Text mining with semantic annotation : using enriched text representation for entity-oriented retrieval, semantic relation identification and text clustering

This project is a step forward in the study of text mining where enhanced text representation with semantic information plays a significant role. It develops effective methods of entity-oriented retrieval, semantic relation identification and text clustering utilizing semantically annotated data. These methods are based on enriched text representation generated by introducing semantic information extracted from Wikipedia into the input text data. The proposed methods are evaluated against several start-of-art benchmarking methods on real-life data-sets. In particular, this thesis improves the performance of entity-oriented retrieval, identifies different lexical forms for an entity relation and handles clustering documents with multiple feature spaces.

The heterogeneous cluster ensemble method using hubness for clustering text documents

We propose a cluster ensemble method to map the corpus documents into the semantic space embedded in Wikipedia and group them using multiple types of feature space. A heterogeneous cluster ensemble is constructed with multiple types of relations i.e. document-term, document-concept and document-category. A final clustering solution is obtained by exploiting associations between document pairs and hubness of the documents. Empirical analysis with various real data sets reveals that the proposed meth-od outperforms state-of-the-art text clustering approaches.

Understanding the phenomenon of IS success in China through the lens of the IS-Impact model

This study is conducted within the IS-Impact Research Track at Queensland University of Technology (QUT). The goal of the IS-Impact Track is, “to develop the most widely employed model for benchmarking information systems in organizations for the joint benefit of both research and practice” (Gable et al, 2006). IS-Impact is defined as “a measure at a point in time, of the stream of net benefits from the IS, to date and anticipated, as perceived by all key-user-groups” (Gable Sedera and Chan, 2008). Track efforts have yielded the bicameral IS-Impact measurement model; the “impact” half includes Organizational-Impact and Individual-Impact dimensions; the “quality” half includes System-Quality and Information-Quality dimensions. The IS-Impact model, by design, is intended to be robust, simple and generalizable, to yield results that are comparable across time, stakeholders, different systems and system contexts. The model and measurement approach employ perceptual measures and an instrument that is relevant to key stakeholder groups, thereby enabling the combination or comparison of stakeholder perspectives. Such a validated and widely accepted IS-Impact measurement model has both academic and practical value. It facilitates systematic operationalization of a main dependent variable in research (IS-Impact), which can also serve as an important independent variable. For IS management practice it provides a means to benchmark and track the performance of information systems in use. The objective of this study is to develop a Mandarin version IS-Impact model, encompassing a list of China-specific IS-Impact measures, aiding in a better understanding of the IS-Impact phenomenon in a Chinese organizational context. The IS-Impact model provides a much needed theoretical guidance for this investigation of ES and ES impacts in a Chinese context. The appropriateness and soundness of employing the IS-Impact model as a theoretical foundation are evident: the model originated from a sound theory of IS Success (1992), developed through rigorous validation, and also derived in the context of Enterprise Systems. Based on the IS-Impact model, this study investigates a number of research questions (RQs). Firstly, the research investigated what essential impacts have been derived from ES by Chinese users and organizations [RQ1]. Secondly, we investigate which salient quality features of ES are perceived by Chinese users [RQ2]. Thirdly, we seek to answer whether the quality and impacts measures are sufficient to assess ES-success in general [RQ3]. Lastly, the study attempts to address whether the IS-Impact measurement model is appropriate for Chinese organizations in terms of evaluating their ES [RQ4]. An open-ended, qualitative identification survey was employed in the study. A large body of short text data was gathered from 144 Chinese users and 633 valid IS-Impact statements were generated from the data set. A generally inductive approach was applied in the qualitative data analysis. Rigorous qualitative data coding resulted in 50 first-order categories with 6 second-order categories that were grounded from the context of Chinese organization. The six second-order categories are: 1) System Quality; 2) Information Quality; 3) Individual Impacts;4) Organizational Impacts; 5) User Quality and 6) IS Support Quality. The final research finding of the study is the contextualized Mandarin version IS-Impact measurement model that includes 38 measures organized into 4 dimensions: System Quality, information Quality, Individual Impacts and Organizational Impacts. The study also proposed two conceptual models to harmonize the IS-Impact model and the two emergent constructs – User Quality and IS Support Quality by drawing on previous IS effectiveness literatures and the Work System theory proposed by Alter (1999) respectively. The study is significant as it is the first effort that empirically and comprehensively investigates IS-Impact in China. Specifically, the research contributions can be classified into theoretical contributions and practical contributions. From the theoretical perspective, through qualitative evidence, the study test and consolidate IS-Impact measurement model in terms of the quality of robustness, completeness and generalizability. The unconventional research design exhibits creativity of the study. The theoretical model does not work as a top-down a priori seeking for evidence demonstrating its credibility; rather, the study allows a competitive model to emerge from the bottom-up and open-coding analysis. Besides, the study is an example extending and localizing pre-existing theory developed in Western context when the theory is introduced to a different context. On the other hand, from the practical perspective, It is first time to introduce prominent research findings in field of IS Success to Chinese academia and practitioner. This study provides a guideline for Chinese organizations to assess their Enterprise System, and leveraging IT investment in the future. As a research effort in ITPS track, this study contributes the research team with an alternative operationalization of the dependent variable. The future research can take on the contextualized Mandarin version IS-Impact framework as a theoretical a priori model, further quantitative and empirical testing its validity.

