I takt med att Internet blir mer och mer tillgängligt och att informationsmängden på Internetkonstant ökar, har ett behov för rekommendationssystem uppkommit. Ett problem på internet äratt veta vem och vad man kan lita på. Ett sätt att komma runt det här tillitsproblemet är attanvända sig av social media. Samtidigt har sociala medier ständigt ökat i populäritet de senasteåren. Syftet med den här uppsatsen är att undersöka hur rekommendationssystem och socialamedier kan dra nytta av varandra samtidigt som ett praktiskt problem om att fårekommendationer från sina (online) vänner löses. Detta uppnås genom att forskningsstrategindesign science används och en IT-artefakt utvecklas. IT-artefakten är en prototyp av en ny etjänst.Utifrån en enkätundersökning på prototypen och grundidén, dras slutsaser om hur detgår att skapa ett generellt personligt rekommendationssystem. Forskningen visar att det går attskapa ett sådant system och att det finns ett behov av ett generellt personligtrekommendationssystem med utgångspunkt i den information som finns lagrad i sociala medier. / As the Internet becomes more and more available, and that the amount of information on theInternet is constantly increasing, a need for recommendation systems has emerged. A problemon the Internet is knowing who and what you can trust. One way to get around this trust issue isto use social media. Meanwhile, social media have consistently increased in popularity in recentyears. The purpose of this paper is to examine how recommendation systems and SNS canbenefit from each other while the practical problem of getting recommendations from one’s(online) friends are solved. This is achieved by using the research strategy design science anddeveloping an IT artifact. The IT artifact is a prototype of a new online service. Based on asurvey of the prototype and the main concept, conclusions are drawn about how a generalpersonal recommendation system can be created. The research shows that it is possible tocreate such a system and that there is a need for a general personal recommendation systembased on the information stored in social media. This essay is written in Swedish.

Master of Science / Department of Computing and Information Sciences / Doina Caragea / The vast amount of data present on the internet calls for ways to label and organize this data according to specific categories, in order to facilitate search and browsing activities. This can be easily accomplished by making use of folksonomies and user provided tags. However, it can be difficult for users to provide meaningful tags. Tag recommendation systems can guide the users towards informative tags for online resources such as websites, pictures, etc. The aim of this thesis is to build a system for recommending tags to URLs available through a bookmark sharing service, called BibSonomy. We assume that the URLs for which we recommend tags do not have any prior tags assigned to them. Two approaches are proposed to address the tagging problem, both of them based on Latent Dirichlet Allocation (LDA) Blei et al. [2003]. LDA is a generative and probabilistic topic model which aims to infer the hidden topical structure in a collection of documents. According to LDA, documents can be seen as mixtures of topics, while topics can be seen as mixtures of words (in our case, tags). The first approach that we propose, called topic words based approach, recommends the top words in the top topics representing a resource as tags for that particular resource. The second approach, called topic distance based approach, uses the tags of the most similar training resources (identified using the KL-divergence Kullback and Liebler [1951]) to recommend tags for a test untagged resource. The dataset used in this work was made available through the ECML/PKDD Discovery Challenge 2009. We construct the documents that are provided as input to LDA in two ways, thus producing two different datasets. In the first dataset, we use only the description and the tags (when available) corresponding to a URL. In the second dataset, we crawl the URL content and use it to construct the document. Experimental results show that the LDA approach is not very effective at recommending tags for new untagged resources. However, using the resource content gives better results than using the description only. Furthermore, the topic distance based approach is better than the topic words based approach, when only the descriptions are used to construct documents, while the topic words based approach works better when the contents are used to construct documents.

