Automatic domain ontology extraction for context-sensitive opinion mining

Automated analysis of the sentiments presented in online consumer feedbacks can facilitate both organizations’ business strategy development and individual consumers’ comparison shopping. Nevertheless, existing opinion mining methods either adopt a context-free sentiment classification approach or rely on a large number of manually annotated training examples to perform context sensitive sentiment classification. Guided by the design science research methodology, we illustrate the design, development, and evaluation of a novel fuzzy domain ontology based contextsensitive opinion mining system. Our novel ontology extraction mechanism underpinned by a variant of Kullback-Leibler divergence can automatically acquire contextual sentiment knowledge across various product domains to improve the sentiment analysis processes. Evaluated based on a benchmark dataset and real consumer reviews collected from Amazon.com, our system shows remarkable performance improvement over the context-free baseline.

A context sensitive model for querying linked scientific data

This thesis provides a query model suitable for context sensitive access to a wide range of distributed linked datasets which are available to scientists using the Internet. The model is designed based on scientific research standards which require scientists to provide replicable methods in their publications. Although there are query models available that provide limited replicability, they do not contextualise the process whereby different scientists select dataset locations based on their trust and physical location. In different contexts, scientists need to perform different data cleaning actions, independent of the overall query, and the model was designed to accommodate this function. The query model was implemented as a prototype web application and its features were verified through its use as the engine behind a major scientific data access site, Bio2RDF.org. The prototype showed that it was possible to have context sensitive behaviour for each of the three mirrors of Bio2RDF.org using a single set of configuration settings. The prototype provided executable query provenance that could be attached to scientific publications to fulfil replicability requirements. The model was designed to make it simple to independently interpret and execute the query provenance documents using context specific profiles, without modifying the original provenance documents. Experiments using the prototype as the data access tool in workflow management systems confirmed that the design of the model made it possible to replicate results in different contexts with minimal additions, and no deletions, to query provenance documents.

Context-sensitive evaluation: Determining the context surrounding the implementation of a government policy

This article explains the essence of the context-sensitive parameters and dimensions in play at the time of an intervention, through the application of Rog’s (2012) model of contextual parameters. Rog’s model offers evaluators a structured approach to examine an intervention. The initial study provided a systematic way to clarify the scope, variables, timing, and appropriate evaluation methodology to evaluate the implementation of a government policy. Given that the government implementation of an educational intervention under study did not follow the experimental research approach, nor the double cycle of action research approach, the application of Rog’s model provided an in-depth understanding of the context-sensitive environment; it is from this clear purpose that the broader evaluation was conducted. Overall, when governments or institutions implement policy to invoke educational change (and this intervention is not guided by an appropriate evaluation approach), then program evaluation is achievable post-implementation. In this situation, Rog’s (2012) model of contextual parameters is a useful way to achieve clarity of purpose to guide the program evaluation.

The Temporal Landscape of Residential Aged Care Facilities – Implications for Context-Sensitive Health Technology

Health information technology (IT) can have a profound effect on the temporal flow and organisation of work. Yet research into the context, meaning and significance of temporal factors remains limited, most likely because of its complexity. This study outlines the role of communications in the context of the temporal and organizational landscape of seven Australian residential aged care facilities displaying a range of information exchange practices and health IT capacity. The study used qualitative and observational methods to identify temporal factors associated with internal and external modes of communication across the facilities and to explore the use of artifacts. The study concludes with a depiction of the temporal landscape of residential aged care particularly in regards to the way that work is allocated, prioritized, sequenced and coordinated. We argue that the temporal landscape involves key context-sensitive factors that are critical to understanding the way that humans accommodate to, and deal with health technologies, and which are therefore important for the delivery of safe and effective care.

Generation in context : an exploratory method for musical enquiry

This paper discusses a method, Generation in Context, for interrogating theories of music analysis and music perception. Given an analytic theory, the method consists of creating a generative process that implements the theory in reverse. Instead of using the theory to create analyses from scores, the theory is used to generate scores from analyses. Subjective evaluation of the quality of the musical output provides a mechanism for testing the theory in a contextually robust fashion. The method is exploratory, meaning that in addition to testing extant theories it provides a general mechanism for generating new theoretical insights. We outline our initial explorations in the use of generative processes for music research, and we discuss how generative processes provide evidence as to the veracity of theories about how music is experienced, with insights into how these theories may be improved and, concurrently, provide new techniques for music creation. We conclude that Generation in Context will help reveal new perspectives on our understanding of music.

