Adults with autism face many difficulties when finding employment, such as struggling with interviews and needing accommodating environments for sensory issues. However, autistic adults also have unique skills to contribute to the workplace that companies have recently started to seek after, such as close attention to detail and trustworthiness. To work around these difficulties and help companies find the talent they are looking for we have developed a job-matching system. Our system is based around the stable matching of the Gale-Shapley algorithm to match autistic adults with employers after estimating how both adults with autism and employers would rank the other group. The system also uses filtering to approximate a stable matching even with a changing pool of users and employers, meaning the results are resistant to change as the result of competition. Such a system would be of benefit to both autistic adults and employers and would advance knowledge in recommendation systems that match two parties.

Indiana University-Purdue University Indianapolis (IUPUI) / This research proposed a dynamic recommendation system for a social learning environment entitled CourseNetworking (CN). The CN provides an opportunity for the users to satisfy their academic requirement in which they receive the most relevant and updated content. In our research, we extracted some implicit and explicit features from the system, which are the most relevant user feature and posts features. The selected features are used to make a rating scale between users and posts so that represent the link between user and post in this learning management system (LMS). We developed an algorithm which measures the link between each user and post for the individual. To achieve our goal in our system design, we applied natural language processing technique (NLP) for text analysis and applied various classi cation technique with the aim of feature selection. We believe that considering the content of the posts in learning environments as an impactful feature will greatly affect to the performance of our system. Our experimental results demonstrated that our recommender system predicts the most informative and relevant posts to the users. Our system design addressed the sparsity and cold-start problems, which are the two main challenging issues in recommender systems.

This study examines the design and trustworthiness factors of recommendation systems forexperience goods in the e-commerce industry. Experience goods are products that involvesensory experiences and pose challenges for consumers to assess and select online. Theresearch adopts a mixed method approach, combining exploratory and interpretive researchmethods to gain insights into users' interpretations and meanings attached to their experiences.The methodology includes analyzing publications, conducting a survey, and objectivelydocumenting recommendation systems in the alpine industry. The survey collects opinions fromparticipants who have used various recommendation systems, covering aspects such as usermodel, item model, recommendation algorithm, user interface, evaluation, and trustworthiness.A thematic analysis is employed to identify patterns and meaningful themes in the data. Thefindings emphasize the importance of understanding user preferences, balancingrecommendations, improving accuracy, enhancing interface usability, incorporating feedback,and addressing recommendation diversity to enhance trustworthiness. A hybrid filteringapproach with feature-based systems and integrated behavior-based techniques is identified aseffective. While the survey's convenience sampling and limited sample size may limitgeneralizability, the findings provide insights for designing effective recommendation systems forexperience goods in e-commerce. By considering the strengths and limitations of differenttechniques, vendors can create systems that assist customers in purchasing these uniqueproducts. However, recommendation systems should be viewed as a valuable tool rather thanthe sole determinant in purchase decisions for alpine equipment. Further research with a largerand more diverse sample is recommended to validate the findings and improve generalizability.

In recent years, Recommendation Systems have revolutionized how social media and ecommerce are used. Fashion Recommendation Systems have made it easier for customers to do shopping, by recommending items to them based on various factors, such as their previous orders, and their similarities to other users. To apply a Fashion Recommendation System, there are four main approaches: Content-based filtering, where the system recommends similar items to the user. Collaborative filtering, in which the system recommends items from similar users. Hybrid filtering, which merges the features of the previous techniques, and Hyper-personalized filtering, which uses the profiling of customers to draw certain assumptions about users. The problem this research addresses is the lack of involving the intent of users when designing and applying a fashion recommendation system, as well as the cold start problem. The Research Questions are: 1. How to develop and implement a Fashion Recommendation System as an artifact that provides recommendations to customers, 2. How to implement intent as context in such Recommendation Systems to provide improved recommendations to the fashion customers, 3. How the inclusion of intent as context in a Fashion Recommendation System impacts customer satisfaction. The Research Methodology used in this study is design science research, with various research strategies and data collection methods used throughout, such as crowdsourcing, document analysis, testing, qualitative questionnaires, and thematic analysis. The Results of the study indicate the involvement of the intent results in better recommendations, a smoother and more accurate shopping experience, and an overall higher customer satisfaction.

