Consumer-generated reviews play an important role in online purchase decisions for many consumers. However, the quality and helpfulness of online reviews varies significantly. In addition, the helpfulness of different consumer-generated reviews is not disclosed to consumers unless they carefully analyze the overwhelming number of available contents. Therefore, it is of vital importance to develop predictive models that can evaluate online product reviews efficiently and then display the most useful reviews to consumers, in order to assist them in making purchase decisions. This thesis examines the problem of building computational models for predicting whether a consumer-generated review is helpful based on consumers' online votes on other reviews (where a consumer's vote on a review is either HELPFUL or UNHELPFUL), with the aim of suggesting the most suitable products and vendors to consumers.In particular, we propose in this thesis three different helpfulness prediction approaches for consumer-generated reviews. Our entropy-based approach is relatively simple and suitable for applications requiring simple recommendation engine with fully-voted reviews. However, our entropy-based approach, as well as the existing approaches, lack a general framework and are all limited to utilizing fully-voted reviews. We therefore present a probabilistic helpfulness prediction framework to overcome these limitations. To demonstrate the versatility and flexibility of this framework, we propose an EM-based model and a logistic regression-based model. We show that the EM-based model can utilize reviews voted by a very small number of voters as the training set, and the logistic regression-based model is suitable for real-time helpfulness predicting of consumer-generated reviews. To our best knowledge, this is the first framework for modeling review helpfulness and measuring the goodness of models. Although this thesis primarily considers the problem of review helpfulness prediction, the presented probabilistic methodologies are, in general, applicable for developing recommender systems that make recommendation based on other forms of user-generated contents.

Living in the information-overloading age, it is difficult to find the right information and identify the resources they need on the websites. As to a user, it is time-consuming in browsing, searching, and making a decision to buy products on online stores. Therefore, many E-commerce websites have implemented recommender systems that intend to provide users with professional recommendation for various types of products and services. Although many recommendation methods have been proposed, there are still some problems like the sparsity and the cold start problems. In addition, some researchers observe there exist users who are biased and products that are controversial. We conjecture that ratings given by biased users or given to controversial products may have impact on estimation accuracy of recommendation. In this thesis, we will examine the measures for user bias and product controversy and propose trust-based-recommendation techniques that take them into account. We evaluate the proposed techniques using the web of trust and rating data collected from the Epinions.com website. It is found that properly setting some parameters, the proposed trust network-based method that incorporates user bias achieve higher recommendation accuracy.

none

Consumer-generated reviews play an important role in online purchase decisions for many consumers. However, the quality and helpfulness of online reviews varies significantly. In addition, the helpfulness of different consumer-generated reviews is not disclosed to consumers unless they carefully analyze the overwhelming number of available contents. Therefore, it is of vital importance to develop predictive models that can evaluate online product reviews efficiently and then display the most useful reviews to consumers, in order to assist them in making purchase decisions. This thesis examines the problem of building computational models for predicting whether a consumer-generated review is helpful based on consumers' online votes on other reviews (where a consumer's vote on a review is either HELPFUL or UNHELPFUL), with the aim of suggesting the most suitable products and vendors to consumers.In particular, we propose in this thesis three different helpfulness prediction approaches for consumer-generated reviews. Our entropy-based approach is relatively simple and suitable for applications requiring simple recommendation engine with fully-voted reviews. However, our entropy-based approach, as well as the existing approaches, lack a general framework and are all limited to utilizing fully-voted reviews. We therefore present a probabilistic helpfulness prediction framework to overcome these limitations. To demonstrate the versatility and flexibility of this framework, we propose an EM-based model and a logistic regression-based model. We show that the EM-based model can utilize reviews voted by a very small number of voters as the training set, and the logistic regression-based model is suitable for real-time helpfulness predicting of consumer-generated reviews. To our best knowledge, this is the first framework for modeling review helpfulness and measuring the goodness of models. Although this thesis primarily considers the problem of review helpfulness prediction, the presented probabilistic methodologies are, in general, applicable for developing recommender systems that make recommendation based on other forms of user-generated contents.

