This study investigates onto which dimensions of service quality have more impact on patients’ overall quality perceptions of a hospital and seeks to determine the nature of relationship between service quality and patients’ willingness to recommend a hospital to their friends and family. The study also uncovers if the levels of service quality and recommendation behaviours and the relationship between service quality and recommendation behaviour exhibit similar patterns among male versus female, black versus white patients and small/medium versus large hospitals. Data gathered via mail questionnaires and phone interviews from a large sample of the patients of a hospital system in the Southern United States serve as the study setting. Results are presented and their implications are discussed. Avenues for future research are offered.

Expert software developer recommendation is a mature research field with many different techniques being developed to help automate the search for experts to help with development tasks and questions. But all previous research on recommending expert developers has had two constant restrictions. First, all previous expert recommendation work assumed that developers only demonstrate positive expertise. But developers can also make mistakes and demonstrate negative expertise, referred to as inexpertise, and show which concepts they don't know as well. Previous research on developer expertise hasn't taken inexpertise into account. Another restriction is that all previous expert developer recommendation research has focused on recommending developers for a single development task or expertise need, such as fixing a bug report or helping with a change request. But not all expertise needs can be easily classified into one of these groups, and having different techniques for every possible task type would be difficult and confusing to maintain and use. We find that inexpertise exists, can be measured, and that it can be used to direct inspection effort to find potentially incorrect or buggy commits. Additionally we investigate how different expertise finding techniques perform on a diverse set of long and short expertise queries and develop new techniques that can get more consistent cross query performance. / Master of Science / Expert software developers are a useful source of information. There have been many papers that research techniques for recommending expert developers for different tasks and questions. But all previous research on recommending expert developers has had two constant restrictions. First, all previous expert recommendation work assumed that developers only demonstrate positive expertise. But developers can also make mistakes and demonstrate negative expertise, referred to as inexpertise, and show which concepts they don’t know as well. Another restriction is that all previous work on recommending expert developers has focused on recommending developers for a single development task or question. But not all expertise needs can be easily classified into one of these groups, and having different techniques for every possible task type would be difficult and confusing to maintain and use. In our first chapter we show that inexpertise exists, can be measured, and that it can be used to help identify potentially buggy or incorrect code. In the second chapter we investigate how different techniques for finding expert developers perform when evaluated on different kinds of expertise finding tasks to find which technique works well on multiples types of tasks.

Recommendation is not a new phenomenon arising from the digital era, but an existing social behavior in real life. Recommendation systems facilitate such natural social recommendation behavior and alleviate information overload facing individuals. Among different recommendation techniques proposed in the literature, the collaborative filtering approach is the most successful and widely adopted recommendation technique to date. However, the traditional collaborative filtering recommendation approach ignores proximities between items. That is, all user ratings on items are deemed identically important and given an equal weight in neighborhood formation process. In this study, we proposed a cluster-based collaborative filtering recommendation approach that takes into account the content similarities of items in the collaborative filtering process. Our empirical evaluation results show that the cluster-based collaborative filtering approach improves the prediction accuracy without sacrificing the prediction coverage, using those achieved by the traditional collaborative filtering approach as performance benchmarks. Due to the sparsity problem, when a prediction is made based on few neighbors, the cluster average method could achieve a better prediction accuracy than the proposed approach. Thus, we further proposed an enhanced cluster-based collaborative filtering approach that combines our approach and the cluster average method. The empirical results suggest that the enhanced approach could result in a prediction accuracy comparable to or even better than that accomplished by the cluster average method.

Recommender systems are an integral and successful application of machine learning in e-commerce industry and in everyday lives of online users. Recommendation algorithms are used extensively for news, musics, books, point of interests, or travel recommendation as well as in many other domains. Although much focus has been paid on improving recommendation quality, however, some real-world aspects are not considered: How to ensure that top-n recommendations are fair and not biased due to any popularity boosting events, such as awards for movies or songs? How to recommend items to entities by explicitly considering information from heterogeneous sources. What is the best way to model sequential recommendation systems as heterogeneous context-aware design, and learning on-the-fly from spatial, temporal and social contexts. Can we model attributes and heterogeneous relations in a heterogeneous information network? The goal of this thesis is to pave the way towards the next generation of realworld recommendation systems tackling fairness and information heterogeneity challenges to improve the user experience, while giving good recommendations. This thesis bridges techniques from recommendation and deep-learning techniques for representation learning by proposing novel techniques to address the above real-world problems. We focus on four directions: (1) model the effect of popularity bias over time on the consumption of items, (2) model the heterogeneous information associated with sequential history of users and social links for sequential recommendation, (3) model the heterogeneous links and rich content of nodes in an academic heterogeneous information network, and (4) learn semantics using topic modeling for nodes based on their content and heterogeneous links in a heterogeneous information network.