Developers are often tasked with maintaining complex systems. Regardless of prior experience, there will inevitably be times in which they must interact with parts of the system with which they are unfamiliar. In such cases, recommendation systems may serve as a valuable tool to assist the developer in implementing a solution. Many recommendation systems in software engineering utilize the Stack Overflow knowledge-base as the basis of forming their recommendations. Traditionally, these systems have relied on the developer to explicitly invoke them, typically in the form of specifying a query. However, there may be cases in which the developer is in need of a recommendation but unaware that their need exists. A new class of recommendation systems deemed Behavior-Driven Recommendation Systems for Software Engineering seeks to address this issue by relying on developer behavior to determine when a recommendation is needed, and once such a determination is made, formulate a search query based on the software engineering task context. This thesis presents one such system, StackInTheFlow, a plug-in integrating into the IntelliJ family of Java IDEs. StackInTheFlow allows the user to intervi act with it as a traditional recommendation system, manually specifying queries and browsing returned Stack Overflow posts. However, it also provides facilities for detecting when the developer is in need of a recommendation, defined when the developer has encountered an error messages or a difficulty detection model based on indicators of developer progress is fired. Once such a determination has been made, a query formulation model constructed based on a periodic data dump of Stack Overflow posts will automatically form a query from the software engineering task context extracted from source code currently open within the IDE. StackInTheFlow also provides mechanisms to personalize, over time, the results displayed to a specific set of Stack Overflow tags based on the results previously selected by the user. The effectiveness of these mechanisms are examined and results based the collection of anonymous user logs and a small scale study are presented. Based on the results of these evaluations, it was found that some of the queries issued by the tool are effective, however there are limitations regarding the extraction of the appropriate context of the software engineering task yet to overcome.

La facilitation est un élément central dans une prise de décision de groupe surtout en faisant l'usage des outils de nouvelle technologie. Le facilitateur, pour rendre sa tâche facile, a besoin des solutions de vote pour départager les décideurs afin d'arriver à des conclusions dans une prise de décision. Une procédure de vote consiste à déterminer à partir d’une méthode le vainqueur ou le gagnant d’un vote. Il y a plusieurs procédures de vote dont certaines sont difficiles à expliquer et qui peuvent élire différents candidats/options/alternatives proposées. Le meilleur choix est celui dont son élection est acceptée facilement par le groupe. Le vote dans la théorie du choix social est une discipline largement étudiée dont les principes sont souvent complexes et difficiles à expliquer lors d’une réunion de prise de décision. Les systèmes de recommandation sont de plus en plus populaires dans tous les domaines de science. Ils peuvent aider les utilisateurs qui n’ont pas suffisamment d’expérience ou de compétence nécessaires pour évaluer un nombre élevé de procédures de vote existantes. Un système de recommandation peut alléger le travail du facilitateur dans la recherche d’une procédure vote adéquate en fonction du contexte de prise de décisions. Le sujet de ce travail de recherche s’inscrit dans le champ de l’aide à la décision de groupe. La problématique consiste à contribuer au développement d’un système d’aide à la décision de groupe (Group Decision Support System : GDSS). La solution devra s’intégrer dans la plateforme logicielle actuellement développée à l’IRIT GRUS : GRoUp Support. / Facilitation is a central element in decision-making, especially when using new technology tools. The facilitator, to make his task easy, needs voting solutions to decide between decision-makers in order to reach conclusions in a decision-making process. A voting procedure consists of determining from a method the winner of a vote. There are several voting procedures, some of which are difficult to explain and which may elect different candidate/options/alternatives proposed. The best choice is the one whose election is easily accepted by the group. Voting in social choice theory is a widely studied discipline whose principles are often complex and difficult to explain at a decision-making meeting. Recommendation systems are becoming more and more popular in all fields of science. They can help users who do not have sufficient experience or competence to evaluate large numbers of existing voting procedures. A recommendation system can lighten the facilitator's workload in finding an appropriate voting procedure based on the decision-making context. The objective of this research work is to design such recommendation system. This work is in the field of group decision support. The issue is to contribute to the development of a Group Decision Support System (GDSS). The solution will have to be integrated into the software platform currently being developed at IRITGRUS: GRoUp Support.

The rapid increase of available products and information on the Internet has created new problems for consumers. In stead of not having adequate alternatives, consumers have to spend a lot of effort in filtering and processing information. Overcoming information overload becomes a key issue for information search. As a result, information filtering and product recommendation become increasingly popular among on-line stores. These e-stores can collect user preference and use the information for product recommendation and personalized services. The purpose of recommendation systems is to increase consumers¡¦ purchase intentions, which may be affected by many factors. The objective of this study is to investigate factors that may affect the purchase intention of consumers. More specifically, the research adopts two theories, the elaboration likelihood model and the social influence theory, to build a research framework. We assume that the recommendation message affect consumer attitudes and intention through information and social influences. A laboratory experiment was conducted that use books and movies as two products to test the theory. The results indicate that purchase intention was affected by the attitude toward the recommended product and informational influence. The attitude toward the recommended product, informational influence, and normative social influence were affected by the type of the products and web comments on the product. Different recommendation approaches also affected consumers¡¦ perception of informational influence. The contribution of the research is two folds. First, we develop a theory that can be used to interpret the effect of different factors in the recommendation process. Second, the results have explored much insight into how product recommendation affects consumer attitude and purchase intention and can also be used in designing recommendation systems.

