Large Amounts Of Text Research Articles

Retraction: Prospects and applications of nanobiotechnology: a medical perspective

This article [1] is retracted as it contains large amount of text that has been duplicated from other articles previously published. We apologize to all affected parties for the inconvenience caused.

Reading <i>Orlando</i> with the Mandala Browser: A Case Study in Algorithmic Criticism via Experimental Visualization

This paper describes the preliminary results of combining two complementary technologies: Orlando, a semantically-tagged XML collection of born-digital scholarly resources, and the Mandala Browser, an XML visualization tool. Orlando's current delivery system privileges text as an approach to literary historical scholarship. The Mandala browser represents a radically different way of mediating between the user and the text, translating a text or set of texts into a circular visual form and pushing the user towards a more distant, or at least a more selective, reading of the materials than that associated with conventional print or screen rendering. Through experimental visualizations of Orlando content, we began to address questions concerning the participation of Victorian and Renaissance writers in various genres, the relationship between reproduction and literary production, the connection of censorship to the destruction of literary works, and the relationship between suffrage and liberal or conservative political groups. We argue that, just as a postcolonialist or a new historicist needs to learn about the tenets and processes involved in a postcolonial or new historical critical framework, so too an algorithmic critic should expect to invest some time learning the techniques of a given approach and how to apply them to a particular text or body of texts. These investigations may interest other humanities scholars working with online digital collections, as well as those thinking through the question of how to involve computational processes in complex inquiries using large quantities of texts.

Incoming Dental Students’ Expectations and Acceptance of an Electronic Textbook Program

Since 2005, the Louisiana State University Health Sciences Center School of Dentistry has required the VitalSource Technologies, Inc. Bookshelf as the textbook program for all dental students. In a 2008 survey, four classes of dental students expressed dissatisfaction with most features of the bookshelf. With the expectation that incoming students would be more accustomed and amenable to digital textbooks and to further determine student attitudes toward electronic textbooks, we developed two surveys for first-year dental students in the class of 2013. The sixty-five first-year students received a survey (S1) one week before they were introduced to the e-textbook program. Questions centered on their undergraduate experience with e-books and their expectations of studying with an electronic textbook collection. In the second survey (S2), sent nine months later, the questions focused on students' opinion of the VitalSource Bookshelf. Forty-five students (69.2 percent) completed the S1 survey. Of those, thirty-six (80 percent) responded that they never used e-textbooks in college. Of the nine students who responded that they used e-books, only two liked them without reservations. The response rate to S2 increased to fifty students (77 percent). After using VitalSource for nine months, thirty-three students (66 percent) indicated a preference for reading print textbooks, compared to forty-seven students (57.3 percent) of the four classes surveyed in 2008. Although we expected incoming dental students to have had previous experience with e-textbooks, only nine students had used e-books in college courses. Few students indicated preference for e-textbooks, and over half of the group was undecided. After experience with VitalSource for first-year courses, students indicated that they like VitalSource for the ability to search for specific topics across the entire collection of dental books, but not for reading large amounts of text.

Opinion mining from noisy text data

The proliferation of Internet has not only led to the generation of huge volumes of unstructured information in the form of web documents, but a large amount of text is also generated in the form of emails, blogs, and feedbacks, etc. The data generated from online communication acts as potential gold mines for discovering knowledge, particularly for market researchers. Text analytics has matured and is being successfully employed to mine important information from unstructured text documents. The chief bottleneck for designing text mining systems for handling blogs arise from the fact that online communication text data are often noisy. These texts are informally written. They suffer from spelling mistakes, grammatical errors, improper punctuation and irrational capitalization. This paper focuses on opinion extraction from noisy text data. It is aimed at extracting and consolidating opinions of customers from blogs and feedbacks, at multiple levels of granularity. We have proposed a framework in which these texts are first cleaned using domain knowledge and then subjected to mining. Ours is a semi-automated approach, in which the system aids in the process of knowledge assimilation for knowledge-base building and also performs the analytics. Domain experts ratify the knowledge base and also provide training samples for the system to automatically gather more instances for ratification. The system identifies opinion expressions as phrases containing opinion words, opinionated features and also opinion modifiers. These expressions are categorized as positive or negative with membership values varying from zero to one. Opinion expressions are identified and categorized using localized linguistic techniques. Opinions can be aggregated at any desired level of specificity i.e. feature level or product level, user level or site level, etc. We have developed a system based on this approach, which provides the user with a platform to analyze opinion expressions crawled from a set of pre-defined blogs.