Using Web Search Logs to Identify Query Classification Terms

Purpose – The work presented in this paper aims to provide an approach to classifying web logs by personal properties of users. Design/methodology/approach – The authors describe an iterative system that begins with a small set of manually labeled terms, which are used to label queries from the log. A set of background knowledge related to these labeled queries is acquired by combining web search results on these queries. This background set is used to obtain many terms that are related to the classification task. The system then ranks each of the related terms, choosing those that most fit the personal properties of the users. These terms are then used to begin the next iteration. Findings – The authors identify the difficulties of classifying web logs, by approaching this problem from a machine learning perspective. By applying the approach developed, the authors are able to show that many queries in a large query log can be classified. Research limitations/implications – Testing results in this type of classification work is difficult, as the true personal properties of web users are unknown. Evaluation of the classification results in terms of the comparison of classified queries to well known age-related sites is a direction that is currently being exploring. Practical implications – This research is background work that can be incorporated in search engines or other web-based applications, to help marketing companies and advertisers. Originality/value – This research enhances the current state of knowledge in short-text classification and query log learning. Classification schemes, Computer networks, Information retrieval, Man-machine systems, User interfaces

Injury narrative text classification : a preliminary study

Description of a patient's injuries is recorded in narrative text form by hospital emergency departments. For statistical reporting, this text data needs to be mapped to pre-defined codes. Existing research in this field uses the Naïve Bayes probabilistic method to build classifiers for mapping. In this paper, we focus on providing guidance on the selection of a classification method. We build a number of classifiers belonging to different classification families such as decision tree, probabilistic, neural networks, and instance-based, ensemble-based and kernel-based linear classifiers. An extensive pre-processing is carried out to ensure the quality of data and, in hence, the quality classification outcome. The records with a null entry in injury description are removed. The misspelling correction process is carried out by finding and replacing the misspelt word with a soundlike word. Meaningful phrases have been identified and kept, instead of removing the part of phrase as a stop word. The abbreviations appearing in many forms of entry are manually identified and only one form of abbreviations is used. Clustering is utilised to discriminate between non-frequent and frequent terms. This process reduced the number of text features dramatically from about 28,000 to 5000. The medical narrative text injury dataset, under consideration, is composed of many short documents. The data can be characterized as high-dimensional and sparse, i.e., few features are irrelevant but features are correlated with one another. Therefore, Matrix factorization techniques such as Singular Value Decomposition (SVD) and Non Negative Matrix Factorization (NNMF) have been used to map the processed feature space to a lower-dimensional feature space. Classifiers with these reduced feature space have been built. In experiments, a set of tests are conducted to reflect which classification method is best for the medical text classification. The Non Negative Matrix Factorization with Support Vector Machine method can achieve 93% precision which is higher than all the tested traditional classifiers. We also found that TF/IDF weighting which works well for long text classification is inferior to binary weighting in short document classification. Another finding is that the Top-n terms should be removed in consultation with medical experts, as it affects the classification performance.

