Decision boundary setting and classifier combination for text classification

This thesis presents a promising boundary setting method for solving challenging issues in text classification to produce an effective text classifier. A classifier must identify boundary between classes optimally. However, after the features are selected, the boundary is still unclear with regard to mixed positive and negative documents. A classifier combination method to boost effectiveness of the classification model is also presented. The experiments carried out in the study demonstrate that the proposed classifier is promising.

Blogging

Weblogs, or blogs, constitute a form and genre of online publishing that emerged in the mid-1990s as a logical consequence of the confluence of personal and professional home pages and new web publishing technologies. To overcome technological limitations, where news updates had to be manually inserted by editing the underlying HTML code, the early content-management systems in the second half of the 1990s built on server-side database technology to dynamically generate web pages; this enabled more convenient and more frequent content updates. Weblogs utilised such technologies to provide an up-to-date news feed, presenting individual news items in reverse chronological order. Most blogging platforms provide commenting functions that enable readers to respond to and discuss individual blog posts...

Deriving word association networks from text corpora

This article presents and evaluates a model to automatically derive word association networks from text corpora. Two aspects were evaluated: To what degree can corpus-based word association networks (CANs) approximate human word association networks with respect to (1) their ability to quantitatively predict word associations and (2) their structural network characteristics. Word association networks are the basis of the human mental lexicon. However, extracting such networks from human subjects is laborious, time consuming and thus necessarily limited in relation to the breadth of human vocabulary. Automatic derivation of word associations from text corpora would address these limitations. In both evaluations corpus-based processing provided vector representations for words. These representations were then employed to derive CANs using two measures: (1) the well known cosine metric, which is a symmetric measure, and (2) a new asymmetric measure computed from orthogonal vector projections. For both evaluations, the full set of 4068 free association networks (FANs) from the University of South Florida word association norms were used as baseline human data. Two corpus based models were benchmarked for comparison: a latent topic model and latent semantic analysis (LSA). We observed that CANs constructed using the asymmetric measure were slightly less effective than the topic model in quantitatively predicting free associates, and slightly better than LSA. The structural networks analysis revealed that CANs do approximate the FANs to an encouraging degree.

Knowledge unlatched: A global library consortium model for funding open access scholarly books: Full report on the Proof of Concept Pilot 2014

This special issue of Cultural Science Journal is devoted to the report of a groundbreaking experiment in re-coordinating global markets for specialist scholarly books and enabling the knowledge commons: the Knowledge Unlatched proof-of-concept pilot. The pilot took place between January 2012 and September 2014. It involved libraries, publishers, authors, readers and research funders in the process of developing and testing a global library consortium model for supporting Open Access books. The experiment established that authors, librarians, publishers and research funding agencies can work together in powerful new ways to enable open access; that doing so is cost effective; and that a global library consortium model has the potential dramatically to widen access to the knowledge and ideas contained in book-length scholarly works.

Centroid training to achieve effective text classification

Traditional text classification technology based on machine learning and data mining techniques has made a big progress. However, it is still a big problem on how to draw an exact decision boundary between relevant and irrelevant objects in binary classification due to much uncertainty produced in the process of the traditional algorithms. The proposed model CTTC (Centroid Training for Text Classification) aims to build an uncertainty boundary to absorb as many indeterminate objects as possible so as to elevate the certainty of the relevant and irrelevant groups through the centroid clustering and training process. The clustering starts from the two training subsets labelled as relevant or irrelevant respectively to create two principal centroid vectors by which all the training samples are further separated into three groups: POS, NEG and BND, with all the indeterminate objects absorbed into the uncertain decision boundary BND. Two pairs of centroid vectors are proposed to be trained and optimized through the subsequent iterative multi-learning process, all of which are proposed to collaboratively help predict the polarities of the incoming objects thereafter. For the assessment of the proposed model, F1 and Accuracy have been chosen as the key evaluation measures. We stress the F1 measure because it can display the overall performance improvement of the final classifier better than Accuracy. A large number of experiments have been completed using the proposed model on the Reuters Corpus Volume 1 (RCV1) which is important standard dataset in the field. The experiment results show that the proposed model has significantly improved the binary text classification performance in both F1 and Accuracy compared with three other influential baseline models.

Leveraging the repository infrastructure to curate institutional heritage materials, learning objects and data assets

Developing and maintaining a successful institutional repository for research publications requires a considerable investment by the institution. Most of the money is spent on developing the skill-sets of existing staff or hiring new staff with the necessary skills. The return on this investment can be magnified by using this valuable infrastructure to curate collections of other materials such as learning objects, student work, conference proceedings and institutional or local community heritage materials. When Queensland University of Technology (QUT) implemented its repository for research publications (QUT ePrints) over 11 years ago, it was one of the first institutional repositories to be established in Australia. Currently, the repository holds over 29,000 open access research publications and the cumulative total number of full-text downloads for these document now exceeds 16 million. The full-text deposit rate for recently-published peer reviewed papers (currently over 74%) shows how well the repository has been embraced by QUT researchers. The success of QUT ePrints has resulted in requests to accommodate a plethora of materials which are ‘out of scope’ for this repository. QUT Library saw this as an opportunity to use its repository infrastructure (software, technical know-how and policies) to develop and implement a metadata repository for its research datasets (QUT Research Data Finder), a repository for research-related software (QUT Software Finder) and to curate a number of digital collections of institutional and local community heritage materials (QUT Digital Collections). This poster describes the repositories and digital collections curated by QUT Library and outlines the value delivered to the institution, and the wider community, by these initiatives.

