algorithms with interactive visualizations to aid authors in understanding differences in a collection of topics and identifying reuse opportunities.

Similarity-based layouts generated by multidimensional projections or other dimension reduction techniques are commonly used to visualize high-dimensional data. Many projection techniques have been recently proposed addressing different objectives and application domains. Nonetheless, very little is known about the effectiveness of the generated layouts from a user's perspective, how distinct layouts from the same data compare regarding the typical visualization tasks they support, or how domain-specific issues affect the outcome of the techniques. Learning more about projection usage is an important step towards both consolidating their role in high-dimensional data analysis and taking informed decisions when choosing techniques. This work provides a contribution towards this goal. We describe the results of an investigation on the performance of layouts generated by projection techniques as perceived by their users. We conducted a controlled user study to test against the following hypotheses: (1) projection performance is task-dependent; (2) certain projections perform better on certain types of tasks; (3) projection performance depends on the nature of the data; and (4) subjects prefer projections with good segregation capability. We generated layouts of high-dimensional data with five techniques representative of different projection approaches. As application domains we investigated image and document data. We identified eight typical tasks, three of them related to segregation capability of the projection, three related to projection precision, and two related to incurred visual cluttering. Answers to questions were compared for correctness against `ground truth' computed directly from the data. We also looked at subject confidence and task completion times. Statistical analysis of the collected data resulted in Hypotheses 1 and 3 being confirmed, Hypothesis 2 being confirmed partially and Hypotheses 4 could not be confirmed. We discuss our findings in comparison with some numerical measures of projection layout quality. Our results offer interesting insight on the use of projection layouts in data visualization tasks and provide a departing point for further systematic investigations.

Internet users are very familiar with the results of a search query displayed as a ranked list of snippets. Each textual snippet shows a content summary of the referred document (or webpage) and a link to it. This display has many advantages, for example, it affords easy navigation and is straightforward to interpret. Nonetheless, any user of search engines could possibly report some experience of disappointment with this metaphor. Indeed, it has limitations in particular situations, as it fails to provide an overview of the document collection retrieved. Moreover, depending on the nature of the query--for example, it may be too general, or ambiguous, or ill expressed--the desired information may be poorly ranked, or results may contemplate varied topics. Several search tasks would be easier if users were shown an overview of the returned documents, organized so as to reflect how related they are, content wise. We propose a visualization technique to display the results of web queries aimed at overcoming such limitations. It combines the neighborhood preservation capability of multidimensional projections with the familiar snippet-based representation by employing a multidimensional projection to derive two-dimensional layouts of the query search results that preserve text similarity relations, or neighborhoods. Similarity is computed by applying the cosine similarity over a "bag-of-words" vector representation of collection built from the snippets. If the snippets are displayed directly according to the derived layout, they will overlap considerably, producing a poor visualization. We overcome this problem by defining an energy functional that considers both the overlapping among snippets and the preservation of the neighborhood structure as given in the projected layout. Minimizing this energy functional provides a neighborhood preserving two-dimensional arrangement of the textual snippets with minimum overlap. The resulting visualization conveys both a global view of the query results and visual groupings that reflect related results, as illustrated in several examples shown.

The influence of a particular individual in a scientific collaboration network could be measured in several ways. Estimating influence commonly requires calculating computationally costly global measures, which may be impractical on networks with hundreds of thousands of vertices. In this paper, we introduce new local measures to estimate the collaborative influence of individual researchers in a collaboration network. Our approach is based on the link prediction technique, and its underlying rationale is to assess how the presence/absence of a researcher affects the link prediction outcome in the network as a whole. It is natural to assume that the absence of a researcher with strong influence in the network will cause negative impact in the correct link prediction. Scientists are represented as vertices in the collaboration graph, and a vertex removal and corresponding link prediction process are performed iteratively for all vertices, each vertex being handled independently. The SVM supervised learning model has been adopted as link predictor. The proposed approach has been tested on real collaboration networks relative to multiple time periods, processing the networks in order to assign more relevance to recent than to older collaborations. The experimental tests suggest that our measure of impact on link prediction has high negative correlation with standard vertex importance measures such as between ness and closeness centrality.

Exploratory tasks supported by visualization are usually improved by Coordinated and Multiple Views (CMV) of the data under study. Several coordination techniques have been proposed in the literature, resulting in a diversity of tools to generate mappings among the multiple views. These mappings can be highly dynamic, and their history reveals the settings employed in the multiple exploratory tasks conducted in a discovery process. Several solutions have been proposed to help users to recover the steps performed in exploratory tasks, but little support is found for registering the multiple coordination mappings employed. This paper provides a contribution in this direction, proposing a model for storing and recovering such mappings. We believe such a facility is an important feature of CMV systems, so that users can recover and rerun the coordinations performed when exploring their data. We present details of the proposed model and show some potential applications.

