Toward Interactive Visualization of Results from Domain-Specific Text Analytics

PurposeText mining has been used for various knowledge discovery based applications, and thus, a lot of research has been contributed towards it. Latest trending research in the text mining is adopting the incremental learning data, as it is economical while dealing with large volume of information.Design/methodology/approachThe primary intention of this research is to design and develop a technique for incremental text categorization using optimized Support Vector Neural Network (SVNN). The proposed technique involves four major steps, such as pre-processing, feature selection, classification and feature extraction. Initially, the data is pre-processed based on stop word removal and stemming. Then, the feature extraction is done by extracting semantic word-based features and Term Frequency and Inverse Document Frequency (TF-IDF). From the extracted features, the important features are selected using Bhattacharya distance measure and the features are subjected as the input to the proposed classifier. The proposed classifier performs incremental learning using SVNN, wherein the weights are bounded in a limit using rough set theory. Moreover, for the optimal selection of weights in SVNN, Moth Search (MS) algorithm is used. Thus, the proposed classifier, named Rough set MS-SVNN, performs the text categorization for the incremental data, given as the input.FindingsFor the experimentation, the 20 News group dataset, and the Reuters dataset are used. Simulation results indicate that the proposed Rough set based MS-SVNN has achieved 0.7743, 0.7774 and 0.7745 for the precision, recall and F-measure, respectively.Originality/valueIn this paper, an online incremental learner is developed for the text categorization. The text categorization is done by developing the Rough set MS-SVNN classifier, which classifies the incoming texts based on the boundary condition evaluated by the Rough set theory, and the optimal weights from the MS. The proposed online text categorization scheme has the basic steps, like pre-processing, feature extraction, feature selection and classification. The pre-processing is carried out to identify the unique words from the dataset, and the features like semantic word-based features and TF-IDF are obtained from the keyword set. Feature selection is done by setting a minimum Bhattacharya distance measure, and the selected features are provided to the proposed Rough set MS-SVNN for the classification.

In this study, define the concept of spatial big data and special feature of spatial big data, examine information visualization methodology for increase the insight into the data. Also presented problems and solutions in the visualization process. Spatial big data is defined as a result of quantitative expansion from spatial information and qualitative expansion from big data. Characteristics of spatial big data id defined as 6V (Volume, Variety, Velocity, Value, Veracity, Visualization), As the utilization and service aspects of spatial big data at issue, visualization of spatial big data has received attention for provide insight into the spatial big data to improve the data value. Methods of information visualization is organized in a variety of ways through Matthias, Ben, information design textbook, etc, but visualization of the spatial big data will go through the process of organizing data in the target because of the vast amounts of raw data, need to extract information from data for want delivered to user. The extracted information is used efficient visual representation of the characteristic, The large amounts of data representing visually can not provide accurate information to user, need to data reduction methods such as filtering, sampling, data binning, clustering.

The analysis of the text content in emails, blogs, tweets, forums and other forms of textual communication constitutes what we call text analytics. Text analytics is applicable to most industries: it can help analyze millions of emails; you can analyze customers’ comments and questions in forums; you can perform sentiment analysis using text analytics by measuring positive or negative perceptions of a company, brand, or product. Text Analytics has also been called text mining, and is a subcategory of the Natural Language Processing (NLP) field, which is one of the founding branches of Artificial Intelligence, back in the 1950s, when an interest in understanding text originally developed. Currently Text Analytics is often considered as the next step in Big Data analysis. Text Analytics has a number of subdivisions: Information Extraction, Named Entity Recognition, Semantic Web annotated domain’s representation, and many more. Several techniques are currently used and some of them have gained a lot of attention, such as Machine Learning, to show a semisupervised enhancement of systems, but they also present a number of limitations which make them not always the only or the best choice. We conclude with current and near future applications of Text Analytics.

In our digital environment, there are both opportunities and challenges associated with the unprecedented growth of data. We will discuss the two areas of investigation (Big Data Analytics and Data Visualization), which are seldom related fields, and both are essential to achieving insights from Big Data. We will discuss the fundamental traits of Big Data, including volume, velocity, and variety, and how data is transitioned from its initial state to data from analytics. We will then discuss the key component that Data Visualization represents as a cognitive tool to make the complex nature of analytics intuitive, readable, and actionable. This presentation will argue for the complementary nature of the two fields, further supporting the notion that this is not optional, but mandatory, given the nature of Big Data Analytics in relation to science, commerce, and government. We will focus on the potential of the lifecycle of data, from collection to visualization, data use, embedded analytics, and the ethical conceptualization of challenges, as well as a future forecast of system technology that will impact the reestablishment of our knowledge and knowledge practices