MeSH Up: effective MeSH text classification for improved document retrieval

Motivation: Controlled vocabularies such as the Medical Subject Headings (MeSH) thesaurus and the Gene Ontology (GO) provide an efficient way of accessing and organizing biomedical information by reducing the ambiguity inherent to free-text data. Different methods of automating the assignment of MeSH concepts have been proposed to replace manual annotation, but they are either limited to a small subset of MeSH or have only been compared with a limited number of other systems.Results: We compare the performance of six MeSH classification systems [MetaMap, EAGL, a language and a vector space model-based approach, a K-Nearest Neighbor (KNN) approach and MTI] in terms of reproducing and complementing manual MeSH annotations. A KNN system clearly outperforms the other published approaches and scales well with large amounts of text using the full MeSH thesaurus. Our measurements demonstrate to what extent manual MeSH annotations can be reproduced and how they can be complemented by automatic annotations. We also show that a statistically significant improvement can be obtained in information retrieval (IR) when the text of a user's query is automatically annotated with MeSH concepts, compared to using the original textual query alone.Conclusions: The annotation of biomedical texts using controlled vocabularies such as MeSH can be automated to improve text-only IR. Furthermore, the automatic MeSH annotation system we propose is highly scalable and it generates improvements in IR comparable with those observed for manual annotations.Contact: trieschn@ewi.utwente.nlSupplementary information: Supplementary data are available at Bioinformatics online.

Split-Second Recognition: What Makes Outdoor Advertising Work?

<h3>ABSTRACT</h3> CBS Outdoor used a tachistoscope to determine how long it takes to recognize the brand/product advertised in 187 outdoor posters in the Netherlands. Additionally, CBS Outdoor measured the creative appeal of these advertisements. Using 80 content and format variables, an explanatory model was developed to measure creative appeal and brand/product recognition. Some preliminary findings: Clear branding and the inclusion of new-product information enhance product recognition. Large amounts of text and pictures of people delay product recognition. Lengthy, large headlines, information cues, humor, and images of women delay brand recognition. Short headlines, a somewhat longer body text, and a product shot enhance the creative appeal of posters. Specifying a brand name in the headline or providing price information reduces appeal.

A Hybrid Semantic Similarity Measure for Spatial Information Retrieval

Semantic similarity is central to many cognitive processes and plays an important role in the way humans process and reason about information. In particular, the retrieval of knowledge from memory hinges crucially on similarity. Likewise, information retrieval systems use similarity to detect relevant information for a given query. Current information retrieval systems apply mainly syntactic techniques to determine similarity. Although such syntactic similarity measures have performed strongly with resources containing large amounts of text, they cannot appropriately cope with syntactic and semantic heterogeneity and ambiguity, if the semantics of the terms is not explicitly available. Therefore, they are rather rigid and inflexible as they cannot adapt to the user's requirements and conceptualization of the domain. Furthermore, geographic features are distinguished via their geometric and thematic data. It is often not possible to capture the complex semantics of geographic features by a single name or a textual description. Therefore spatial data is different from text documents typically found in enterprise databases or on the Web. Retrieval of spatial information requires new, intelligent retrieval mechanisms that satisfy its specific requirements. A semantics-based solution can more easily adapt to user needs and therefore increases the flexibility and usability of spatial data and retrieval methods. This paper investigates the suitability of various approaches—originally developed to explain human similarity judgement—in the context of spatial information retrieval. We propose a new, hybrid approach for semantic similarity measurement, which can represent the complex semantics of spatial data. It allows for retrieving relevant data by determining the similarity between the query and the semantic descriptions of geographic feature types within the database. The hybrid similarity measure combines the geometric structure of conceptual spaces with the relational structure of semantic nets to one, cognitively plausible knowledge representation with an inherent similarity measure.