Yes / The reliability of delivering packets through multi-hop intermediate nodes is a significant issue in the mobile ad hoc networks (MANETs). The distributed mobile nodes establish connections to form the MANET, which may include selfish and misbehaving nodes. Recommendation based trust management has been proposed in the literature as a mechanism to filter out the misbehaving nodes while searching for a packet delivery route. However, building a trust model that relies on the recommendations from other nodes in the network is vulnerable to the possible dishonest behaviour, such as bad-mouthing, ballot-stuffing, and collusion, of the recommending nodes. . This paper investigates the problems of attacks posed by misbehaving nodes while propagating recommendations in the existing trust models. We propose a recommendation based trust model with a defence scheme that utilises clustering technique to dynamically filter attacks related to dishonest recommendations within certain time based on number of interactions, compatibility of information and node closeness. The model is empirically tested in several mobile and disconnected topologies in which nodes experience changes in their neighbourhoods and consequently face frequent route changes. The empirical analysis demonstrates robustness and accuracy of the trust model in a dynamic MANET environment.

Recommendation Systems or Recommender Systems have become widely popular due to surge of information at present time and consumer centric environment. Researchers have looked into a wide range of recommendation systems leveraging a wide range of algorithms. This study investigates three popular recommendation systems in existence, Collaborative Filtering, Content-Based Filtering, and Hybrid recommendation system. The famous MovieLens dataset was utilized for the purpose of this study. The evaluation looked into both quantitative and qualitative aspects of the recommendation systems. We found that from both the perspectives, the hybrid recommendation system performs comparatively better than standalone Collaborative Filtering or Content-Based Filtering recommendation system

Denna studie har analyserat den kortsiktiga lönsamheten på aktierekommendationer mellan åren 2019 till och med första halvåret 2021. Syftet med studien var att jämföra kursutvecklingen på aktierekommendationer jämfört med indexet OMXSPI på kort sikt. Studien har också undersökt om det finns skillnader i volatiliteten mellan köp- och säljrekommendationer. Studien är kvantitativ och genomförd med deduktiv ansats. Det finns ett antal olika teorier om vad som styr priset på aktier, både självständigt och i samband med rekommendationer. Denna studie genomfördes för att få mer praktisk förståelse för aktiemarknaden då teorierna tidigare forskning använt sig av kan vara problematiska att bekräfta. Tidigare genomförda studier har resulterat i rekommendationer som fördelaktiga, resultaten från denna studie visar på motsatsen. Resultat från studien visade på att säljrekommendationer var något mer volatila initialt än köprekommendationer. Studien har som förslag för vidare forskning att utvärdera kortsiktig kursutveckling parallellt med långsiktig kursutveckling. Detta för att kunna uttala sig bättre om en rekommendations prestation. / This paper examines whether it’s possible to profit from short term investments on the Swedish stock market based on stock recommendations during 2019 through H1 2021. The study is quantitative with a deductive approach. The paper also compares volatility amongst buy and sell recommendations. This was done to get a better understanding of how the stock market works in practical terms due to there being many different adoptions of theory. The majority of previously completed studies show that recommendations are more favourable than OMXSPI index short term. However, the results from this study show that it’s not possible to profit from short term stock recommendations compared to OMXSPI index, hence the market isn’t effective. The study found vague results indicating that sell recommendations act more volatile. The study also found that different broker houses performed differently. Future research suggests short term returns to be evaluated parallel to long term returns. The reasoning for this being better understanding of short term returns.

For learners engaging in senior-level courses, tutors in many cases would like to pick some articles as supplementary reading materials for them each week. Unlike researchers Googling papers from the Internet, tutors, when making recommendations, should consider course syllabus and their assessment of learners along many dimensions. As such, simply Googling articles from the Internet is far from enough. That is, learner models of each individual, including their learning interest, knowledge, goals, etc. should be considered when making paper recommendations, since the recommendation should be carried out so as to ensure that the suitability of a paper for a learner is calculated as the summation of the fitness of the appropriateness of it to help the learner in general. This type of the recommendation is called a Pedagogical Paper Recommender.<p>In this thesis, we propose a set of recommendation methods for a Pedagogical Paper Recommender and study the various important issues surrounding it. Experimental studies confirm that making recommendations to learners in social learning environments is not the same as making recommendation to users in commercial environments such as Amazon.com. In such learning environments, learners are willing to accept items that are not interesting, yet meet their learning goals in some way or another; learners overall impression towards each paper is not solely dependent on the interestingness of the paper, but also other factors, such as the degree to which the paper can help to meet their cognitive goals.<p>It is also observed that most of the recommendation methods are scalable. Although the degree of this scalability is still unclear, we conjecture that those methods are consistent to up to 50 papers in terms of recommendation accuracy. <p>The experiments conducted so far and suggestions made on the adoption of recommendation methods are based on the data we have collected during one semester of a course. Therefore, the generality of results needs to undergo further validation before more certain conclusion can be drawn. These follow up studies should be performed (ideally) in more semesters on the same course or related courses with more newly added papers. Then, some open issues can be further investigated. <p>Despite these weaknesses, this study has been able to reach the research goals set out in the proposed pedagogical paper recommender which, although sounding intuitive, unfortunately has been largely ignored in the research community. <p>Finding a good paper is not trivial: it is not about the simple fact that the user will either accept the recommended items, or not; rather, it is a multiple step process that typically entails the users navigating the paper collections, understanding the recommended items, seeing what others like/dislike, and making decisions. Therefore, a future research goal to proceed from the study here is to design for different kinds of social navigation in order to study their respective impacts on user behavior, and how over time, user behavior feeds back to influence the system performance.