An individual’s ability to locate the information they desire grows more slowly than the rate at which new information becomes available. Customers are constantly confronted with situations in which they have many options to choose from and need assistance exploring or narrowing down the possibilities. Recommender systems are one tool to help bridge this gap. There are various mechanisms being employed to create recommender systems, but the most common systems fall into two main classes: content-based and collaborative filtering systems. Content-based recommender systems match the textual information of a particular product with the textual information representing the interests of a customer. Collaborative filtering systems use patterns in customer ratings to make recommendations. Both types of recommender systems require significant data resources in the form of a customer’s ratings and product features; hence they are not able to generate high quality recommendations. Hybrid mechanisms have been used by researchers to improve the performance of recommender systems where one can integrate more than one mechanism to overcome the drawbacks of an individual system. The hybrid approach proposed in this thesis is the integration of content and context-based with collaborative filtering, since these are the most successful and widely used mechanisms. This proposed approach will look into the integration of content and context data with rating data using a different mechanism that mainly focuses on boosting a customer’s trust in the recommender system. Researchers have been trying to improve system performance using hybrid approaches, but research is lacking on providing justifications for recommended products. Hence, the proposed approach will mainly focus on providing justifications for recommended products as this plays a crucial role in obtaining the satisfaction and trust of customers. A product’s features and a customer’s context attributes are used to provide justifications. In addition to this, the presentation mechanism needs to be very effective as it has been observed that customers trust more in a system when there are explanations on how the recommended products have been computed and presented. Finally, this proposed recommender system will allow the customer to interact with it in various ways to provide feedback on the recommendations and justifications. Overall, this integration will be very useful in achieving a stronger correlation between the customers and products. Experimental results clearly showed that the majority of the participants prefer to have recommendations with their justifications and they received valuable recommendations on which they could trust.

§ For a researcher it is always important to increase his/her social capital and excel attheir research area. For this, conferences act as perfect medium where researchers meetand present their work. However, due to the structure of the conferences finding similarauthors or interesting talks is not obvious for the researchers. One of most importantobservation made from the conferences is, researchers tend to form communities withcertain research topics as the series of conferences progresses. These communitiesand their research topics could be used in helping researchers find their potentialcollaborators and in attending interesting talks. In this research we present the design and implementation of a recommender systemwhich is built to provide recommendation of authors and talks at the conferences.Various concepts like Social Network Analysis (SNA), context awareness, communityanalysis, and topic modeling are used to build the system. This system can beconsidered as an extension to the previous system CAMRS (Context Aware MobileRecommender System). CAMRS is a mobile application which serves the same purposeas the current system. However, CAMRS uses only SNA and context to providerecommendations. Current system, CAMRS-2, is also an Android application builtusing REST based architecture. The system is successfully is deployed, and as partof thesis the system is evaluated. The evaluation results proved CAMRS-2 providesbetter recommendations over its predecessor.

Knowledge is a critical dimension in the problem solving processes of human intelligence. Consequently, enabling intelligent systems to provide advanced services requires that their artificial intelligence routines have access to knowledge of relevant domains. Ontologies are often utilised as the formal conceptualisation of domains, in that they identify and model the concepts and relationships of the targeted domain. However complexities inherent in ontology development and maintenance have limited their availability. Separate from the conceptualisation component, domain knowledge also encompasses the concept membership of object instances within the domain. The need to capture both the domain model and the current state of instances within the domain has motivated the import of Formal Concept Analysis into intelligent systems research. Formal Concept Analysis, which provides a simplified model of a domain, has the advantage in that not only does it define concepts in terms of their attribute description but object instances are simultaneously ascribed to their appropriate concepts. Nonetheless, a significant drawback of Formal Concept Analysis is that when applied to a large dataset, the lattice with which it models a domain is often composed of a copious amount of concepts, many of which are arguably unnecessary or invalid. In this research a novel measure is introduced which assigns a relevance value to concepts in the lattice. This measure is termed the Collapse Index and is based on the minimum number of object instances that need be removed from a domain in order for a concept to be expunged from the lattice. Mathematics that underpin its origin and behaviour are detailed in the thesis showing that if the relevance of a concept is defined by the Collapse Index: a concept will eventually lose relevance if one of its immediate subconcepts increasingly acquires object instance support; and a concept has its highest relevance when its immediate subconcepts have equal or near equal object instance support. In addition, experimental evaluation is provided where the Collapse Index demonstrated comparable or better performance than the current prominent alternatives in: being consistent across samples; the ability to recall concepts in noisy lattices; and efficiency of calculation. It is also demonstrated that the Collapse Index affords concepts with low object instance support the opportunity to have a higher relevance than those of high supportThe second contribution to knowledge is that of an approach to semantic extraction from a dataset where the Collapse Index is included as a method of selecting concepts for inclusion in a final concept hierarchy. The utility of the approach is demonstrated by reviewing its inclusion in the implementation of a recommender system. This recommender system serves as the final contribution featuring a unique design where lattices represent user profiles and concepts in these profiles are pruned using the Collapse Index. Results showed that pruning of profile lattices enabled by the Collapse Index improved the success levels of movie recommendations if the appropriate thresholds are set.