Text categorization is a text mining process and it aims to discover relevant information and relationship in a huge amounts of text data. Feature extraction is an important preprocessing step of text categorization, as extracted features are used to represent texts. Several methods, feature models, and algorithms are needed to extract useful features from textual contents. One of the these methods is frequent itemset mining which is a basic data mining technique that employed to find interesting patterns in data. As the frequent itemsets (termsets) reflect strong associations between items they provide more underlying contextual semantic than an individual word. Therefore, it is used in text mining domain for different purposes (e.g., frequent itemset based text clustering). In this paper, we employ termsets for text representation, and use both binary and cardinality based approaches for termset weighting. Unlike existing studies, we use character level n-grams to represent items in a transaction in addition to the traditional bag of words model. Through our experimental results on Mod-Apte split of the Reuters-21578 dataset, we determined that performing document-transaction conversion at level of character n-grams improves the performance of the Support Vector Machine classifier.

We are living in an age where everything is getting recorded digitally, thanks to the rise of the Internet and Social Media. Exabytes of data are getting generated frequently which needs to be explored, cleansed and analysed to make them usable. Big data is a term that represents a huge volume of structured, semi-structured, or unstructured data. Translating information into meaningful visual context such as graphs, maps or charts to make data easier as well as pulling insights are called Data visualization. It also introduces numerous possibilities for solving the big data problem by creative ideation through visual means. Lots of challenges as well as problems are associated with big data analysis due to its complex characteristics. In this article, we'll discuss about the reasons of big data visualization being necessary, as well as some big data visualization tools. We will also summarize different types of challenges in visualization methods as well as suggest possible way forward for complications pertaining to the visualization of Big Data. In addition, the working procedure, characteristics, and drawbacks of several tools and techniques for big data visualization are examined in our research.

Named Entity Recognition (NER) is an important step in text mining. This paper proposes a survey on extracting named entities from new domains using big data analytics. The survey shows the methods and challenges applied for the efficient extraction of named entities from various fields having large corpus of data such as banking, medical and social networks. Most of NER methods discussed below are normally based on supervised learning techniques which often require a large amount of training dataset to train a good classifier. However, many applications in Information Retrieval (IR) and Natural Language Processing (NLP) suffer high from the noisy and short nature of texts.

Visualization of big data is crucial for meaningful interpretations and especially for healthcare. Brief discussions are made for big data, background for healthcare, and recent work in big data analytics for healthcare. This research pertains to different levels of big data: 5,110 vs. 101,766 vs. 320,200 vs. 1 million data values. Data visualizations and predictive analytics are presented of big data for selected diseases of stroke with 5,110 data values, diabetes with 101,766 data values, and two COVID-19 studies: one with 320,200 data values and another with 1 million data values. Data visualizations are generated for these diseases with big data using Tableau. For stroke patients, an investigation was performed to determine how different living environments affect relationship between strokes. The data visualizations for diabetes showed impact of insulin use yielded reduced hospital stays. Data visualizations for COVID-19 provided temporal trends in confirmed cases, mortality, and recovery rates for 2020-2023. Conclusions and future directions of research are presented.

Big Data, which contains image, video, text, audio and other forms of data, collected from multiple datasets, is difficult to process using traditional database management tools or applications. In this paper, we establish the 5Ws model by using 5Ws data dimension for Big Data analysis and visualization. 5Ws data dimension stands for, What the data content is, Why the data occurred, Where the data came from, When the data occurred, Who received the data and How the data was transferred. This framework not only classifies Big Data attributes and patterns, but also establishes density patterns that provide more analytical features. We use visual clustering to display data sending and receiving densities which demonstrate Big Data patterns. The model is tested by using the network security ISCX2012 dataset. The experiment shows that this new model with clustered visualization can be efficiently used for Big Data analysis and visualization.

Text mining is increasingly used to manage the accelerating pace of the biomedical literature. Many text mining applications depend on accurate named entity recognition (NER) and normalization (grounding). While high performing machine learning methods trainable for many entity types exist for NER, normalization methods are usually specialized to a single entity type. NER and normalization systems are also typically used in a serial pipeline, causing cascading errors and limiting the ability of the NER system to directly exploit the lexical information provided by the normalization. We propose the first machine learning model for joint NER and normalization during both training and prediction. The model is trainable for arbitrary entity types and consists of a semi-Markov structured linear classifier, with a rich feature approach for NER and supervised semantic indexing for normalization. We also introduce TaggerOne, a Java implementation of our model as a general toolkit for joint NER and normalization. TaggerOne is not specific to any entity type, requiring only annotated training data and a corresponding lexicon, and has been optimized for high throughput. We validated TaggerOne with multiple gold-standard corpora containing both mention- and concept-level annotations. Benchmarking results show that TaggerOne achieves high performance on diseases (NCBI Disease corpus, NER f-score: 0.829, normalization f-score: 0.807) and chemicals (BioCreative 5 CDR corpus, NER f-score: 0.914, normalization f-score 0.895). These results compare favorably to the previous state of the art, notwithstanding the greater flexibility of the model. We conclude that jointly modeling NER and normalization greatly improves performance. The TaggerOne source code and an online demonstration are available at: http://www.ncbi.nlm.nih.gov/bionlp/taggerone zhiyong.lu@nih.gov Supplementary data are available at Bioinformatics online.