External influence as an indicator of scholarly importance

Although the external influence of scholars has usually been approximated by publication and citation count, the array of scholarly activities is far more extensive. Today, new technologies, in particular Internet search engines, allow more accurate measurement of scholars' influence on societal discourse. Hence, in this article, we analyse the relation between the internal and external influence of 723 top economists using the number of pages indexed by Google and Bing as a measure of external influence. We not only identify a small association between these scholars’ internal and external influence but also a correlation between internal influence, as captured by receipt of such major academic awards as the Nobel Prize and John Bates Clark Medal, and the external prominence of the top 100 researchers (JEL Code: A11, A13, Z18).

[await full-text]Evaluation of QAS Workplace Health and Safety Action Plan

This report identifies the outcomes of a program evaluation of the five year Workplace Health and Safety Strategy (2012-2017), specifically, the engagement component within the Queensland Ambulance Service. As part of the former Department of Community Safety, their objective was to work towards harmonising the occupational health and safety policies and process to improve the workplace culture. The report examines and assess the process paths and resource inputs into the strategy, provides feedback on progress to achieving identified goals as well as identify opportunities for improvements and barriers to progress. Consultations were held with key stakeholders within QAS and focus groups were facilitated with managers and health and safety representatives of each Local Area Service Network.

Text segmentation in unconstrained hand-drawings in whiteboard photos

In this paper we present a robust method to detect handwritten text from unconstrained drawings on normal whiteboards. Unlike printed text on documents, free form handwritten text has no pattern in terms of size, orientation and font and it is often mixed with other drawings such as lines and shapes. Unlike handwritings on paper, handwritings on a normal whiteboard cannot be scanned so the detection has to be based on photos. Our work traces straight edges on photos of the whiteboard and builds graph representation of connected components. We use geometric properties such as edge density, graph density, aspect ratio and neighborhood similarity to differentiate handwritten text from other drawings. The experiment results show that our method achieves satisfactory precision and recall. Furthermore, the method is robust and efficient enough to be deployed in a mobile device. This is an important enabler of business applications that support whiteboard-centric visual meetings in enterprise scenarios. © 2012 IEEE.

A service-oriented architecture for text analytics enabled business applications

Experiences showed that developing business applications that base on text analysis normally requires a lot of time and expertise in the field of computer linguistics. Several approaches of integrating text analysis systems with business applications have been proposed, but so far there has been no coordinated approach which would enable building scalable and flexible applications of text analysis in enterprise scenarios. In this paper, a service-oriented architecture for text processing applications in the business domain is introduced. It comprises various groups of processing components and knowledge resources. The architecture, created as a result of our experiences with building natural language processing applications in business scenarios, allows for the reuse of text analysis and other components, and facilitates the development of business applications. We verify our approach by showing how the proposed architecture can be applied to create a text analytics enabled business application that addresses a concrete business scenario. © 2010 IEEE.

Uncovering misconceptions through text analysis

Assessing students’ conceptual understanding of technical content is important for instructors as well as students to learn content and apply knowledge in various contexts. Concept inventories that identify possible misconceptions through validated multiple-choice questions are helpful in identifying a misconception that may exist, but do not provide a meaningful assessment of why they exist or the nature of the students’ understanding. We conducted a case study with undergraduate students in an electrical engineering course by testing a validated multiple-choice response concept inventory that we augmented with a component for students to provide written explanations for their multiple-choice selection. Results revealed that correctly chosen multiple-choice selections did not always match correct conceptual understanding for question testing a specific concept. The addition of a text-response to multiple-choice concept inventory questions provided an enhanced and meaningful assessment of students’ conceptual understanding and highlighted variables associated with current concept inventories or multiple choice questions.

Medical free-text to concept mapping as an information retrieval problem

Concept mapping involves determining relevant concepts from a free-text input, where concepts are defined in an external reference ontology. This is an important process that underpins many applications for clinical information reporting, derivation of phenotypic descriptions, and a number of state-of-the-art medical information retrieval methods. Concept mapping can be cast into an information retrieval (IR) problem: free-text mentions are treated as queries and concepts from a reference ontology as the documents to be indexed and retrieved. This paper presents an empirical investigation applying general-purpose IR techniques for concept mapping in the medical domain. A dataset used for evaluating medical information extraction is adapted to measure the effectiveness of the considered IR approaches. Standard IR approaches used here are contrasted with the effectiveness of two established benchmark methods specifically developed for medical concept mapping. The empirical findings show that the IR approaches are comparable with one benchmark method but well below the best benchmark.

