Hui an Chu

Developing a semantic-enable information retrieval mechanism

The existing information retrieval systems are mostly keyword-based and retrieve relevant documents or information by matching keywords. Keyword-based search, in spite of its merits of expedient query for information and ease-of-use, has failed to represent the complete semantics contained in the content and has let to the retrieval failure. In a textual content, the authors intention is represented in a semantic format of various combinations of word-word relations that are comprehensible to human beings. Query constructed by descriptions in natural language best reflects querists intention. This study developed a semantic-enable information retrieval mechanism that handles the processing, recognition, extraction, extensions and matching of content semantics to achieve the following objectives: (1) to analyze and determine the semantic features of content, to develop a semantic pattern that represents semantic features of the content, and to structuralize and materialize semantic features; (2) to analyze users query and extend its implied semantics through semantic extension so as to identify more semantic features for matching; and (3) to generate contents with approximate semantics by matching against the extended query to provide correct contents to the querist. This mechanism is capable of improving the traditional problem of keyword search and enables the user to perform a semantic-based query and search for the required information, thereby improving the reusing and sharing of information.

Electronic word of mouth analysis for service experience

Since eWOM provides a rich source of objective information about products or services, it has become one of the major ways in which consumers collect information about items they are interested in buying. However, the problem of eWOM overload makes it difficult to effectively collect this information, and may have adverse effects on their actual purchase behavior. eWOM content is characterized by unstructured text formats, oversimplified expressions, and newly coined phrases (textspeak), and these all contribute to the challenges that arise when analyzing eWOM. This study thus proposes an eWOM analysis method for analyzing eWOM, which may lead to a more effective method for analyzing eWOM content, extracting both positive and negative appraisals, and help consumers in their decision making. At the same time, the method proposed in this study can also be utilized as a tool to assist companies in better understanding product or service appraisals, thus translating these opinions into business intelligence and as the basis for product/service improvements.

Enhancement of domain ontology construction using a crystallizing approach

Research highlights? We proposed an automatic ontology construction mechanism. ? The quality of constructed ontology might not be as good as experts ontology. ? The constructed ontology can serve as an primitive ontology. ? The mechanism can accelerate the process of construction and reduce the time. An ontology is a representation model which defines domain knowledge with explicit specifications that feature interoperability between human and machine, thereby solving the problems of ambiguity and vagueness in knowledge sharing and reuse. Ontology construction is a lengthy, costly and controversial process. Hence, many studies in automatic ontology construction have emerged. In the processes of ontology construction, relations between concepts and the ways concepts are organized by their relations determine the ontology structure, which in turn affects the accuracy of domain knowledge. Consequently, concept relations exploration is the most important process of ontology construction. This study proposes a concept relation exploration approach that combines the characteristics of middle-out and top-down approaches in a process that resembles snowflakes crystallization. Based on the crystallizing concept exploration approach, this study implements an ontology construction mechanism that can automatically mine domain concepts out of domain document, determine relations between concept, and construct the domain ontology accordingly, thereby reducing cost and burden that would be incurred in a manual construction process.

Learning case adaptation for problem-oriented e-learning on mathematics teaching for students with mild disabilities

Both problem-oriented learning and case-based learning are effective methods for practical knowledge development. However, an automatic development of learning cases for adaptive learning is still an open issue. To support adaptive case-based learning in a proposed problem-oriented e-learning (POeL) environment and to address the complexity and diversity of the learning problems of students with mild disabilities, this study presents a learning case adaptation framework to support problem-oriented e-learning. This framework provides mechanisms to search and match similar learning cases according to encountered teaching problems by information retrieval techniques and to develop an adaptive learning case by adaptation techniques. Adaptation techniques include a substitution technique, a removal technique, and a composition technique, and utilize cosine-measure and genetic algorithm. In this research, adaptive learning cases were developed for teaching students with mild disabilities so as to assist regular and special education teachers to develop practical knowledge of teaching more effectively.

