Personalised ontology learning and mining for web information gathering

Over the last decade, the rapid growth and adoption of the World Wide Web has further exacerbated user needs for e±cient mechanisms for information and knowledge location, selection, and retrieval. How to gather useful and meaningful information from the Web becomes challenging to users. The capture of user information needs is key to delivering users' desired information, and user pro¯les can help to capture information needs. However, e®ectively acquiring user pro¯les is di±cult. It is argued that if user background knowledge can be speci¯ed by ontolo- gies, more accurate user pro¯les can be acquired and thus information needs can be captured e®ectively. Web users implicitly possess concept models that are obtained from their experience and education, and use the concept models in information gathering. Prior to this work, much research has attempted to use ontologies to specify user background knowledge and user concept models. However, these works have a drawback in that they cannot move beyond the subsumption of super - and sub-class structure to emphasising the speci¯c se- mantic relations in a single computational model. This has also been a challenge for years in the knowledge engineering community. Thus, using ontologies to represent user concept models and to acquire user pro¯les remains an unsolved problem in personalised Web information gathering and knowledge engineering. In this thesis, an ontology learning and mining model is proposed to acquire user pro¯les for personalised Web information gathering. The proposed compu- tational model emphasises the speci¯c is-a and part-of semantic relations in one computational model. The world knowledge and users' Local Instance Reposito- ries are used to attempt to discover and specify user background knowledge. From a world knowledge base, personalised ontologies are constructed by adopting au- tomatic or semi-automatic techniques to extract user interest concepts, focusing on user information needs. A multidimensional ontology mining method, Speci- ¯city and Exhaustivity, is also introduced in this thesis for analysing the user background knowledge discovered and speci¯ed in user personalised ontologies. The ontology learning and mining model is evaluated by comparing with human- based and state-of-the-art computational models in experiments, using a large, standard data set. The experimental results are promising for evaluation. The proposed ontology learning and mining model in this thesis helps to develop a better understanding of user pro¯le acquisition, thus providing better design of personalised Web information gathering systems. The contributions are increasingly signi¯cant, given both the rapid explosion of Web information in recent years and today's accessibility to the Internet and the full text world.

A Personalized Ontology Model for Web Information Gathering

As a model for knowledge description and formalization, ontologies are widely used to represent user profiles in personalized web information gathering. However, when representing user profiles, many models have utilized only knowledge from either a global knowledge base or a user local information. In this paper, a personalized ontology model is proposed for knowledge representation and reasoning over user profiles. This model learns ontological user profiles from both a world knowledge base and user local instance repositories. The ontology model is evaluated by comparing it against benchmark models in web information gathering. The results show that this ontology model is successful.

Loculus : an ontology-based information management framework for the motion picture industry

"How do you film a punch?" This question can be posed by actors, make-up artists, directors and cameramen. Though they can all ask the same question, they are not all seeking the same answer. Within a given domain, based on the roles they play, agents of the domain have different perspectives and they want the answers to their question from their perspective. In this example, an actor wants to know how to act when filming a scene involving a punch. A make-up artist is interested in how to do the make-up of the actor to show bruises that may result from the punch. Likewise, a director wants to know how to direct such a scene and a cameraman is seeking guidance on how best to film such a scene. This role-based difference in perspective is the underpinning of the Loculus framework for information management for the Motion Picture Industry. The Loculus framework exploits the perspective of agent for information extraction and classification within a given domain. The framework uses the positioning of the agent’s role within the domain ontology and its relatedness to other concepts in the ontology to determine the perspective of the agent. Domain ontology had to be developed for the motion picture industry as the domain lacked one. A rule-based relatedness score was developed to calculate the relative relatedness of concepts with the ontology, which were then used in the Loculus system for information exploitation and classification. The evaluation undertaken to date have yielded promising results and have indicated that exploiting perspective can lead to novel methods of information extraction and classifications.

Towards semantic search and inference in electronic medical records : an approach using concept-based information retrieval

Background This paper presents a novel approach to searching electronic medical records that is based on concept matching rather than keyword matching. Aim The concept-based approach is intended to overcome specific challenges we identified in searching medical records. Method Queries and documents were transformed from their term-based originals into medical concepts as defined by the SNOMED-CT ontology. Results Evaluation on a real-world collection of medical records showed our concept-based approach outperformed a keyword baseline by 25% in Mean Average Precision. Conclusion The concept-based approach provides a framework for further development of inference based search systems for dealing with medical data.