Beyond the Flickering Screen: Re-situating e-books

Beyond the Flickering Screen: Re-situating e-books

Biomedical Ontologies and Text Mining for Biomedicine and Healthcare: A Survey

In this survey paper, we discuss biomedical ontologies and major text mining techniques applied to biomedicine and healthcare. Biomedical ontologies such as UMLS are currently being adopted in text mining approaches because they provide domain knowledge for text mining approaches. In addition, biomedical ontologies enable us to resolve many linguistic problems when text mining approaches handle biomedical literature. As the first example of text mining, document clustering is surveyed. Because a document set is normally multiple-topic, text mining approaches use document clustering as a preprocessing step to group similar documents. Additionally, document clustering is able to inform the biomedical literature searches required for the practice of evidence-based medicine. We introduce Swanson's UnDiscovered Public Knowledge (UDPK) model to generate biomedical hypotheses from biomedical literature such as MEDLINE by discovering novel connections among logically-related biomedical concepts. Another important area of text mining is document classification. Document classification is a valuable tool for biomedical tasks that involve large amounts of text. We survey well-known classification techniques in biomedicine. As the last example of text mining in biomedicine and healthcare, we survey information extraction. Information extraction is the process of scanning text for information relevant to some interest, including extracting entities, relations, and events. We also address techniques and issues of evaluating text mining applications in biomedicine and healthcare.

Modern methods of speech synthesis

We have examined various aspects of how to produce synthetic speech. There are numerous applications for such synthetic speech, mostly when starting from a textual input, i.e., TTS. Given the large amount of text in databases and the public's need to access information efficiently, synthetic speech is a natural way to obtain information. A major application of the future will be speech-to-speech translation, in which a person speaking in one language will be able to converse automatically with someone using another language: ASR would transcribe the original speech to a textual form in language A, then an automatic text translator would map that text to language B, and finally a TTS system for this second language would generate the output speech.

Spécificités morpho-syntaxiques des constructions à verbe support en allemand

In this article, we give evidence for a detailed morpho-syntactic description of support verb constructions (SVCs); we claim that SVCs must be described at the same level of detail as single word items. We give examples from French and German, concerning both, morphosyntactic specificities of the nominal and of the verbal element of a SVC. Furthermore we show that methods of corpus analysis are well suited or the extraction of such data form large amounts of text; the corpus-based aproach is all the more necessary, as most morphosyntactic phenomena within SVCs are preferences rather than categorical features. We describe a range of extraction methods, and we argue for a robust syntactic analysis as a basis for extraction. The article ends with a small case study on preferences of German support verbs with respect to active vs. passive.

Distinguishing the Trees from the Forest: Applying Cluster Analysis to Thematic Qualitative Data

Qualitative data analysis requires organizing and synthesizing often large quantities of text. In many cases, this analysis entails negotiating the interplay between raw data, semantic themes or codes, and the overarching conceptual framework. In this article, the authors use a case study, which examines HIV vaccine efficacy trial participants' discourse, to demonstrate how cluster analysis can be used to aid in the analysis of large qualitative data sets. After briefly reviewing the systematic approaches to qualitative analysis and describing the project background, the authors present an example of how a hierarchical cluster technique can be incorporated into a multistage thematic analysis.

The potential of latent semantic analysis for machine grading of clinical case summaries

Objective: This paper introduces latent semantic analysis (LSA), a machine learning method for representing the meaning of words, sentences, and texts. LSA induces a high-dimensional semantic space from reading a very large amount of texts. The meaning of words and texts can be represented as vectors in this space and hence can be compared automatically and objectively. Psychological theory: A generative theory of the mental lexicon based on LSA is described. The word vectors LSA constructs are context free, and each word, irrespective of how many meanings or senses it has, is represented by a single vector. However, when a word is used in different contexts, context appropriate word senses emerge. Current applications: Several applications of LSA to educational software are described, involving the ability of LSA to quickly compare the content of texts, such as an essay written by a student and a target essay. Potential medical applications: An LSA-based software tool is sketched for machine grading of clinical case summaries written by medical students.

The Heinz Electronic Library Interactive Online System (HELIOS): Building a Digital Archive Using Imaging, OCR, and Natural Language Processing Technologies.