Ontology-based SWOT analysis method for electronic word-of-mouth

SWOT analysis highlights a companys strengths, weaknesses, opportunities and threats by addressing internal and external factors affecting the enterprise. Although traditionally it is a tools used by management, they are likely to hold biased views, thus tampers result of the analysis. Therefore, yow to effectively conduct more effective SWOT analyses has become an important task for modern enterprises. eWOM appraisals are one form of consumer opinions, and include information a firms brand, as well as the strengths, weaknesses, opportunities, and threats (SWOT) that exist with regard to its products or services. Through the use of eWOM appraisals, it is expected that a SWOT analysis may be more objective and provide enterprises with more accurate information to carry out more effective strategic planning. Therefore, this study develops an ontology-based SWOT analysis mechanism that can reveal the information structure of eWOM appraisals, and thus the strengths, weaknesses, opportunities, and threats of an enterprise. This approach can be an effective tool for strategic planning. Specifically,, this study has the following aims: (i) designing an eWOM management framework; (ii) constructing an ontology-based SWOT analysis model; (iii) providing an ontology-based SWOT analysis method; and (iv) developing an ontology-based SWOT analysis mechanism for eWOM. The results of this study were verified using questionnaires, which showed that this approach can be effective in assisting managers in their making strategic planning.

Enhancement of information seeking using an information needs radar model

Information seeking is the act of obtaining information from existing resources in both human and technological contexts, and past studies have applied the behavior of users to determine the user needs. Search engines, information retrieval, and recommendation systems are the major solutions of information seeking. However, these techniques lack a description method for overall information needs and other limitations. Information seeking behavior is related to the content and concepts in content, and this study proposes an information needs radar model, which consists of users, content and concepts to describe information needs. The information seeking architecture based on this model is used to evaluate and obtain information about users needs. The experimental results indicated that our proposed architecture has stable and better performance irrespective of data size, which demonstrates the applicability and effectiveness of the architecture. Furthermore, the information needs the radar model to be able to satisfy customer demands; it is not only helpful in the development of information filtering, recommendation systems, and knowledge-based systems, but also enhances the reliance and loyalty of users towards the system.

The effectiveness of image features based on fractal image coding for image annotation

Image annotation is a process of assigning metadata to digital images in the form of captions or keywords, and has been regarded as image management and one of the most crucial processes of image retrieval. And many automatic methods have been proposed. However, these methods still have some problems respectively. Fractals are fragmented geometries and can be considered separate parts; each part is similar to the contracted overall shape. Fractal features provide geometric information of an image that is irrelevant to the shape and size of an object in the image; therefore, fractal features are more robust than color and texture features. Therefore, this study proposed a fractal-driven image annotation (FIA) schema that extracts fractal features through fractal image coding and integrates color and texture as new visual features to conduct image-based annotation. Experimental results indicate that the effect of thresholds on annotating accuracy is insignificant. This finding supports the application of FIA on complex practical environments, reduces the time for identifying the optimal thresholds, and improves the practicality of using FIA in real environments.

Image completion using prediction concept via support vector regression

Image completion is a widely used method for automatically removing objects or repairing the damaged portions of an image. However, information of the original image is often lacking in reconstructed structures; therefore, images with complex structures are difficult to restore. This study proposes a prediction-oriented image completion mechanism (PICM), which applies the prediction concept to image completion using numerous techniques and methods. The experiment results indicate that under normal circumstances, our PICM not only produces good inpainting quality but it is also easy to use.

Facial emotion recognition with transition detection for students with high-functioning autism in adaptive e-learning

Emotions deeply affect learning achievement. In the case of students with high-functioning autism (HFA), negative emotions such as anxiety and anger can impair the learning process due to the inability of these individuals to control their emotions. Attempts to regulate negative emotions in HFA students once they have occurred, subsequent regulation to HFA students is often ineffective because it is difficult to calm them down. Hence, detecting emotional transitions and providing adaptive emotional regulation strategies in a timely manner to regulate negative emotions can be especially important for students with HFA in an e-learning environment. In this study, a facial expression-based emotion recognition method with transition detection was proposed. An emotion elicitation experiment was performed to collect facial-based landmark signals for the purpose of building classifiers of emotion recognition. The proposed method used sliding window technique and support vector machine (SVM) to build classifiers in order to recognize emotions. For the purpose of determining robust features for emotion recognition, Information Gain (IG) and Chi-square were used for feature evaluations. The effectiveness of classifiers with different parameters of sliding windows was also examined. The experimental results confirmed that the proposed method has sufficient discriminatory capability. The recognition rates for basic emotions and transitional emotions were 99.13 and 92.40%, respectively. Also, through feature selection, training time was accelerated by 4.45 times, and the recognition rates for basic emotions and transitional emotions were 97.97 and 87.49%, respectively. The method was applied in an adaptive e-learning environment for mathematics to demonstrate its application effectiveness.