Data preprocessing for anomaly based network intrusion detection : a review

Data preprocessing is widely recognized as an important stage in anomaly detection. This paper reviews the data preprocessing techniques used by anomaly-based network intrusion detection systems (NIDS), concentrating on which aspects of the network traffic are analyzed, and what feature construction and selection methods have been used. Motivation for the paper comes from the large impact data preprocessing has on the accuracy and capability of anomaly-based NIDS. The review finds that many NIDS limit their view of network traffic to the TCP/IP packet headers. Time-based statistics can be derived from these headers to detect network scans, network worm behavior, and denial of service attacks. A number of other NIDS perform deeper inspection of request packets to detect attacks against network services and network applications. More recent approaches analyze full service responses to detect attacks targeting clients. The review covers a wide range of NIDS, highlighting which classes of attack are detectable by each of these approaches. Data preprocessing is found to predominantly rely on expert domain knowledge for identifying the most relevant parts of network traffic and for constructing the initial candidate set of traffic features. On the other hand, automated methods have been widely used for feature extraction to reduce data dimensionality, and feature selection to find the most relevant subset of features from this candidate set. The review shows a trend toward deeper packet inspection to construct more relevant features through targeted content parsing. These context sensitive features are required to detect current attacks.

Exploring the opportunities and challenges of using mobile sensing for gamification and achievements

Gamified services delivered on smart phones, such as Foursquare, are able to utilise the sensors on the phone to capture user contexts as a means of triggering game elements. This paper identifies and discusses opportunities and challenges that exist when using mobile sensors as input for game elements. We present initial findings from a field study of a gamified mobile application made to support the university orientation event for new students using game achievements. The study showed that overall the use of context was well received by participants when compared to game elements that required no context to complete. It was also found that using context could help validate that an activity was completed however there were still technical challenges when using sensors that led to exploits in the game elements, or cheating.

An aspect query language model based on query decomposition and high-order contextual term associations

In information retrieval (IR) research, more and more focus has been placed on optimizing a query language model by detecting and estimating the dependencies between the query and the observed terms occurring in the selected relevance feedback documents. In this paper, we propose a novel Aspect Language Modeling framework featuring term association acquisition, document segmentation, query decomposition, and an Aspect Model (AM) for parameter optimization. Through the proposed framework, we advance the theory and practice of applying high-order and context-sensitive term relationships to IR. We first decompose a query into subsets of query terms. Then we segment the relevance feedback documents into chunks using multiple sliding windows. Finally we discover the higher order term associations, that is, the terms in these chunks with high degree of association to the subsets of the query. In this process, we adopt an approach by combining the AM with the Association Rule (AR) mining. In our approach, the AM not only considers the subsets of a query as “hidden” states and estimates their prior distributions, but also evaluates the dependencies between the subsets of a query and the observed terms extracted from the chunks of feedback documents. The AR provides a reasonable initial estimation of the high-order term associations by discovering the associated rules from the document chunks. Experimental results on various TREC collections verify the effectiveness of our approach, which significantly outperforms a baseline language model and two state-of-the-art query language models namely the Relevance Model and the Information Flow model

The role of human factors when evaluating information accountability for eHealth systems

The availability of health information is rapidly increasing; its expansion and proliferation is inevitable. At the same time, breeding of health information silos is an unstoppable and relentless exercise. Information security and privacy concerns are therefore major barriers in the eHealth socio-eco system. We proposed Information Accountability as a measurable human factor that should eliminate and mitigate security concerns. Information accountability measures would be practicable and feasible if legislative requirements are also embedded. In this context, information accountability constitutes a key component for the development of effective information technology requirements for health information system. Our conceptual approach to measuring human factors related to information accountability in eHealth is presented in this paper with some limitations.

Information organisation behaviours within everyday life : an exploration using the diary method

This paper presents the results from a study of information behaviours (IB), with specific focus on information- organisation-related behaviours conducted as part of a larger daily diary study with 40 participants. The findings indicate that organisation of information in everyday life is problematic due to various factors, specifically temporal and spatial ones, i.e., the passage of time, along with the difference in the physical environment between when the information was organised and when the information is retrieved. These have implications for information organisation schemas, and point toward the need for a context-sensitive model of information organisation that reflects the relation between information objects, information representation, and information users.

Navigating emotion research during a paradigm shift in psychology

Human emotional responses are highly individual. A comprehensive analysis of emotion research in cognitive psychology and physiology, including laboratory-based experiments, showed that understanding human emotions requires a dynamic systems approach incorporating insights from scientific disciplines beyond psychology. Importantly, subjective and automatic evaluations of emotive information are context-sensitive and changeable, confirming the dynamic nature of emotion and role of individual differences. Furthermore, a comparison of different statistical approaches established that statistical estimation, rather than averages, best captures our highly individual emotional responses. Emotion research needs a cross-disciplinary approach.