Document clustering with K-tree

This paper describes the approach taken to the XML Mining track at INEX 2008 by a group at the Queensland University of Technology. We introduce the K-tree clustering algorithm in an Information Retrieval context by adapting it for document clustering. Many large scale problems exist in document clustering. K-tree scales well with large inputs due to its low complexity. It offers promising results both in terms of efficiency and quality. Document classification was completed using Support Vector Machines.

Strategic short termism as an issue of top-teams’ temporal orientation

Short-termism among firms, the tendency to excessively discount long-term benefits and favour less valuable short-term benefits, has been a prominent issue in business and public policy debates but research to date has been inconclusive. We study how managers frame, interpret, and resolve problems of intertemporal choice in actual decisions by using computer aided text analysis to measure the frequency of top-team temporal references in 1653 listed Australian firms between 1992-2005. Contrary to short-termism arguments we find evidence of a significant general increase in Future orientation and a significant decrease in Current/Past orientation. We also show top-teams’ temporal orientation is related to their strategic orientation, specifically the extent to which they focus on Innovation-Expansion and Capacity Building.

The use of narrative text for injury surveillance research : a systematic review

Objective: To summarise the extent to which narrative text fields in administrative health data are used to gather information about the event resulting in presentation to a health care provider for treatment of an injury, and to highlight best practise approaches to conducting narrative text interrogation for injury surveillance purposes.----- Design: Systematic review----- Data sources: Electronic databases searched included CINAHL, Google Scholar, Medline, Proquest, PubMed and PubMed Central.. Snowballing strategies were employed by searching the bibliographies of retrieved references to identify relevant associated articles.----- Selection criteria: Papers were selected if the study used a health-related database and if the study objectives were to a) use text field to identify injury cases or use text fields to extract additional information on injury circumstances not available from coded data or b) use text fields to assess accuracy of coded data fields for injury-related cases or c) describe methods/approaches for extracting injury information from text fields.----- Methods: The papers identified through the search were independently screened by two authors for inclusion, resulting in 41 papers selected for review. Due to heterogeneity between studies metaanalysis was not performed.----- Results: The majority of papers reviewed focused on describing injury epidemiology trends using coded data and text fields to supplement coded data (28 papers), with these studies demonstrating the value of text data for providing more specific information beyond what had been coded to enable case selection or provide circumstantial information. Caveats were expressed in terms of the consistency and completeness of recording of text information resulting in underestimates when using these data. Four coding validation papers were reviewed with these studies showing the utility of text data for validating and checking the accuracy of coded data. Seven studies (9 papers) described methods for interrogating injury text fields for systematic extraction of information, with a combination of manual and semi-automated methods used to refine and develop algorithms for extraction and classification of coded data from text. Quality assurance approaches to assessing the robustness of the methods for extracting text data was only discussed in 8 of the epidemiology papers, and 1 of the coding validation papers. All of the text interrogation methodology papers described systematic approaches to ensuring the quality of the approach.----- Conclusions: Manual review and coding approaches, text search methods, and statistical tools have been utilised to extract data from narrative text and translate it into useable, detailed injury event information. These techniques can and have been applied to administrative datasets to identify specific injury types and add value to previously coded injury datasets. Only a few studies thoroughly described the methods which were used for text mining and less than half of the studies which were reviewed used/described quality assurance methods for ensuring the robustness of the approach. New techniques utilising semi-automated computerised approaches and Bayesian/clustering statistical methods offer the potential to further develop and standardise the analysis of narrative text for injury surveillance.

