Pattern-based topic modelling and its application for information filtering and information retrieval

This thesis targets on a challenging issue that is to enhance users' experience over massive and overloaded web information. The novel pattern-based topic model proposed in this thesis can generate high-quality multi-topic user interest models technically by incorporating statistical topic modelling and pattern mining. We have successfully applied the pattern-based topic model to both fields of information filtering and information retrieval. The success of the proposed model in finding the most relevant information to users mainly comes from its precisely semantic representations to represent documents and also accurate classification of the topics at both document level and collection level.

Strenthening information literacy through collaboration: Implications for AIM

Because of its size, its excellent VET history, and its emerging higher education provision, AIM is in a special position to be an exemplar of good practice in the VET-HE transition. Many dual sector providers, by virtue of their size, tend to focus on higher education, on the assumption that VET ‘competence’ implies that their VET entrants to HE are confident and capable in information literacy skills. While this is only one of the many challenges that such students face in their undergraduate programs, it is the most critical for most of them in their quest for academic success. All students (school leavers, gap-year participants, articulating, mature age) entering HE will face specific challenges. For articulating students, the nature of credit transfer arrangements will often mean they commence studies in units that are not designated first year units. In this case, the embedded support structures are not as prominent. The existing literature is not consistent in reports on the rates of completion, retention and attrition of articulating students. There is some evidence that VET-qualified students have higher retention rates than school leavers [1], but limited information literacy skills can lead to attrition [2].

How everyday language can and will boost effective information retrieval

Typing 2 or 3 keywords into a browser has become an easy and efficient way to find information. Yet, typing even short queries becomes tedious on ever shrinking (virtual) keyboards. Meanwhile, speech processing is maturing rapidly, facilitating everyday language input. Also, wearable technology can inform users proactively by listening in on their conversations or processing their social media interactions. Given these developments, everyday language may soon become the new input of choice. We present an information retrieval (IR) algorithm specifically designed to accept everyday language. It integrates two paradigms of information retrieval, previously studied in isolation; one directed mainly at the surface structure of language, the other primarily at the underlying meaning. The integration was achieved by a Markov machine that encodes meaning by its transition graph, and surface structure by the language it generates. A rigorous evaluation of the approach showed, first, that it can compete with the quality of existing language models, second, that it is more effective the more verbose the input, and third, as a consequence, that it is promising for an imminent transition from keyword input, where the onus is on the user to formulate concise queries, to a modality where users can express more freely, more informal, and more natural their need for information in everyday language.

Identifying satisfaction factors in tertiary education: The case of an information systems program

This paper introduces a modified Kano approach to analysing and classifying quality attributes that drive student satisfaction in tertiary education. The approach provides several benefits over the traditional Kano approach. Firstly, it uses existing student evaluations of subjects in the educational institution instead of purpose-built surveys as the data source. Secondly, since the data source includes qualitative comments and feedback, it has the exploratory capability to identify emerging and unique attributes. Finally, since the quality attributes identified could be tied directly to students’ detailed feedback, the approach enables practitioners to easily translate the results into concrete action plans. In this paper, the approach is applied to analysing 26 subjects in the information systems school of an Australia university. The approach has enabled the school to uncover new quality attributes and paves the way for other institutions to use their student evaluations to continually understand and addressed students’ changing needs.

Exploiting inference from semantic annotations for information retrieval

The increasing amount of information that is annotated against standardised semantic resources offers opportunities to incorporate sophisticated levels of reasoning, or inference, into the retrieval process. In this position paper, we reflect on the need to incorporate semantic inference into retrieval (in particular for medical information retrieval) as well as previous attempts that have been made so far with mixed success. Medical information retrieval is a fertile ground for testing inference mechanisms to augment retrieval. The medical domain offers a plethora of carefully curated, structured, semantic resources, along with well established entity extraction and linking tools, and search topics that intuitively require a number of different inferential processes (e.g., conceptual similarity, conceptual implication, etc.). We argue that integrating semantic inference in information retrieval has the potential to uncover a large amount of information that otherwise would be inaccessible; but inference is also risky and, if not used cautiously, can harm retrieval.

Reliable fault diagnosis for incipient low-speed bearings using fault feature analysis based on a binary bat algorithm

In this paper, we propose a highly reliable fault diagnosis scheme for incipient low-speed rolling element bearing failures. The scheme consists of fault feature calculation, discriminative fault feature analysis, and fault classification. The proposed approach first computes wavelet-based fault features, including the respective relative wavelet packet node energy and entropy, by applying a wavelet packet transform to an incoming acoustic emission signal. The most discriminative fault features are then filtered from the originally produced feature vector by using discriminative fault feature analysis based on a binary bat algorithm (BBA). Finally, the proposed approach employs one-against-all multiclass support vector machines to identify multiple low-speed rolling element bearing defects. This study compares the proposed BBA-based dimensionality reduction scheme with four other dimensionality reduction methodologies in terms of classification performance. Experimental results show that the proposed methodology is superior to other dimensionality reduction approaches, yielding an average classification accuracy of 94.9%, 95.8%, and 98.4% under bearing rotational speeds at 20 revolutions-per-minute (RPM), 80 RPM, and 140 RPM, respectively.

Deriving information systems innovation execution mechanisms

Despite a wealth of studies focusing on innovation, types of innovations and their outcomes, the process of innovation has largely been under studied. In 2010, Swanson calls for researchers to address the ‘innovation process black box’, to better understand how IT innovation potential can be exploited upon. This study derives and instantiates three unique and mutually exclusive innovation execution mechanisms: Continual, Progressive and Plug and Play. The innovation execution mechanisms of this study are developed with reference to Swanson (1994) Information Systems innovation types.