Abstract Visualization of high‐dimensional data requires a mapping to a visual space. Whenever the goal is to preserve similarity relations a frequent strategy is to use 2D projections, which afford intuitive interactive exploration, e.g., by users locating and selecting groups and gradually drilling down to individual objects. In this paper, we propose a framework for projecting high‐dimensional data to 3D visual spaces, based on a generalization of the Least‐Square Projection (LSP). We compare projections to 2D and 3D visual spaces both quantitatively and through a user study considering certain exploration tasks. The quantitative analysis confirms that 3D projections outperform 2D projections in terms of precision. The user study indicates that certain tasks can be more reliably and confidently answered with 3D projections. Nonetheless, as 3D projections are displayed on 2D screens, interaction is more difficult. Therefore, we incorporate suitable interaction functionalities into a framework that supports 3D transformations, predefined optimal 2D views, coordinated 2D and 3D views, and hierarchical 3D cluster definition and exploration. For visually encoding data clusters in a 3D setup, we employ color coding of projected data points as well as four types of surface renderings. A second user study evaluates the suitability of these visual encodings. Several examples illustrate the framework's applicability for both visual exploration of multidimensional abstract (non‐spatial) data as well as the feature space of multi‐variate spatial data.

Document interpretation is a crucial task in many visual analytics applications, made harder by the widespread availability of freely available textual files. In this paper we propose an approach based on topic detection coupled with multiple coordinated views to assist analysis of time varying document collections. Given multiple document maps built from a set of text files, we define a strategy to support users locating the evolution of topics addressed by the documents, along various time steps. The approach is supported by a new algorithm for topic extraction from texts, also introduced. Finally, we show several examples illustrating how the proposed strategy may be applied in the analysis of document collections.

We introduce the HexBoard space and visualization tool, that provides an incremental visualization space that conveys pairwise similarity among all neighboring elements from a dynamic data set. It is a significant evolution on our previous work, incBoard, a chess board analogy for displaying (projecting) objects from a dynamic set on a 2D space, considering their similarity in a higher dimensional space. HexBoard relays on hexagons to represent data items: the only regular polygons that provide a regular tessellation of the Euclidean plane and where neighboring elements always share an edge. These edges are then easily manipulated to convey pairwise similarity information, thus overcoming a serious limitation of the previous solution, while preserving all advantages of incBoard (no occlusion, coherent disposition of elements, inherently incremental solution and low computational cost). This paper introduces HexBoard, discusses its potential and illustrates its application with examples.

Experimental replications are very important to the advancement of empirical software engineering. Replications are one of the key mechanisms to confirm previous experimental findings. They are also used to transfer experimental knowledge, to train people, and to expand a base of experimental evidence. Unfortunately, experimental replications are difficult endeavors. It is not easy to transfer experimental know-how and experimental findings. Based on our experience, this paper discusses this problem and proposes a Framework for Improving the Replication of Experiments (FIRE). The FIRE addresses knowledge sharing issues both at the intra-group (internal replications) and inter-group (external replications) levels. It encourages coordination of replications in order to facilitate knowledge transfer for lower cost, higher quality replications and more generalizable results.

Time series analysis poses many challenges to professionals in a wide range of domains. Several visualization solutions have been proposed for exploratory tasks on time series collections. For large data sets, however, current techniques fail to provide a global view that supports a good association between groups of similar time series. We employ fast multidimensional projection techniques to create concise visual representations of a collection of time series. The whole collection can be viewed in a two-dimensional graph-based representation that provides a starting point for further exploration and detailed analysis. The projections employ distance metrics to compare the series and generate a layout that attempts to group those with similar behavior. We illustrate the approach on a real data set containing streamflows describing the behavior of hydroelectric power plants in Brazil.

Multiple Views have been put forward as an alternative to assist exploration of evolving phenomena or associations between distinct data sets or distinct presentations of a single data set. Coordinating between views is a challenge that must be met to improve visualization support for exploratory tasks. This is particularly true for high-dimensional data, such as document collections. We introduce a coordination framework for multiple views of document collections created using projections and point placement visualizations. Coordination can occur between different views of a single data set or between views of multiple data sets. Multiple coordinations are also admitted. Three new types of coordination are presented to illustrate the framework; these have been implemented in a multipurpose multi-dimensional visualization system called PEx (Projection Explorer).

Extracting association rules from large datasets typically results in a huge amount of rules. An approach to tackle this problem is to filter the resulting rule set, which reduces the rules, at the cost of also eliminating potentially interesting ones. In exploring a new dataset in search of relevant associations, it may be more useful for miners to have an overview of the space of rules obtainable from the dataset, rather than getting an arbitrary set satisfying high values for given interest measures. We describe a rule extraction approach that favors rule diversity, allowing miners to gain an overview of the rule space while reducing semantic redundancy within the rule set. This approach adopts an itemset-driven rule generation coupled with a cluster-based filtering process. The set of rules so obtained provides a starting point for a user-driven exploration of it.

