Interference in text categorisation experiments

This article examines manual textual categorisation by human coders with the hypothesis that the law of total probability may be violated for difficult categories. An empirical evaluation was conducted to compare a one step categorisation task with a two step categorisation task using crowdsourcing. It was found that the law of total probability was violated. Both a quantum and classical probabilistic interpretations for this violation are presented. Further studies are required to resolve whether quantum models are more appropriate for this task.

Effect of text type on near work-induced contrast adaptation in myopic and emmetropic young adults

Purpose Contrast adaptation has been speculated to be an error signal for emmetropization. Myopic children exhibit higher contrast adaptation than emmetropic children. This study aimed to determine whether contrast adaptation varies with the type of text viewed by emmetropic and myopic young adults. Methods Baseline contrast sensitivity was determined in 25 emmetropic and 25 spectacle-corrected myopic young adults for 0.5, 1.2, 2.7, 4.4, and 6.2 cycles per degree (cpd) horizontal sine wave gratings. The adults spent periods looking at a 6.2 cpd high-contrast horizontal grating and reading lines of English and Chinese text (these texts comprised 1.2 cpd row and 6 cpd stroke frequencies). The effects of these near tasks on contrast sensitivity were determined, with decreases in sensitivity indicating contrast adaptation. Results Contrast adaptation was affected by the near task (F2,672 = 43.0; P < 0.001). Adaptation was greater for the grating task (0.13 ± 0.17 log unit, averaged across all frequencies) than reading tasks, but there was no significant difference between the two reading tasks (English 0.05 ± 0.13 log unit versus Chinese 0.04 ± 0.13 log unit). The myopic group showed significantly greater adaptation (by 0.04, 0.04, and 0.05 log units for English, Chinese, and grating tasks, respectively) than the emmetropic group (F1,48 = 5.0; P = 0.03). Conclusions In young adults, reading Chinese text induced similar contrast adaptation as reading English text. Myopes exhibited greater contrast adaptation than emmetropes. Contrast adaptation, independent of text type, might be associated with myopia development.

Text messaging to support off-campus clinical nursing facilitators : a descriptive survey

Background Managing large student cohorts can be a challenge for university academics, coordinating these units. Bachelor of Nursing programmes have the added challenge of managing multiple groups of students and clinical facilitators whilst completing clinical placement. Clear, time efficient and effective communication between coordinating academics and clinical facilitators is needed to ensure consistency between student and teaching groups and prompt management of emerging issues. Methods This study used a descriptive survey to explore the use of text messaging via a mobile phone, sent from coordinating academics to off-campus clinical facilitators, as an approach to providing direction and support. Results The response rate was 47.8% (n = 22). Correlations were found between the approachability of the coordinating academic and clinical facilitator perception that, a) the coordinating academic 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. Conclusions This study demonstrates that use of regular text messages improves communication between coordinating academics and clinical facilitators. Findings suggest improved connection, approachability and collaboration between the coordinating academic and clinical facilitation staff.

Rough set based approach to text classification

Textual document set has become an important and rapidly growing information source in the web. Text classification is one of the crucial technologies for information organisation and management. Text classification has become more and more important and attracted wide attention of researchers from different research fields. In this paper, many feature selection methods, the implement algorithms and applications of text classification are introduced firstly. However, because there are much noise in the knowledge extracted by current data-mining techniques for text classification, it leads to much uncertainty in the process of text classification which is produced from both the knowledge extraction and knowledge usage, therefore, more innovative techniques and methods are needed to improve the performance of text classification. It has been a critical step with great challenge to further improve the process of knowledge extraction and effectively utilization of the extracted knowledge. Rough Set decision making approach is proposed to use Rough Set decision techniques to more precisely classify the textual documents which are difficult to separate by the classic text classification methods. The purpose of this paper is to give an overview of existing text classification technologies, to demonstrate the Rough Set concepts and the decision making approach based on Rough Set theory for building more reliable and effective text classification framework with higher precision, to set up an innovative evaluation metric named CEI which is very effective for the performance assessment of the similar research, and to propose a promising research direction for addressing the challenging problems in text classification, text mining and other relative fields.

Can we text you? A qualitative exploration of young unemployed job-seekers’ attitudes to receiving resilience-building SMS messages

A significant minority of young job-seekers remain unemployed for many months, and are at risk of developing depression. Both empirical studies and theoretical models suggest that cognitive, behavioural and social isolation factors interact to increase this risk. Thus, interventions that reduce or prevent depression in young unemployed job-seekers by boosting their resilience are required. Mobile phones may be an effective medium to deliver resilience-boosting support to young unemployed people by using SMS messages to interrupt the feedback loop of depression and social isolation. Three focus groups were conducted to explore young unemployed job-seekers’ attitudes to receiving and requesting regular SMS messages that would help them to feel supported and motivated while job-seeking. Participants reacted favourably to this proposal, and thought that it would be useful to continue to receive and request SMS messages for a few months after commencing employment as well.