AIM: The aim of this study was to a) find out which recommendations are given by nurses regarding breastfeeding to HIV infected mothers, at Muhimbili hospital and the adherence of these, and (b) to find out the nurses’ opinions regarding the WHO recommendations and the parents’ adherence to these. The study will also look into if the nurses are aware of any changes in knowledge among the parents in an HIV context.METHOD: There were eight semi-structured interviews with open ended questions that were performed at Muhimbili Hospital. All the interviews were recorded and transcribed with content analysis.RESULT: The nurses’ recommendations are adapted to the mothers’ socio-economical situation. The benefits of replacement foods are emphasized if conditions are suitable, otherwise exclusive breast feeding is recommended. Some recommendations are difficult to follow due to poor sanitary standards, low economical standard and stigmatization. Cultural norms may affect the mothers’ choice of feeding method as it might raise suspicions in their community if they do not breastfeed. The knowledge of mother-to-child-transmission has increased but to reduce the transmission rates more knowledge is still needed and a change in attitude towards HIV infected mothers.CONCLUSION: The recommendations given by the nurses to HIV-positive mothers are not directly according to the ones by the WHO although the content is similar. The recommendations are adjusted in accordance to the Tanzanian women’s individual situation. Adherence problems to the recommendations are due to lack of economic recourses and stigmatization from the community. In order to improve the adherence of the given recommendations a reduction in stigmatization is needed, through increased knowledge and changes in attitudes.

For learners engaging in senior-level courses, tutors in many cases would like to pick some articles as supplementary reading materials for them each week. Unlike researchers Googling papers from the Internet, tutors, when making recommendations, should consider course syllabus and their assessment of learners along many dimensions. As such, simply Googling articles from the Internet is far from enough. That is, learner models of each individual, including their learning interest, knowledge, goals, etc. should be considered when making paper recommendations, since the recommendation should be carried out so as to ensure that the suitability of a paper for a learner is calculated as the summation of the fitness of the appropriateness of it to help the learner in general. This type of the recommendation is called a Pedagogical Paper Recommender.<p>In this thesis, we propose a set of recommendation methods for a Pedagogical Paper Recommender and study the various important issues surrounding it. Experimental studies confirm that making recommendations to learners in social learning environments is not the same as making recommendation to users in commercial environments such as Amazon.com. In such learning environments, learners are willing to accept items that are not interesting, yet meet their learning goals in some way or another; learners overall impression towards each paper is not solely dependent on the interestingness of the paper, but also other factors, such as the degree to which the paper can help to meet their cognitive goals.<p>It is also observed that most of the recommendation methods are scalable. Although the degree of this scalability is still unclear, we conjecture that those methods are consistent to up to 50 papers in terms of recommendation accuracy. <p>The experiments conducted so far and suggestions made on the adoption of recommendation methods are based on the data we have collected during one semester of a course. Therefore, the generality of results needs to undergo further validation before more certain conclusion can be drawn. These follow up studies should be performed (ideally) in more semesters on the same course or related courses with more newly added papers. Then, some open issues can be further investigated. <p>Despite these weaknesses, this study has been able to reach the research goals set out in the proposed pedagogical paper recommender which, although sounding intuitive, unfortunately has been largely ignored in the research community. <p>Finding a good paper is not trivial: it is not about the simple fact that the user will either accept the recommended items, or not; rather, it is a multiple step process that typically entails the users navigating the paper collections, understanding the recommended items, seeing what others like/dislike, and making decisions. Therefore, a future research goal to proceed from the study here is to design for different kinds of social navigation in order to study their respective impacts on user behavior, and how over time, user behavior feeds back to influence the system performance.