No description available.

No description available.

No description available.

No description available.

No description available.

This thesis introduces a new approach to designing a Message Handling Assistant (MA). It presents a model of an MA and an intention extraction function for text messages, such as emails and Newsgroups articles. Based on a speech act theory and the belief-desire-intention (BDI) theory of rational agency, we define a generic MA. By interpreting intuitive descriptions of the desired behaviours of an MA using the BDI theory and speech act theory, we conjecture that intentions of messages alone provide enough information needed to capture user models and to reason how messages should be processed. To identify intentions of messages written in natural language, we develop a model of an intention extraction function that maps messages to intentions. This function is modelled in two steps. First, each sentence in a message is converted into a tuple (performative, proposition) using a dialogue act classifier. Second, the sender's intentions are formulated from the tuples using constraints for felicitous human communication. As an investigation of the use of machine learning technologies for designing the intention extraction function, four dialog act classifiers are implemented and evaluated on Newsgroups articles. The thesis also proposes a semantic communication framework, which integrates the agent and Internet technologies for automatic message composing and ontology exchange services.

The tremendous growth of information on the Internet has been above our ability to process. A recommender system, which filters out useful information and generate recommendations, has been introduced to help users overcome the information overload problem and has been widely applied in an ever-increasing number of e-commercial websites. Collaborative filtering and content-based recommendation methods are two major approaches used in recommender systems. The collaborative filtering predicts items which a particular user prefers by using a database about the past preferences of users with similar interests. The content-based method analyses the content of the objects to generate a representative list of the user’s interests, and then compares the similarity of item descriptions. These two methods have some drawbacks in dealing with situations such as sparse data and cold start problems. Recently, hybrid methods combining collaborative filtering and content-based methods have been proposed to overcome these limitations. However, personalized recommender system attempt to penetrate people’s various demand and generate the tailored recommendations. A highly effective and personalised recommender system may still face new challenges including interestdrifting and multicriteria optimisation. For example, a user’s interest may change over time. They may no longer like a item which was strongly preferred. Another example is that a person’s preference is varying and always has multiple criteria. Classic collaborative filtering uses a single overall rating for prediction. It does not properly reflect the opinion on a item and the reason why people rated this item high or low. Unfortunately, the current recommender systems do not consider these important factors. First, we proposed a novel hybrid recommender system to overcome interest-drifting by embedding the time-sensitive functions into the recommendation process. The experimental results show that the intergraded approach with interest-drifting can constantly perform better and provide users with higher quality recommendations. Meanwhile, the experimental results on different size of training dataset show that our algorithm can boost the prediction accuracy for all configurations. The contributions of this proposed algorithm are in two main aspects. First, using time function to reflect users’ intersts changing in order to achieve higher quality of recommendations. Second, using intergraded methods to solve some problems such as sparsity and cold start. Then we developed a new technique to aggregate the multicriteria ratings for predicting more accurate recommendations. The results show that our algorithms outperforms the traditional collaborative filtering recommender system on both accuracy of predicting ratings and accuracy of recommendations. The one of contributions in this proposed method is that we introduced the multicriteria concept into recommender systems to reflect the users’ opinion more accurate. Another contribution is that we develop a linear method to aggregate multicriteria to single rating for higher quality of recommendations. Our experiments demonstrate that the recommendation achieved better performances when interest-drifting and multicriteria ratings were considered. The significance of our research study is that we consider incorporating interest-drifting, and multicriteria ratings into a recommender system to generate personalised and effective recommendations.

This research focuses on developing a series of mobile learning applications for future 'beyond' classroom learning environments. The thesis describes the general use pattern of the prototype and explores the key factors that could affect users‘ attitudes towards potential acceptance of the mobile learning applications. Finally, this thesis explores the user acceptance of the mobile learning applications; and investigates the mobility issue and the comparison of applying learning activities through mobile learning and e-learning.

A multiplatform e-learning system is an e-learning system that can deliver learning content to different accessing devices such as PCs, PDAs and mobile phones. The main objective of the research is to formulate a framework for multiplatform e-learning systems. This thesis focuses on the formulation, competency and constitution of the multiplatform e-learning systems framework and the implementation of a multiplatform e-learning system. In conjunction with the main objective, the research also addresses the factors that influence learner satisfaction during their engagement with a multiplatform e-learning system. In addition, the research investigates the relationships between these factors in influencing learner satisfaction. The research also intends to validate the assertion that multiplatform e-learning systems are better than non-adaptive e-learning systems. A comparative evaluation between a traditional e-learning system and a multiplatform e-learning system from end user (learner) perspective was conducted. The evaluation instrument is based on multiplatform e-learning system questionnaires (MELQ). A total of forty participants took part in the evaluation. Four participants took part in the initial pilot evaluation while thirty six participants took part in the final evaluation. Data analysis and statistical results indicate that there are potential gains in learner satisfaction score in multiplatform e-learning systems over traditional e-learning systems. The results also show that the gain is most significant in mobile devices than in desktop PCs. Statistical analysis reveals that all the factors that influence the learner satisfaction are significant and they have different levels of influence over learner satisfaction. These factors can be further organized into primary factors and secondary factors. These findings and the methodology of evaluation can play an important role for e-learning systems designer to improve the adaptation process and to enhance the level of learner satisfaction in multiplatform e-learning systems.

The focus of this research is to investigate the potential of user interface (UI) pattern languages in assisting students of Human Computer Interaction (HCI) to learn the principles of UI design. A graphical representation named a UI-pattern model was developed. It arose from the evaluation of four existing pattern languages. The UI-pattern model is an enhanced form of UI pattern list that represents a specific UI. It was recognised that the UI-pattern model has the potential to help students learn about pattern language structure. It was also realised that UI-pattern modelling can be used to incrementally improve pattern languages through the generative process proposed by Alexander (1979). A UI pattern language Maturity Model (UMM) has been developed. This model can be used by educators when selecting and/or modifying existing UI pattern languages so that they are more appropriate for student use. A method for developing detailed UI designs that utilises a UI pattern language has been developed with the aim of providing students with an ‘authentic’ real-world UI design experience, as envisaged by constructivist educational theory (Jonassen 1999). This UI design method (TUIPL) guides the students’ development of user interface conceptual models. To establish the authenticity of TUIPL three case studies were undertaken out with developers who had differing levels of UI design experience. A series of studies investigated how HCI students used TUIPL to guide the development of UI-pattern models and canonical abstract prototypes. The studies also ascertained the students’ views on using three different forms of UI pattern (illustrated, narrative and diagrammed). Data was collected by observation, questionnaires and completed exercises. The results indicate that the students developed an understanding of pattern language structure, were positive about their experience building UI-pattern models and canonical abstract prototypes, and that patterns aided communication. The learning outcomes were encouraging and students responded positively to using a UI pattern language.