Relevance feature discovery for text mining

It is a big challenge to guarantee the quality of discovered relevance features in text documents for describing user preferences because of large scale terms and data patterns. Most existing popular text mining and classification methods have adopted term-based approaches. However, they have all suffered from the problems of polysemy and synonymy. Over the years, there has been often held the hypothesis that pattern-based methods should perform better than term-based ones in describing user preferences; yet, how to effectively use large scale patterns remains a hard problem in text mining. To make a breakthrough in this challenging issue, this paper presents an innovative model for relevance feature discovery. It discovers both positive and negative patterns in text documents as higher level features and deploys them over low-level features (terms). It also classifies terms into categories and updates term weights based on their specificity and their distributions in patterns. Substantial experiments using this model on RCV1, TREC topics and Reuters-21578 show that the proposed model significantly outperforms both the state-of-the-art term-based methods and the pattern based methods.

Text mining for screening efficiency? Testing within a Cochrane public health review

Background The requirement for dual screening of titles and abstracts to select papers to examine in full text can create a huge workload, not least when the topic is complex and a broad search strategy is required, resulting in a large number of results. An automated system to reduce this burden, while still assuring high accuracy, has the potential to provide huge efficiency savings within the review process. Objectives To undertake a direct comparison of manual screening with a semi‐automated process (priority screening) using a machine classifier. The research is being carried out as part of the current update of a population‐level public health review. Methods Authors have hand selected studies for the review update, in duplicate, using the standard Cochrane Handbook methodology. A retrospective analysis, simulating a quasi‐‘active learning’ process (whereby a classifier is repeatedly trained based on ‘manually’ labelled data) will be completed, using different starting parameters. Tests will be carried out to see how far different training sets, and the size of the training set, affect the classification performance; i.e. what percentage of papers would need to be manually screened to locate 100% of those papers included as a result of the traditional manual method. Results From a search retrieval set of 9555 papers, authors excluded 9494 papers at title/abstract and 52 at full text, leaving 9 papers for inclusion in the review update. The ability of the machine classifier to reduce the percentage of papers that need to be manually screened to identify all the included studies, under different training conditions, will be reported. Conclusions The findings of this study will be presented along with an estimate of any efficiency gains for the author team if the screening process can be semi‐automated using text mining methodology, along with a discussion of the implications for text mining in screening papers within complex health reviews.

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.

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.

Relevance feature discovery for text analysis

It is a big challenge to guarantee the quality of discovered relevance features in text documents for describing user preferences because of the large number of terms, patterns, and noise. Most existing popular text mining and classification methods have adopted term-based approaches. However, they have all suffered from the problems of polysemy and synonymy. Over the years, people have often held the hypothesis that pattern-based methods should perform better than term- based ones in describing user preferences, but many experiments do not support this hypothesis. This research presents a promising method, Relevance Feature Discovery (RFD), for solving this challenging issue. It discovers both positive and negative patterns in text documents as high-level features in order to accurately weight low-level features (terms) based on their specificity and their distributions in the high-level features. The thesis also introduces an adaptive model (called ARFD) to enhance the exibility of using RFD in adaptive environment. ARFD automatically updates the system's knowledge based on a sliding window over new incoming feedback documents. It can efficiently decide which incoming documents can bring in new knowledge into the system. Substantial experiments using the proposed models on Reuters Corpus Volume 1 and TREC topics show that the proposed models significantly outperform both the state-of-the-art term-based methods underpinned by Okapi BM25, Rocchio or Support Vector Machine and other pattern-based methods.

Scoring-thresholding pattern based text classifier

A big challenge for classification on text is the noisy of text data. It makes classification quality low. Many classification process can be divided into two sequential steps scoring and threshold setting (thresholding). Therefore to deal with noisy data problem, it is important to describe positive feature effectively scoring and to set a suitable threshold. Most existing text classifiers do not concentrate on these two jobs. In this paper, we propose a novel text classifier with pattern-based scoring that describe positive feature effectively, followed by threshold setting. The thresholding is based on score of training set, make it is simple to implement in other scoring methods. Experiment shows that our pattern-based classifier is promising.

Mapping semantic knowledge for unsupervised text categorisation

Text categorisation is challenging, due to the complex structure with heterogeneous, changing topics in documents. The performance of text categorisation relies on the quality of samples, effectiveness of document features, and the topic coverage of categories, depending on the employing strategies; supervised or unsupervised; single labelled or multi-labelled. Attempting to deal with these reliability issues in text categorisation, we propose an unsupervised multi-labelled text categorisation approach that maps the local knowledge in documents to global knowledge in a world ontology to optimise categorisation result. The conceptual framework of the approach consists of three modules; pattern mining for feature extraction; feature-subject mapping for categorisation; concept generalisation for optimised categorisation. The approach has been promisingly evaluated by compared with typical text categorisation methods, based on the ground truth encoded by human experts.

A pattern based two-stage text classifier

In a classification problem typically we face two challenging issues, the diverse characteristic of negative documents and sometimes a lot of negative documents that are closed to positive documents. Therefore, it is hard for a single classifier to clearly classify incoming documents into classes. This paper proposes a novel gradual problem solving to create a two-stage classifier. The first stage identifies reliable negatives (negative documents with weak positive characteristics). It concentrates on minimizing the number of false negative documents (recall-oriented). We use Rocchio, an existing recall based classifier, for this stage. The second stage is a precision-oriented “fine tuning”, concentrates on minimizing the number of false positive documents by applying pattern (a statistical phrase) mining techniques. In this stage a pattern-based scoring is followed by threshold setting (thresholding). Experiment shows that our statistical phrase based two-stage classifier is promising.

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.

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.