Exploiting medical hierarchies for concept-based information retrieval

Search technologies are critical to enable clinical sta to rapidly and e ectively access patient information contained in free-text medical records. Medical search is challenging as terms in the query are often general but those in rel- evant documents are very speci c, leading to granularity mismatch. In this paper we propose to tackle granularity mismatch by exploiting subsumption relationships de ned in formal medical domain knowledge resources. In symbolic reasoning, a subsumption (or `is-a') relationship is a parent-child rela- tionship where one concept is a subset of another concept. Subsumed concepts are included in the retrieval function. In addition, we investigate a number of initial methods for combining weights of query concepts and those of subsumed concepts. Subsumption relationships were found to provide strong indication of relevant information; their inclusion in retrieval functions yields performance improvements. This result motivates the development of formal models of rela- tionships between medical concepts for retrieval purposes.

AEHRC & QUT at TREC 2011 Medical Track : a concept-based information retrieval approach

The Australian e-Health Research Centre and Queensland University of Technology recently participated in the TREC 2011 Medical Records Track. This paper reports on our methods, results and experience using a concept-based information retrieval approach. Our concept-based approach is intended to overcome specific challenges we identify in searching medical records. Queries and documents are transformed from their term-based originals into medical concepts as de ned by the SNOMED-CT ontology. Results show our concept-based approach performed above the median in all three performance metrics: bref (+12%), R-prec (+18%) and Prec@10 (+6%).

Mining specific features for acquiring user information needs

Term-based approaches can extract many features in text documents, but most include noise. Many popular text-mining strategies have been adapted to reduce noisy information from extracted features; however, text-mining techniques suffer from low frequency. The key issue is how to discover relevance features in text documents to fulfil user information needs. To address this issue, we propose a new method to extract specific features from user relevance feedback. The proposed approach includes two stages. The first stage extracts topics (or patterns) from text documents to focus on interesting topics. In the second stage, topics are deployed to lower level terms to address the low-frequency problem and find specific terms. The specific terms are determined based on their appearances in relevance feedback and their distribution in topics or high-level patterns. We test our proposed method with extensive experiments in the Reuters Corpus Volume 1 dataset and TREC topics. Results show that our proposed approach significantly outperforms the state-of-the-art models.

Adaptive dual control of topic-based information retrieval

Information Retrieval is an important albeit imperfect component of information technologies. A problem of insufficient diversity of retrieved documents is one of the primary issues studied in this research. This study shows that this problem leads to a decrease of precision and recall, traditional measures of information retrieval effectiveness. This thesis presents an adaptive IR system based on the theory of adaptive dual control. The aim of the approach is the optimization of retrieval precision after all feedback has been issued. This is done by increasing the diversity of retrieved documents. This study shows that the value of recall reflects this diversity. The Probability Ranking Principle is viewed in the literature as the “bedrock” of current probabilistic Information Retrieval theory. Neither the proposed approach nor other methods of diversification of retrieved documents from the literature conform to this principle. This study shows by counterexample that the Probability Ranking Principle does not in general lead to optimal precision in a search session with feedback (for which it may not have been designed but is actively used). Retrieval precision of the search session should be optimized with a multistage stochastic programming model to accomplish the aim. However, such models are computationally intractable. Therefore, approximate linear multistage stochastic programming models are derived in this study, where the multistage improvement of the probability distribution is modelled using the proposed feedback correctness method. The proposed optimization models are based on several assumptions, starting with the assumption that Information Retrieval is conducted in units of topics. The use of clusters is the primary reasons why a new method of probability estimation is proposed. The adaptive dual control of topic-based IR system was evaluated in a series of experiments conducted on the Reuters, Wikipedia and TREC collections of documents. The Wikipedia experiment revealed that the dual control feedback mechanism improves precision and S-recall when all the underlying assumptions are satisfied. In the TREC experiment, this feedback mechanism was compared to a state-of-the-art adaptive IR system based on BM-25 term weighting and the Rocchio relevance feedback algorithm. The baseline system exhibited better effectiveness than the cluster-based optimization model of ADTIR. The main reason for this was insufficient quality of the generated clusters in the TREC collection that violated the underlying assumption.

The evidence-based development of an intervention to address the information needs of adults newly diagnosed with primary brain tumours and their carers