Identifying work related injuries : comparison of methods for interrogating text fields

Background: Work-related injuries in Australia are estimated to cost around $57.5 billion annually, however there are currently insufficient surveillance data available to support an evidence-based public health response. Emergency departments (ED) in Australia are a potential source of information on work-related injuries though most ED’s do not have an ‘Activity Code’ to identify work-related cases with information about the presenting problem recorded in a short free text field. This study compared methods for interrogating text fields for identifying work-related injuries presenting at emergency departments to inform approaches to surveillance of work-related injury.---------- Methods: Three approaches were used to interrogate an injury description text field to classify cases as work-related: keyword search, index search, and content analytic text mining. Sensitivity and specificity were examined by comparing cases flagged by each approach to cases coded with an Activity code during triage. Methods to improve the sensitivity and/or specificity of each approach were explored by adjusting the classification techniques within each broad approach.---------- Results: The basic keyword search detected 58% of cases (Specificity 0.99), an index search detected 62% of cases (Specificity 0.87), and the content analytic text mining (using adjusted probabilities) approach detected 77% of cases (Specificity 0.95).---------- Conclusions The findings of this study provide strong support for continued development of text searching methods to obtain information from routine emergency department data, to improve the capacity for comprehensive injury surveillance.

Application of K-tree to document clustering

Digital collections are growing exponentially in size as the information age takes a firm grip on all aspects of society. As a result Information Retrieval (IR) has become an increasingly important area of research. It promises to provide new and more effective ways for users to find information relevant to their search intentions. Document clustering is one of the many tools in the IR toolbox and is far from being perfected. It groups documents that share common features. This grouping allows a user to quickly identify relevant information. If these groups are misleading then valuable information can accidentally be ignored. There- fore, the study and analysis of the quality of document clustering is important. With more and more digital information available, the performance of these algorithms is also of interest. An algorithm with a time complexity of O(n2) can quickly become impractical when clustering a corpus containing millions of documents. Therefore, the investigation of algorithms and data structures to perform clustering in an efficient manner is vital to its success as an IR tool. Document classification is another tool frequently used in the IR field. It predicts categories of new documents based on an existing database of (doc- ument, category) pairs. Support Vector Machines (SVM) have been found to be effective when classifying text documents. As the algorithms for classifica- tion are both efficient and of high quality, the largest gains can be made from improvements to representation. Document representations are vital for both clustering and classification. Representations exploit the content and structure of documents. Dimensionality reduction can improve the effectiveness of existing representations in terms of quality and run-time performance. Research into these areas is another way to improve the efficiency and quality of clustering and classification results. Evaluating document clustering is a difficult task. Intrinsic measures of quality such as distortion only indicate how well an algorithm minimised a sim- ilarity function in a particular vector space. Intrinsic comparisons are inherently limited by the given representation and are not comparable between different representations. Extrinsic measures of quality compare a clustering solution to a “ground truth” solution. This allows comparison between different approaches. As the “ground truth” is created by humans it can suffer from the fact that not every human interprets a topic in the same manner. Whether a document belongs to a particular topic or not can be subjective.

PLDA based speaker recognition on short utterances

This paper investigates the effects of limited speech data in the context of speaker verification using a probabilistic linear discriminant analysis (PLDA) approach. Being able to reduce the length of required speech data is important to the development of automatic speaker verification system in real world applications. When sufficient speech is available, previous research has shown that heavy-tailed PLDA (HTPLDA) modeling of speakers in the i-vector space provides state-of-the-art performance, however, the robustness of HTPLDA to the limited speech resources in development, enrolment and verification is an important issue that has not yet been investigated. In this paper, we analyze the speaker verification performance with regards to the duration of utterances used for both speaker evaluation (enrolment and verification) and score normalization and PLDA modeling during development. Two different approaches to total-variability representation are analyzed within the PLDA approach to show improved performance in short-utterance mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development. The results presented within this paper using the NIST 2008 Speaker Recognition Evaluation dataset suggest that the HTPLDA system can continue to achieve better performance than Gaussian PLDA (GPLDA) as evaluation utterance lengths are decreased. We also highlight the importance of matching durations for score normalization and PLDA modeling to the expected evaluation conditions. Finally, we found that a pooled total-variability approach to PLDA modeling can achieve better performance than the traditional concatenated total-variability approach for short utterances in mismatched evaluation conditions and conditions for which insufficient speech resources are available for adequate system development.