Ethnic diversity and its impact on community social cohesion and neighborly exchange

Putnam's “constrict theory” suggests that ethnic diversity creates challenges for developing and sustaining social capital in urban settings. He argues that diversity decreases social cohesion and reduces social interactions among community residents. While Putnam's thesis is the subject of much debate in North America, the United Kingdom, and Europe, there is a limited focus on how ethnic diversity impacts upon social cohesion and neighborly exchange behaviors in Australia. Employing multilevel modeling and utilizing administrative and survey data from 4,000 residents living in 148 Brisbane suburbs, we assess whether ethnic diversity lowers social cohesion and increases “hunkering.” Our findings indicate that social cohesion and neighborly exchange are attenuated in ethnically diverse suburbs. However, diversity is less consequential for neighborly exchange among immigrants when compared to the general population. Our results provide at least partial support for Putnam's thesis.

Clinician-driven automated classification of limb fractures from free-text radiology reports

The aim of this research is to report initial experimental results and evaluation of a clinician-driven automated method that can address the issue of misdiagnosis from unstructured radiology reports. Timely diagnosis and reporting of patient symptoms in hospital emergency departments (ED) is a critical component of health services delivery. However, due to disperse information resources and vast amounts of manual processing of unstructured information, a point-of-care accurate diagnosis is often difficult. A rule-based method that considers the occurrence of clinician specified keywords related to radiological findings was developed to identify limb abnormalities, such as fractures. A dataset containing 99 narrative reports of radiological findings was sourced from a tertiary hospital. The rule-based method achieved an F-measure of 0.80 and an accuracy of 0.80. While our method achieves promising performance, a number of avenues for improvement were identified using advanced natural language processing (NLP) techniques.

Automatic classification of free-text radiology reports to identify limb fractures using machine learning and the SNOMED CT ontology

Objective To develop and evaluate machine learning techniques that identify limb fractures and other abnormalities (e.g. dislocations) from radiology reports. Materials and Methods 99 free-text reports of limb radiology examinations were acquired from an Australian public hospital. Two clinicians were employed to identify fractures and abnormalities from the reports; a third senior clinician resolved disagreements. These assessors found that, of the 99 reports, 48 referred to fractures or abnormalities of limb structures. Automated methods were then used to extract features from these reports that could be useful for their automatic classification. The Naive Bayes classification algorithm and two implementations of the support vector machine algorithm were formally evaluated using cross-fold validation over the 99 reports. Result Results show that the Naive Bayes classifier accurately identifies fractures and other abnormalities from the radiology reports. These results were achieved when extracting stemmed token bigram and negation features, as well as using these features in combination with SNOMED CT concepts related to abnormalities and disorders. The latter feature has not been used in previous works that attempted classifying free-text radiology reports. Discussion Automated classification methods have proven effective at identifying fractures and other abnormalities from radiology reports (F-Measure up to 92.31%). Key to the success of these techniques are features such as stemmed token bigrams, negations, and SNOMED CT concepts associated with morphologic abnormalities and disorders. Conclusion This investigation shows early promising results and future work will further validate and strengthen the proposed approaches.

Automated classification of limb fractures from free-text radiology reports using a clinician-informed gazetteer methodology

Background Timely diagnosis and reporting of patient symptoms in hospital emergency departments (ED) is a critical component of health services delivery. However, due to dispersed information resources and a vast amount of manual processing of unstructured information, accurate point-of-care diagnosis is often difficult. Aims The aim of this research is to report initial experimental evaluation of a clinician-informed automated method for the issue of initial misdiagnoses associated with delayed receipt of unstructured radiology reports. Method A method was developed that resembles clinical reasoning for identifying limb abnormalities. The method consists of a gazetteer of keywords related to radiological findings; the method classifies an X-ray report as abnormal if it contains evidence contained in the gazetteer. A set of 99 narrative reports of radiological findings was sourced from a tertiary hospital. Reports were manually assessed by two clinicians and discrepancies were validated by a third expert ED clinician; the final manual classification generated by the expert ED clinician was used as ground truth to empirically evaluate the approach. Results The automated method that attempts to individuate limb abnormalities by searching for keywords expressed by clinicians achieved an F-measure of 0.80 and an accuracy of 0.80. Conclusion While the automated clinician-driven method achieved promising performances, a number of avenues for improvement were identified using advanced natural language processing (NLP) and machine learning techniques.