This report presents a survey of the state-of-the-art methods for building recommendation systems. The report mainly concentrates on systems that use the available side information in addition to a fraction of known affinity values such as ratings. Such data is referred to as Dyadic Data with Covariates (DyadC). The sources of side information being considered includes user/item entity attributes, temporal information and social network attributes. Further, two new models for recommendation systems that make use of the available side information within the collaborative filtering (CF) framework, are proposed. Review Quality Aware Collaborative Filtering, uses external side information, especially review text to evaluate the quality of available ratings. These quality scores are then incorporated into probabilistic matrix factorization (PMF) to develop a weighted PMF model for recommendation. The second model, Mixed Membership Bayesian Affinity Estimation (MMBAE), is based on the paradigm of Simultaneous Decomposition and Prediction (SDaP). This model simultaneously learns mixed membership cluster assignments for users and items along with a predictive model for rating prediction within each co-cluster. Experimental evaluation on benchmark datasets are provided for these two models. / text

Made available in DSpace on 2014-06-12T15:52:44Z (GMT). No. of bitstreams: 2 arquivo1844_1.pdf: 1599198 bytes, checksum: 84a19c5d7769a76fba813a0cac740509 (MD5) license.txt: 1748 bytes, checksum: 8a4605be74aa9ea9d79846c1fba20a33 (MD5) Previous issue date: 2009 / Conselho Nacional de Desenvolvimento Científico e Tecnológico / As organizações, com o intuito de aumentarem o seu grau de competitividade no mercado, vêm a cada instante buscando novas formas de evoluir a produtividade e a qualidade dos produtos desenvolvidos, além da diminuição de custos que está diretamente relacionada ao aumento do faturamento líquido. Para que tais objetivos possam ser alcançados é primordial explorar ao máximo o potencial de seus colaboradores e os possíveis relacionamentos que esses colaboradores têm uns com os outros, ou seja, encontrar e partilhar conhecimento tácito. Como o conhecimento tático está na mente das pessoas, é difícil de ser formalizado e documentado, por isso, o ideal seria identificar e recomendar a pessoa que detém o conhecimento. Diante disso, a presente dissertação apresenta o Sistema de Recomendação de Especialistas SWEETS e a sua implantação no ambiente a.m.i.g.o.s., uma plataforma de gestão de conhecimento baseada em conceitos voltados às redes sociais. O SWEETS foi desenvolvido em duas versões, 1.0 e 2.0. A versão 1.0, de forma pró-ativa, aproxima pessoas com especialidades em comum, ora pelos seus conhecimentos (perfil de escrita), ora pelos seus interesses (perfil de leitura). Já a versão 2.0 do SWEETS não atua de forma pró-ativa, ou seja, é necessário que haja a requisição de um usuário especialista em determinada área, e é baseada em folksonomia para extração de uma ontologia, fundamental para identificar as especialidades das pessoas de forma mais eficaz. Esta ontologia é refletida pela co-ocorrência das tags (conceitos) em relação aos itens (instâncias) e é independente de domínio principal contribuição dessa dissertação. A implantação do SWEETS no a.m.i.g.o.s. visa trazer benefícios como: minimizar o problema de comunicação na corporação, prover um incentivo ao conhecimento social e partilhar conhecimento; proporcionando, assim, à empresa, a utilização mais eficaz dos conhecimentos de seus colaboradores

Today, commercial industry spends huge amount of resources in advertisement campaigns, new marketing strategies, and promotional deals to introduce their product to public and attract a large number of customers. These massive investments by a company are worthwhile because marketing tactics greatly influence the consumer behavior. Alternatively, these advertising campaigns have a discernible impact on recommendation systems which tend to promote popular items by ranking them at the top, resulting in biased and unfair decision making and loss of customers’ trust. The biasing impact of popularity of items on recommendations, however, is not fixed, and varies with time. Therefore, it is important to build a bias-aware recommendation system that can rank or predict items based on their true merit at given time frame. This thesis proposes a framework that can model the temporal bias of individual items defined by their characteristic contents, and provides a simple process for bias correction. Bias correction is done either by cleaning the bias from historical training data that is used for building predictive model, or by ignoring the estimated bias from the predictions of a standard predictor. Evaluated on two real world datasets, NetFlix and MovieLens, our framework is shown to be able to estimate and remove the bias as a result of adopted marketing techniques from the predicted popularity of items at a given time.