Spatial governance: The metalanguage of spatiotemporal information and its infrastructure

‘Spatial governance’ involves a large number of situations where knowledge of place and time is important in achieving acceptable organisational outcomes. This paper argues that spatial governance calls for information-intensive activity in three main areas. The first establishes ‘authority’ in a legal entity to decide issues regarding resources within a territorial jurisdiction. The second involves planning the future use of resources. It engages a language of design, purpose, modeling, visualization, expectations and risk. The third involves monitoring of outcomes to see if expectations are met; and whether changes to authority and planning regimes need to be made in the light of experience. This engages a language of observing, recording, accounting, auditing, statistical indicators and accountability. ‘Authority’, ‘planning’ and ‘monitoring’ regimes can be constructed using a relatively small number of elements, in much the same way that a large number of words with recognisable meanings can be created using a relatively few standardised letters of the alphabet. Words can combine in a similar process of combinatorial explosion to create any message that can be imagined. Similarly, combining authority, planning and monitoring regimes can create a metalanguage of ‘spatial governance’ to give purpose, meaning and value to any spatiotemporal information system that can be imagined, described, interpreted and understood.

Demand for ecolabeled seafood in the Japanese market: A conjoint analysis of the impact of information and interaction with other labels

The use of seafood ecolabels is expanding in the world marketplace, but so are labels indicating other product attributes, such as country of origin and wild vs. farmed. The interactive effects of these labels and attributes in evaluating consumers' preferences for ecolabeled seafood are relatively unexplored. In this paper we investigate (1) the direct and interactive effects of seafood ecolabels with other common fish labels, and (2) how consumers' perceptions about the state of marine stocks and the valuation of ecolabels may be affected by different information. We find moderate interactive effects between ecolabels and country of origin labels, whereas the valuation for seafood ecolabels is fairly high. In terms of information, we find that consumers' perceptions about fish stock levels changed (negatively) after receiving information on declining stock levels, and more sensationalized information led to increased change. However, valuation for a seafood ecolabel increases only when the information was perceived positively (credible/interesting); whereas exaggerated information (which was also perceived less credible) had insignificant effects on WTP.

Teachers-as-writers: Writing information texts in English and vernacular

Our contribution to this volume is not on the work of the teacher who inspires the child writer, but the teacher as the writer and illustrator of multilingual texts for classroom use that inspires the child reader. This chapter focuses on a first time teacher writer from Fiji, Bereta , who participated in a two day writing workshop known as the Information Text Awareness Project (hereafter ITAP). This chapter commences with an overview of the ITAP which was conducted in Nadi, Fiji, in 2012 with Bereta and 17 teachers from urban, semi-urban and rural contexts within the Nadi educational district. The politics of presenting Western ways of knowing to teachers from diverse cultural and linguistic contexts via a Western pedagogical approach is explored in the second section. We believe that this work involves a moral dimension that needs careful consideration. The third section outlines the eight stages of ITAP where teacher writers such as Bereta produced an English and a vernacular information text for use in their classrooms. The outline of the eight stages of ITAP is justified with links to the research literature. The final section recounts Bereta’s interview data where she talks about using the newly created English and vernacular information texts in the classroom and the community’s response to her inaugural publications. The findings may be of interest to those seeking to establish an adult writing cooperative to produce English and vernacular information texts for classroom use.

Catering for cultural and linguistic diversity: Using teacher created information texts

Teachers in the Pacific region have often signalled the need for more locally produced information texts in both the vernacular and English, to engage their readers with local content and to support literacy development across the curriculum. The Information Text Awareness Project (ITAP), initially informed by the work of Nea Stewart-Dore, has provided a means to address this need through supporting local teachers to write their own information texts. The article reports on the impact of an ITAP workshop carried out in Nadi, Fiji in 2012. Nine teacher volunteers from the project trialled the use of the texts in their classrooms with positive results in relation to student learning and belief in themselves as writers.

Information Accountability Framework (IAF)

POSTER: Information Accountability Framework (IAF) to mitigate and manage the risk of data breaches and unauthorised used of medical information (e.g., Electronic Health Records)

Gearing up academics for collaborative Building Information Modelling (BIM) education

Building information modelling (BIM) radically changes the practices in architecture, engineering and construction (AEC) and creates new job opportunities. Many governments, such as the United Kingdom, have made BIM a mandatory requirement. This substantially drives the demand for a BIM-literate workforce. Universities are facing the challenge to incorporate BIM into their curricula and produce “BIM ready” graduates to meet the needs of the industry. Like other universities, Queensland University of Technology (QUT) is at the heart of this change and aspires to develop collaborative BIM education across AEC. Previous BIM education studies identify that inadequate BIM awareness of AEC academics is one of the challenges for developing a BIM curriculum and there is a dearth in the learning and teaching support for academics on BIM education. Equipping the AEC academics for a more BIM focused curriculum is all the while more important. This paper aims to leverage knowledge drawn from a Learning & Teaching project currently undertaken at QUT. Its specific objectives are to: 1) review the existing learning and teaching initiatives on BIM education; and 2) briefly describe the learning and teaching activities on collaborative BIM education at QUT. Significance of the paper lies on revealing the importance of building up the capacity of AEC academics for collaborative BIM education. The paper contributes to sparking the interests in better equipping AEC academics to understand what curriculum changes would assist in BIM uptake within the relevant courses to provide context for changes in units; and how the use of BIM can improve the understanding by students of the large amounts of professional knowledge they need to function effectively as graduates.