Researchers and users are well aware of the difficulties related to finding an appropriate configuration of the axes mapping attributes in multidimensional visualization techniques, particularly in visualizations that show a large number of attributes simultaneously. We address this problem with a simple strategy that offers both dimension ordering and dimension reduction. Dimension ordering is based on attribute similarity heuristics, and the basic rationale is extended to support dimension reduction. We discuss the performance of our algorithms and present some results of their application to several data sets. The algorithms improve the capability of visualization techniques to segregate clusters present in the data and reduce the visual clutter aggravated by arbitrary distributions of the axes

A map of multi-dimensional data is a graphical representation - defined in 2D or 3D space - of a set of data points that reflects similarity relationships amongst them. Triangulations of those points can be produced to generate surface meshes on which additional information can be mapped to visual attributes such as color or height. Such surfaces may then be used to explore the data set and the similarities between the different data points. In this paper we introduce Voromap, an exploration tool that is based on Voronoi diagrams of the projected data, and compare that representation with a standard representation that uses triangulations. Voronoi diagrams represent each element in the data set by the area of a polygon in which every point within the polygon is closer to its generating point than to any other point from the data set. A user experiment was conducted to compare Voronoi maps with equivalent maps represented by surface triangulations explored with a similar triangulation-based tool.

This paper presents an analytical taxonomy that can suitably describe, rather than simply classify, techniques for data presentation. Unlike previous works, we do not consider particular aspects of visualization techniques, but their mechanisms and foundational vision perception. Instead of just adjusting visualization research to a classification system, our aim is to better understand its process. For doing so, we depart from elementary concepts to reach a model that can describe how visualization techniques work and how they convey meaning

Despite the significant evolution of techniques for 3D-reconstruction from planar cross sections, establishing the correspondence of regions in adjacent slices remains an important issue. In this article, we propose a novel approach for solving the correspondence problem in a flexible manner. We show that from the 3D Delaunay triangulation, it is possible to derive a distance measure among regions lying in adjacent slices. Such distance is used to define a positive integer parameter, called β, responsible for establishing the connections. Varying β thus allows the construction of different models from a given set of cross-sectional regions: small values of β causes closer regions to be connected into a single component, and as β increases, more distant regions are connected together. The algorithm, named β-connection, is described, and examples are provided that illustrate its applicability in solid modeling and model reconstruction from real data. The underlying reconstruction method is effective, which jointly with the β-connection correspondence strategy, improve the usability of volumetric reconstruction techniques considerably.

We survey work on the different uses of graphical mapping and interaction techniques for visual data mining of large data sets represented as table data. Basic terminology related to data mining, data sets, and visualization is introduced. Previous work on information visualization is reviewed in light of different categorizations of techniques and systems. The role of interaction techniques is discussed, in addition to work addressing the question of selecting and evaluating visualization techniques. We review some representative work on the use of information visualization techniques in the context of mining data. This includes both visual data exploration and visually expressing the outcome of specific mining algorithms. We also review recent innovative approaches that attempt to integrate visualization into the DM/KDD process, using it to enhance user interaction and comprehension.

This paper presents a novel algorithm for volumetric reconstruction of objects from planar sections using Delaunay triangulation, which solves the main problems posed to models defined by reconstruction, particularly from the viewpoint of producing meshes that are suitable for interaction and simulation tasks. The requirements for these applications are discussed here and the results of the method are presented. Additionally, it is compared to another commonly used reconstruction algorithm based on Delaunay triangulation, showing the advantages of the reconstructions obtained by our technique.

This paper presents a formal definition for HMBS (Hypermedia Model Based on Statecharts). HMBS uses the structure and execution semantics of statecharts to specify both the structural organization and the browsing semantics of hypermedia applications. Statecharts are an extension of finite-state machines and the model is thus a generalization of hypergraph-based hypertext models. Some of the most important features of HMBS are its ability to model hierarchy and synchronization of information; provision of mechanisms for specifying access structures, navigational contexts, access control, multiple tailored versions,and hierarchical views. Analysis of the underlying statechart machine allows verification of page reachability, valid paths, and other properties, thus providing mechanisms to support authors in the development of structured applications.

Introduces hypercharts, a novel and effective notation that extends the well-known statechart formalism to make it suitable for the specification of temporal and information synchronization requirements of hypermedia applications. Three new definitions are added: timed history, timed transitions, and a set of synchronization mechanisms. The proposed extensions are based on the major characteristics of some Petri net-based multimedia models, and have their semantics described in terms of conventional statechart models. Therefore, any hyperchart construction can be transformed into a statechart that exhibits the desired behavior, giving hyperchart models the same semantic behavior as statecharts. The new constructs are illustrated using a case study based on a hypermedia-modeling example.

This paper introduces hypercharts, a novel and effective model that extends the well-known statechart formalism to make it suitable for the specification of the temporal and information synchronization requirements of hypermedia applications. Three new definitions are added: timed history, timed transitions and a set of synchronization mechanisms. The proposed extensions are based on the major characteristics of some Petri net based multimedia models, and have their semantics described in the paper in terms of conventional statechart models.