In this paper we deal with the main aspect of the problem of extracting meaning from documents, namely, with the problem of text categorization, outlining a novel and systematic approach to its solution. We present a text categorization system for non-domain specific full-text documents. The main contribution of this paper lies on the feature extraction methodology which, first, involves word semantic categories and not raw words as other rival approaches. As a consequence of coping with the problem of dimensionality reduction, the proposed approach introduces a novel second and third order feature extraction approach for text categorization by considering word semantic categories cooccurrence analysis. The suggested methodology compares favorably to widely accepted, raw word frequency based techniques in a collection of documents concerning the Dewey Decimal Classification (DDC) system. In these comparisons different Multilayer Perceptrons (MLP) algorithms, the LVQ and the conventional k-NN technique are involved.

Investigation on big data evaluation and visualization of internet of things based on edge computing

Public health researchers increasingly recognize that to advance their field they must grapple with the availability of increasingly large (i.e., thousands of variables) traditional population-level datasets (e.g., electronic medical records), while at the same time integrating additional large datasets (e.g., data on genomics, the microbiome, environmental exposures, socioeconomic factors, and health behaviors). Leveraging these multiple forms of data might well provide unique and unexpected discoveries about the determinants of health and wellbeing. However, we are in the very early stages of advancing the techniques required to understand and analyze big population-level data for public health research. To address this problem, this paper describes how we propose that big data can be efficiently used for public health discoveries. We show that data analytics techniques traditionally employed in public health studies are not up to the task of the data we now have in hand. Instead we present techniques adapted from big data visualization and analytics approaches used in other domains that can be used to answer important public health questions utilizing these existing and new datasets. Our findings are based on an exploratory big data case study carried out in San Diego County, California where we analyzed thousands of variables related to health to gain interesting insights on the determinants of several health outcomes, including life expectancy and anxiety disorders. These findings provide a promising early indication that public health research will benefit from the larger set of activities in contemporary big data research.

A rich source of information relevant to smart cities and health care comes from sensors embedded in the environment, or ambient sensors. Strategically responding to sensed data helps healthcare would be smarter. By gaining real time access to this information, city services can respond promptly to urgent health needs and make decisions to avoid unhealthy situations. The emergence of virtual reality and ICT assisted urban planning effectively overcomes these complexities through visualization of big data. Web-based visualization technologies such as virtual reality (VR) present a highly detailed dynamic virtual environment. Also, there is continuously increasing demand for the effective organization of this diversified data, linkage with other data, and the visualization of data. In recent years, there has been a rapid increase in the development of health information systems motivated by legislation intended to protect patients’ information and privacy and government interest in reducing the cost and improving the quality of healthcare. In this paper, we investigate types of physiological content and the related sensors that can be included in a smart city healthcare system. We present a technical healthcare information model with XML in a standardized format for the implementation of a 3D virtual smart city as follows: Firstly, 3D virtual environment and healthcare information systems were confirmed to be dictated by sensor information parameters via XML. Secondly, real-time location, direction, and health data representation for 3D health management sensor data monitoring and real-time monitoring were conducted in XML. The identified key use case physiological sensor-based XML is helpful as it provides a standardized format for the implementation of a 3D virtual smart city. For implementation, X3D was used for visualizing an example health information system.

The articles in this special section focus on analytic rendering and hardware-accelerated simulation for scientific applications. Data visualization is now one of the cornerstones of data science, turning the abundance of big data being produced through modern systems into actionable knowledge. Data visualization in the big data era raises the need to co-design and more closely align the underlying data management systems with the user-oriented techniques that state-of-the-art visualization systems now offer. In addition, the tight integration of suitable machine learning approaches with data visualization and their control by users-in-theloop promises to enhance scalability, effectiveness, and adaptivity of the interactive visual data analysis process. This special issue attracted and publishes research work on multidisciplinary research areas from the human–computer interaction, computer graphics, and data management communities.