An orientation to early childhood education for sustainability and research : framing the text

This publication arose from the interests of the chapter authors, ‘a small group of thoughtful people’ almost all of whom participated in one or both Transnational Dialogues in Research in Early Childhood Education for Sustainability, held in Stavanger, Norway in 2010 and Brisbane, Australia in 2011 (Refer Appendix 1 for list of participants). These meetings were the first time that a critical mass of researchers from vastly different parts of the globe - Norway, Sweden, Australia and New Zealand at the inaugural meeting, with additional participants from Korea, Japan and Singapore attending the second - had come together to debate, discuss and share ideas about research and theory in the emerging field of Early Childhood Education for Sustainability (ECEfS. Some of the researchers who joined these Transnational Dialogues, had met serendipitously at earlier conferences and meetings, or corresponded via email, but many had never met face-to-face. Now a significant number are contributing authors in this text. It is a testament to these researchers’ interest in this agenda that they mostly self-funded their travel and other costs to attend the Transnational Dialogues research meetings. While most chapter authors come from the field of early childhood education, a few are more aligned with education for sustainability/environmental education, while a much smaller number are already working at the intersection of early childhood education and education for sustainability. What we share as a group is a range of perspectives and orientations to research and to the research focus at the heart of this book - young children and their actual and potential capabilities as agents of change for sustainability. As researchers, regardless of experience and perspectives, participants knew they had something extra to offer - their expertise as researchers - providing scholarly insights into the work of practitioners, applying critically reflective lenses to curricula, pedagogies and assumptions, testing of ideas and theories, and presenting a sense for where ECEfS might fit or, indeed, go beyond norms and orthodoxies. This is a text, then, for both researchers and those whose primary interests lie in daily interactions with children, families and communities.

Time, space, and text in the elementary school digital writing classroom

Theorists of multiliteracies, social semiotics, and the New Literacy Studies have drawn attention to the potential changing nature of writing and literacy in the context of networked communications. This article reports findings from a design-based research project in Year 4 classrooms (students aged 8.5-10 years) in a low socioeconomic status school. A new writing program taught students how to design multimodal and digital texts across a range of genres and text types, such as web pages, online comics, video documentaries, and blogs. The authors use Bernstein’s theory of the pedagogic device to theorize the pedagogic struggles and resolutions in remaking English through the specialization of time, space, and text. The changes created an ideological struggle as new writing practices were adapted from broader societal fields to meet the instructional and regulative discourses of a conventional writing curriculum.

Can a text message a week improve breastfeeding?

Background Breastfeeding is recognised as the optimal method for feeding infants with health gains made by reducing infectious diseases in infancy; and chronic diseases, including obesity, in childhood, adolescence and adulthood. Despite this, exclusivity and duration in developed countries remains resistant to improvement. The objectives of this research were to test if an automated mobile phone text messaging intervention, delivering one text message a week, could increase “any” breastfeeding rates and improve breastfeeding self-efficacy and coping. Methods Women were eligible to participate if they were: over eighteen years; had an infant less than three months old; were currently breastfeeding; no diagnosed mental illness; and used a mobile phone . Women in the intervention group received MumBubConnect, a text messaging service with automated responses delivered once a week for 8 weeks. Women in the comparison group received their usual care and were sampled two years after the intervention group. Data collection included online surveys at two time points, week zero and week nine, to measure breastfeeding exclusivity and duration, coping, emotions, accountability and self-efficacy. A range of statistical analyses were used to test for differences between groups. Hierarchical regression was used to investigate change in breastfeeding outcome, between groups, adjusting for co-variates. Results The intervention group had 120 participants at commencement and 114 at completion, the comparison group had 114 participants at commencement and 86 at completion. MumBubConnect had a positive impact on the primary outcome of breastfeeding behaviors with women receiving the intervention more likely to continue exclusive breastfeeding; with a 6% decrease in exclusive breastfeeding in the intervention group, compared to a 14% decrease in the comparison group (p < 0.001). This remained significant after controlling for infant age, mother’s income, education and delivery type (p = 0.04). Women in the intervention group demonstrated active coping and were less likely to display emotions-focussed coping (p < .001). There was no discernible statistical effect on self-efficacy or accountability. Conclusions A fully automated text messaging services appears to improve exclusive breastfeeding duration. The service provides a well-accepted, personalised support service that empowers women to actively resolve breastfeeding issues. Trial registration Australian New Zealand Clinical Trials Registry: ACTRN12614001091695.

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.