Destinations: 3 Large Cast Plays for Young People

This book is a collection of three large-cast plays written in response to a very specific problem. My work as a teacher of drama often required me to locate a script that would somehow miraculously work for a cast of unknown number and gender, and most likely uneven skills and enthusiasm, who I hadn’t even met yet. It’s a familiar dilemma for teachers and students of drama in education contexts, at whatever level you’re teaching. I’d first addressed this creative problem with scripts such as Gate 38 (2010). I had tried using scripts that already existed, but found they required such extensive editing to suit the parameters of cast and performance duration that I may as well have been writing them myself. Even in the setting of a closed studio, in altering these plays I felt I was bending the vision of the playwright, and certainly their narrative structure, out of shape. Everyone who’s attempted to stage a performance with a large cast of students in an educational setting knows it takes time to truly connect with a play, its social contexts, themes and characters. It also takes a lot of time to get on top of the practicalities of learning, rehearsing, directing and running a performance with young people. Often the curtain goes up on something unfinished and unstable. I was looking for ways to reduce the complexity of staging a script, while maintaining the potential of this process as a site of rich, enjoyable learning. Two of the plays (Duty Free and Please Be Seated) are comprised of multiple monologues, combined with music-driven ensemble sequences. The monologues enable individuals to develop and polish their own performances, work in small groups, and cut down on the laborious detail of directing naturalistic scenes based in character interaction. The third (Australian Drama) involves a lot of duologues, meaning that its rehearsal process can happily employ that mainstay of the drama classroom: small group work. There’s plenty of room to move in terms of gender-blind casting as well. Please be Seated is mainly young women. The scripts also contain ensemble-based interludes which are non-verbal, music driven, with a choreographic element. They have also springboarded further explorations in form. The ethical and aesthetic complexities of verbatim works; the interaction between music and theatre; and meta-concerns related to the performing of performance: ‘how can the act of acting ‘acted’. The narratives of all three of these plays are deliberately open, enabling the flexible casting and on-the hop editing that large-group, time-poor processes sometimes necessitate. Duty Free is about the overseas ‘adventures’ of young people. Please Be Seated is based in verbatim text about young people falling in and out of love. Australian Drama is about young people in a drama classroom trying to connect with each other and put their own shine on dull fragments of the theatrical canon. The plays were published as a collection in hardcopy and digital editions by Playlab Press in 2015. Please be Seated is a co-write with a large group. These co-author’s names are listed in the publication, and below in ‘additional information’.

Enhancement of relevant features for text mining

With the explosion of information resources, there is an imminent need to understand interesting text features or topics in massive text information. This thesis proposes a theoretical model to accurately weight specific text features, such as patterns and n-grams. The proposed model achieves impressive performance in two data collections, Reuters Corpus Volume 1 (RCV1) and Reuters 21578.

Democracy, Participation, and Deliberation in China : The discussion about democratic centralism in the official Chinese press, 1978-1981

This study examines the Chinese press discussion about democratic centralism in 1978-1981 in newspapers, political journals and academic journals distributed nationwide. It is thus a study of intellectual trends during the Hua Guofeng period and of methods, strategies, and techniques of public political discussion of the time. In addition, this study presents democratic centralism as a comprehensive theory of democracy and evaluates this theory. It compares the Chinese theory of democratic centralism with Western traditions of democracy, not only with the standard liberal theory but also with traditions of participatory and deliberative democracy, in order to evaluate whether the Chinese theory of democratic centralism forms a legitimate theory of democracy. It shows that the Chinese theory comes close to participatory types of democracy and shares a conception of democracy as communication with the theory of deliberative democracy. Therefore, the Chinese experience provides some empirical evidence of the practicability of these traditions of democracy. Simultaneously, this study uses experiences of participatory democracies outside of China to explain some earlier findings about the Chinese practices. This dissertation also compares Chinese theory with some common Western theories and models of Chinese society as well as with Western understandings of Chinese political processes. It thus aims at opening more dialogue between Chinese and Western political theories and understandings about Chinese polity. This study belongs to scholarly traditions of the history of ideas, political philosophy, comparative politics, and China studies. The main finding of this study is that the Chinese theory of democratic centralism is essentially a theory about democracy, but whether its scrupulous practicing alone would be sufficient for making a country a democracy depends on which established definition of democracy one applies and on what kind of democratic deficits are seen as being acceptable within a truly democratic system. Nevertheless, since the Chinese theory of democratic centralism fits well with some established definitions of democracy and since democratic deficits are a reality in all actual democracies, the Chinese themselves are talking about democracy in terms acceptable to Western political philosophy as well.