In February 1994, Carnegie Mellon University (CMU) embarked on an ambitious project to convert one million pages of the congressional papers of Senator John Heinz (R-PA) into digital format and to provide access to these papers through innovative information retrieval software developed at CMU. Named in memory of the late Senator, the Heinz Electronic Library Interactive Online System (HELIOS) supports full-page digital images and it utilizes natural language processing (NLP) technology to search large quantities of unstructured text. HELIOS will allow researchers to access the Heinz papers through the campus network as well as through the Internet. Over one million dollars was donated by the Heinz Family Foundation, Heinz Company Foundation, and Heinz Endowments to support the establishment of the H. John Heinz III Archives and the digitization project. Heinz assistance has made it possible to advance the principles of digital preservation and access for archival collections. In addition to the Heinz gift, CMU has committed an additional $450,000 in matching resources to the project. These resources primarily come in the form of permanent full-time staff salaries, archival equipment, and rental of a processing facility. Our goal is to develop a digital archive that will serve as a model for the archival profession. We expect to create an archival information technology environment that dramatically increases the depth of indexing and the quality of retrieval beyond what archiving resources have traditionally allowed. To create the HELIOS database, documents are scanned, converted to ASCII form via OCR, verified and organized, and indexed using the CLARIT natural language processing software. The project will develop three graphical user interfaces in a Microsoft Windows environment: a scanning interface, an archivist/verification interface, and an end-user interface. HELIOS represents a significant breakthrough technology that has the potential to transform the work of archivists by helping them to overcome the significant challenges they face, including an inability to: 1. create good finding aids and indexes for paper archives that provide deep access to collections, 2. provide effective retrieval from paper archives due to the inherent diversity and size of these one-of-a-kind files, and 3. offer broad public access to archives because they represent resources that the researcher must visit in order to use effectively. Archivists have resisted the use of information technology because they lack appropriate tools to automatically process large amounts of text for retrieval. HELIOS will offer such a tool. Clearly, there are many problems yet to be solved in the management and preservation of digital archives, but it is CMU's intention to work with the larger archival and library community to help establish standard practices for digitizing paper archives and to develop the information management tools to give scholars and students state-of-the-art access to them.

The National Library in an Electronic Age: Dinosaur or Catalyst?

A key factor relating to the future of some national libraries is the future of the nation state itself. As some nations break up, we must expect some existing national libraries to face the prospect of fragmentation. All national libraries will have to be increasingly aware of the need to reflect the full range of cultures within their countries if they are to survive as nationally acceptable institutions. A second key factor is economic growth, which leads to more literate people, more publications to be collected, more libraries of other kinds, and the production of an increasing amount of public information. Continued economic growth depends on access to knowledge, but priorities need to be assessed. Recent technological developments are changing the basic nature of libraries, including national libraries. Three crucial current developments are the economic storage in electronic form of large amounts of text and images; national and global communication networks; and desktop publishing. Faced with these trends, national libraries, if they are to be successful over the longer term, must develop as agents of national identity and culture, as well as of national economic advance.

Optical character scanning: A discussion of efficiency and politics

Optical Character Recognition is shown to be significantly more expensive than keyboarding, using off-shore contractors, for entry of large amounts of text where high accuracy is required. Using large test samples in French and English, the paper indicates that OCR applications which require significant post-scan editing are labor intensive projects that can be accomplished more efficiently by keyboarding. Most OCR systems are still not capable of entering large amounts of text accurately enough to avoid an expensive editing step.

Computers in pathology - an analysis of text retrieval in laboratory operations and research

Many computer systems currently available in major hospitals rely on standard database design with emphasis on the relation of database which is able to store a wide variety of data types. Such a database is most efficient when dealing with numerical data for text field data and although many of these databases allow free text fields for software does not usually allow complex subject orientated analysis of the data contained in the free text entries. Over the last few years a number of text retrieval systems have become available and some of these show particular promise for use in pathology laboratories, particularly those relying on text based pathology reports (anatomical and forensic pathology). Other departments could also deal with a large quantity of text based data may also have a need for this type of software. The use of Topic based text retrieval which allows users to develop their own expert interpretation of text will be discussed together with the impact such a system has on the design of computer systems within pathology.

Effectiveness and efficiency in natural language processing for large amounts of text

An efficient and effective system for natural language processing (NLP) was developed for improving free text analysis. The main linguistic ideas and the global system architecture are described. For improving effectiveness while keeping efficiency high we made use of principled techniques from empirical linguistics. This means that all rules are evaluated and the rule system is kept as small as possible. The approach is exemplified by the analysis of conjunctions

Marcon plus: Text retrieval sofware a review

MARCON is an exceptionally full featured information retrieval system, well suited to the construction of online research catalogs, and databases containing large quantities of text. It is less well suited to structured database applications, especially those requiring substantial printed reporting, for which it will be found wanting.

Forensic linguistics: the determination of authorship from habits of style

The application of a method of literary stylistics (or stylo-metry) to forensic problems such as the authentication of disputed witness statements is described. Relatively large amounts of text are required for both specimen and questioned material before an effective comparison can be attempted and this severely restricts the number of cases in which the method may be applied. The validity of the method as applied to materials of forensic interest is considered to be as yet unproven but such methods are certainly worthy of further study.