Les systèmes de recommandation sont conçus dans une variété d'applications pour aider à la prise de décision. Dans un environnement collaboratif, le système de recommandation peut guider la collaboration. Les utilisateurs laissent des traces d’interaction lorsqu'ils collaborent sur une plateforme numérique. Ces traces peuvent être analysées pour détecter les signaux forts et les signaux faibles d’une collaboration. Cette thèse porte sur la mise en œuvre d'un système de recommandation exploitant les traces de collaboration dans un environnement informatique. Les travaux réalisés ont été testés au sein de la plateforme web collaborative E-MEMORAe. / With the development of information and Internet technology, human society has stepped into an era of information overload. Owing to the overwhelming quantity of information, both information providers and information consumers are facing challenges: information providers want the information to be transferred to the target audience while information consumers need to find the information most relevant to their need. To bridge the gap, recommender systems have been designed and applied in a variety of applications to help making decisions on movies, music, news and even services and persons. In a Collaborative Working Environment, recommender systems are also needed to guide collaboration and allocate task efficiently. When people exchange information and resources, they leave traces in some way or other. For a typical Web-based Collaborative Working Environment, traces can be recorded which are mainly produced by collaborative activities or interactions. The modelled traces represent knowledge as well as experience concerning the interactive actions among users and resources. Such traces can be defined, modelled and exploited in return to offer a clue on a variety of deductions. Firstly they can indicate whether a user is active or not concerning interactions on a certain subject. Combining with users’ evaluation of the information and resources during interaction, we can further evaluate a user’s competency on each subject. This aids the decision for further collaboration because knowing the specialization of users helps to distribute tasks reasonably.This thesis focuses on implementing a recommender system by exploiting various collaborative traces in the group shared/collaborative workspace. To achieve this goal, firstly we collect traces and get them filtered by system filters. For evaluating shared resources we propose a system of vote and combine the result with collaborative traces. Furthermore, we present two mathematical approaches (TF-IDF and Bayes Classifier) with semantic meanings of traced resources and a machine learning method (Logistic Regression) with user profile to exploit traces, and then discuss comprehensive examples. As a practical experience we tested our prototype in the context of the E-MEMORAe collaborative platform. By comparing the results of experiments we assess the strengths and weaknesses of each of the three methods and in which scenario they perform better. Cases show that our exploitation framework and various methods can facilitate both personal and collaborative work and help decision-making.

Consumer-generated reviews play an important role in online purchase decisions for many consumers. However, the quality and helpfulness of online reviews varies significantly. In addition, the helpfulness of different consumer-generated reviews is not disclosed to consumers unless they carefully analyze the overwhelming number of available contents. Therefore, it is of vital importance to develop predictive models that can evaluate online product reviews efficiently and then display the most useful reviews to consumers, in order to assist them in making purchase decisions. This thesis examines the problem of building computational models for predicting whether a consumer-generated review is helpful based on consumers' online votes on other reviews (where a consumer's vote on a review is either HELPFUL or UNHELPFUL), with the aim of suggesting the most suitable products and vendors to consumers.In particular, we propose in this thesis three different helpfulness prediction approaches for consumer-generated reviews. Our entropy-based approach is relatively simple and suitable for applications requiring simple recommendation engine with fully-voted reviews. However, our entropy-based approach, as well as the existing approaches, lack a general framework and are all limited to utilizing fully-voted reviews. We therefore present a probabilistic helpfulness prediction framework to overcome these limitations. To demonstrate the versatility and flexibility of this framework, we propose an EM-based model and a logistic regression-based model. We show that the EM-based model can utilize reviews voted by a very small number of voters as the training set, and the logistic regression-based model is suitable for real-time helpfulness predicting of consumer-generated reviews. To our best knowledge, this is the first framework for modeling review helpfulness and measuring the goodness of models. Although this thesis primarily considers the problem of review helpfulness prediction, the presented probabilistic methodologies are, in general, applicable for developing recommender systems that make recommendation based on other forms of user-generated contents.

Many countries depend heavily on tourism for their economic growth. The invention of the web has opened new opportunities for tourists to discover new places and live new adventures. However, the number of possible destinations has become huge and even an entire lifespan would not be enough to visit all of these places. Even for one city, there are a significant number of possible places to visit. Nowadays, searching online to find an interesting place to visit is harder than ever, not because there is a lack of information but rather due to the vast amount of information that can be found. Trip planning is a tedious task, especially when the tourist does not want to pick a preplanned itinerary from a traveling agency. That being said, even these preplanned itineraries need a lot of time and effort to be customized. Moreover, the set of itineraries that a tourist can select from is usually limited. In addition, there may be many places that tourists would enjoy visiting but that are not included in the itineraries. Thus, static planners do not always choose the right place at the right time. This is why the planning process should take into consideration many factors in order to give the tourist the best possible suggestions. In this Thesis, we propose an algorithm called the Balanced Orienteering Problem to design trips for tourists. This algorithm, combined with a context-aware recommender system for tourism suggestions, create the infrastructure of the mobile application for the augmented reality tourism guide that we developed. We cover the background knowledge of tour planning problems and tourism recommender systems and describe the existing techniques. Furthermore, a comparison between the existing systems and our algorithm is completed to illustrate that our proposed algorithm yields better results. We also discuss the workflow of our system implementation and how our mobile application is designed. Lastly, we address suggestions for future works and end with a conclusion.