Text messaging to support off-campus clinical facilitators of undergraduate student nurses

Managing large cohorts of undergraduate student nurses during off-campus clinical placement is complex and challenging. Clinical facilitators are required to support and assess nursing students during clinical placement. Therefore clear communication between university academic coordinators and clinical facilitators is essential for consistency and prompt management of emerging issues. Increasing work demands require both coordinators and facilitators to have an efficient and effective mode of communication. The aim of this study was to explore the use of Short Message Service (SMS) texts, sent between mobile phones, for communication between university Unit Coordinators and off-campus Clinical Facilitators. This study used an after-only design. During a two week clinical placement 46 clinical facilitators working with first and second year Bachelor of Nursing students from a large metropolitan Australian university were regularly sent SMS texts of relevant updates and reminders from the university coordinator. A 15 item questionnaire comprising x of 5 point likert scale and 3 open-ended questions was then used to survey the clinical facilitators. The response rate was 47.8% (n=22). Correlations were found between the approachability of the coordinator and facilitator perception of a) that the coordinator understood issues on clinical placement (r=0.785, p<0.001,), and b) being part of the teaching team (r=0.768, p<0.001). Analysis of responses to qualitative questions revealed three themes: connection, approachability and collaboration. Results indicate that SMS communication is convenient and appropriate in this setting. This quasi-experimental after-test study found regular SMS communication improves a sense of connection, approachability and collaboration.

Protocol for a randomised blocked design study using telephone and text-messaging to support cardiac patients with diabetes : a cross cultural international collaborative project

Background The prevalence of type 2 diabetes is rising internationally. Patients with diabetes have a higher risk of cardiovascular events accounting for substantial premature morbidity and mortality, and health care expenditure. Given healthcare workforce limitations, there is a need to improve interventions that promote positive self-management behaviours that enable patients to manage their chronic conditions effectively, across different cultural contexts. Previous studies have evaluated the feasibility of including telephone and Short Message Service (SMS) follow up in chronic disease self-management programs, but only for single diseases or in one specific population. Therefore, the aim of this study is to evaluate the feasibility and short-term efficacy of incorporating telephone and text messaging to support the care of patients with diabetes and cardiac disease, in Australia and in Taiwan. Methods/design A randomised controlled trial design will be used to evaluate a self-management program for people with diabetes and cardiac disease that incorporates the use of simple remote-access communication technologies. A sample size of 180 participants from Australia and Taiwan will be recruited and randomised in a one-to-one ratio to receive either the intervention in addition to usual care (intervention) or usual care alone (control). The intervention will consist of in-hospital education as well as follow up utilising personal telephone calls and SMS reminders. Primary short term outcomes of interest include self-care behaviours and self-efficacy assessed at baseline and four weeks. Discussion If the results of this investigation substantiate the feasibility and efficacy of the telephone and SMS intervention for promoting self management among patients with diabetes and cardiac disease in Australia and Taiwan, it will support the external validity of the intervention. It is anticipated that empirical data from this investigation will provide valuable information to inform future international collaborations, while providing a platform for further enhancements of the program, which has potential to benefit patients internationally.

A novel process of group-oriented question reduction for rule-based recommendation websites

Several websites utilise a rule-base recommendation system, which generates choices based on a series of questionnaires, for recommending products to users. This approach has a high risk of customer attrition and the bottleneck is the questionnaire set. If the questioning process is too long, complex or tedious; users are most likely to quit the questionnaire before a product is recommended to them. If the questioning process is short; the user intensions cannot be gathered. The commonly used feature selection methods do not provide a satisfactory solution. We propose a novel process combining clustering, decisions tree and association rule mining for a group-oriented question reduction process. The question set is reduced according to common properties that are shared by a specific group of users. When applied on a real-world website, the proposed combined method outperforms the methods where the reduction of question is done only by using association rule mining or only by observing distribution within the group.

The ranking based constrained document clustering method and its application to social event detection

With the growing size and variety of social media files on the web, it’s becoming critical to efficiently organize them into clusters for further processing. This paper presents a novel scalable constrained document clustering method that harnesses the power of search engines capable of dealing with large text data. Instead of calculating distance between the documents and all of the clusters’ centroids, a neighborhood of best cluster candidates is chosen using a document ranking scheme. To make the method faster and less memory dependable, the in-memory and in-database processing are combined in a semi-incremental manner. This method has been extensively tested in the social event detection application. Empirical analysis shows that the proposed method is efficient both in computation and memory usage while producing notable accuracy.