Adults diagnosed with primary brain tumours often experience physical, cognitive and neuropsychiatric impairments and decline in quality of life. Although disease and treatment-related information is commonly provided to cancer patients and carers, newly diagnosed brain tumour patients and their carers report unmet information needs. Few interventions have been designed or proven to address these information needs. Accordingly, a three-study research program, that incorporated both qualitative and quantitative research methods, was designed to: 1) identify and select an intervention to improve the provision of information, and meet the needs of patients with a brain tumour; 2) use an evidence-based approach to establish the content, language and format for the intervention; and 3) assess the acceptability of the intervention, and the feasibility of evaluation, with newly diagnosed brain tumour patients. Study 1: Structured concept mapping techniques were undertaken with 30 health professionals, who identified strategies or items for improving care, and rated each of 42 items for importance, feasibility, and the extent to which such care was provided. Participants also provided data to interpret the relationship between items, which were translated into ‘maps’ of relationships between information and other aspects of health care using multidimensional scaling and hierarchical cluster analysis. Results were discussed by participants in small groups and individual interviews to understand the ratings, and facilitators and barriers to implementation. A care coordinator was rated as the most important strategy by health professionals. Two items directly related to information provision were also seen as highly important: "information to enable the patient or carer to ask questions" and "for doctors to encourage patients to ask questions". Qualitative analyses revealed that information provision was individualised, depending on patients’ information needs and preferences, demographic variables and distress, the characteristics of health professionals who provide information, the relationship between the individual patient and health professional, and influenced by the fragmented nature of the health care system. Based on quantitative and qualitative findings, a brain tumour specific question prompt list (QPL) was chosen for development and feasibility testing. A QPL consists of a list of questions that patients and carers may want to ask their doctors. It is designed to encourage the asking of questions in the medical consultation, allowing patients to control the content, and amount of information provided by health professionals. Study 2: The initial structure and content of the brain tumour specific QPL developed was based upon thematic analyses of 1) patient materials for brain tumour patients, 2) QPLs designed for other patient populations, and 3) clinical practice guidelines for the psychosocial care of glioma patients. An iterative process of review and refinement of content was undertaken via telephone interviews with a convenience sample of 18 patients and/or carers. Successive drafts of QPLs were sent to patients and carers and changes made until no new topics or suggestions arose in four successive interviews (saturation). Once QPL content was established, readability analyses and redrafting were conducted to achieve a sixth-grade reading level. The draft QPL was also reviewed by eight health professionals, and shortened and modified based on their feedback. Professional design of the QPL was conducted and sent to patients and carers for further review. The final QPL contained questions in seven colour-coded sections: 1) diagnosis; 2) prognosis; 3) symptoms and problems; 4) treatment; 5) support; 6) after treatment finishes; and 7) the health professional team. Study 3: A feasibility study was conducted to determine the acceptability of the QPL and the appropriateness of methods, to inform a potential future randomised trial to evaluate its effectiveness. A pre-test post-test design was used with a nonrandomised control group. The control group was provided with ‘standard information’, the intervention group with ‘standard information’ plus the QPL. The primary outcome measure was acceptability of the QPL to participants. Twenty patients from four hospitals were recruited a median of 1 month (range 0-46 months) after diagnosis, and 17 completed baseline and follow-up interviews. Six participants would have preferred to receive the information booklet (standard information or QPL) at a different time, most commonly at diagnosis. Seven participants reported on the acceptability of the QPL: all said that the QPL was helpful, and that it contained questions that were useful to them; six said it made it easier to ask questions. Compared with control group participants’ ratings of ‘standard information’, QPL group participants’ views of the QPL were more positive; the QPL had been read more times, was less likely to be reported as ‘overwhelming’ to read, and was more likely to prompt participants to ask questions of their health professionals. The results from the three studies of this research program add to the body of literature on information provision for brain tumour patients. Together, these studies suggest that a QPL may be appropriate for the neuro-oncology setting and acceptable to patients. The QPL aims to assist patients to express their information needs, enabling health professionals to better provide the type and amount of information that patients need to prepare for treatment and the future. This may help health professionals meet the challenge of giving patients sufficient information, without providing ‘too much’ or ‘unnecessary’ information, or taking away hope. Future studies with rigorous designs are now needed to determine the effectiveness of the QPL.

Towards semantic search and inference in electronic medical records : an approach using concept-based information retrieval

For more than a decade research in the field of context aware computing has aimed to find ways to exploit situational information that can be detected by mobile computing and sensor technologies. The goal is to provide people with new and improved applications, enhanced functionality and better use experience (Dey, 2001). Early applications focused on representing or computing on physical parameters, such as showing your location and the location of people or things around you. Such applications might show where the next bus is, which of your friends is in the vicinity and so on. With the advent of social networking software and microblogging sites such as Facebook and Twitter, recommender systems and so on context-aware computing is moving towards mining the social web in order to provide better representations and understanding of context, including social context. In this paper we begin by recapping different theoretical framings of context. We then discuss the problem of context- aware computing from a design perspective.

Reorganizing a technical services division using collaborative evidence based information practice at Auraria Library

The article focuses on the evidence-based information practice (EBIP) applied at the Auraria Library in Denver, Colorado during the reorganization of its technical services division. Collaboration processes were established for the technical services division through the reorganization and redefinition of workflows. There are several factors that form part of the redefinition of roles including personal interests, department needs, and library needs. A collaborative EBIP environment was created in the division by addressing issues of workplace hierarchies, by the distribution of problem solving, and by the encouragement of reflective dialogue.