The field of regulated financial services has been ill-served by marketing theory. As a consequence: (1) the nature of marketing in this sector has been misunderstood; (2) the key mechanism for generating new business in the field, namely, referrals, has been the subject of serious misapprehension; and, (3) the guidance offered to practitioners has been negligible. In particular, the role of the independent financial advisor (IFA) appears to have been conceptualised as a sales role, and the nature of the relationship between the IFA and the client has been addressed as though it were a straightforward buyer-seller relationship, with the IFA selling products to the client. It is unlikely that these conceptualisations were ever satisfactory and following recent regulatory changes in the sector they have become even less relevant. Since January 1st 2013 commission-based selling of financial investment products to consumers has been prohibited so that independent financial advice has become largely a fee-based service. The focus of this research is on referrals as a method of generating new business; the research context is the UK independent financial advice industry. The objectives of the study are to: (1) define and conceptualise referrals in the context of the financial advice industry; (2) develop a framework of the referral process; (3) provide practitioners with empirical evidence in connection with their embedded beliefs about referrals in this industry; (4) explore whether (as many practitioner believe) it is possible to actively manage referral generation within a financial advice business; and, (5) to investigate the importance of referrals as a means of generating new business for advisors. It was found that practitioners believe they influence referrals in four main ways: excellent service, higher qualifications, contact frequency and speed of response. However the results of this study clearly indicate that referrals are not the outcome of agency; they are a random occurrence, determined by happenstance and the result of an opportunist conversation between a prospect and a client. In turn, contrary to the advice of consultancy providers, asking for referrals was found to be ineffective and not welcomed by consumers. While word-of-mouth (WOM) often instigates referral generation, the value of WOM, needs be treated with caution, since consumers were found to have limited understanding of the service provided by independent advisors. Despite the importance consumers attribute to investment performance practitioners do not, commonly, provide investment benchmarks nor do consumers use analytical tools to assess the performance of their advisor. The absence of performance measures connects with the finding that practitioners have difficulty in describing what they do hence consumers are uncertain how to describe the service and what to say about it when asked.

The new social media sites - blogs, micro-blogs, and social networking sites, among others - are gaining considerable momentum to facilitate collaboration and social interactions in general. These sites provide a tremendous asset for understanding social phenomena by providing a wide availability of novel data sources. Recent estimates suggest that social media sites are responsible for as much as one third of new Web content, in the forms of social networks, comments, trackbacks, advertisements, tags, etc. One critical and immediate challenge facing the MIS researchers then becomes - how to effectively utilize this huge wealth of social media data, to facilitate business knowledge discovery and decision making.Among these available data sources, social networks constitute the backbone of almost all social media sites. These network structures provide a rich description of the social scenes and contexts, which is helpful for us to address the above challenge. In this dissertation, I have primarily employed the probabilistic network models, to study various social network related problems arose from the use of social media services. In Chapter 2 and Chapter 3, I studied how information overload can affect the efficiency of information diffusion in online social networks (Delicious.com and Digg.com). Novel diffusion model were proposed to model the observed information overload. The models and their extensions are thoroughly evaluated by solving the Influence Maximization problem related to information diffusion and viral marketing applications. In Chapter 4, I studied the information overload in a micro-blogging application (Twitter.com) using a design science methodology. A content recommendation framework was proposed to help micro-blogging users to efficiently identify quality emergency news feeds. Chapter 5 presents a novel burst detection algorithm concerning identifying and analyzing correlated burst patterns by considering multiple inputs (data streams) that co-evolve over time. The algorithm was later used for discovering burst keywords/tag pairs from online social communities, which are strong indicators of emerging or changing user interests.Chapter 6 concludes this dissertation by highlighting major research contributions and future directions.

Cloud computing, mobile computing, Service-Oriented Computing (SOC), and Software as a Service (SaaS) indicate that the Internet emerges to an anonymous service market where service functionality can be dynamically and ubiquitously consumed. Among functionally similar services, service consumers are interested in the consumption of the services which perform best towards their optimization preferences. The experienced performance of a service at consumer side is expressed in its non-functional properties (NFPs). Selecting the best-fit service is an individual challenge as the preferences of consumers vary. Furthermore, service markets such as the Internet are characterized by perpetual change and complexity. The complex collaboration of system environments and networks as well as expected and unexpected incidents may result in various performance experiences of a specific service at consumer side. The consideration of certain call side aspects that may distinguish such differences in the experience of NFPs is reflected in various call contexts. Service optimization based on a collaborative knowledge base of previous experiences of other, similar consumers with similar preferences is a desirable foundation. The research work described in this dissertation aims at an individually optimized selection of services considering the individual call contexts that have an impact on the performance, or NFPs in general, of a service as well as the various consumer preferences. The presented approach exploits shared measurement information about the NFP behavior of a service gained from former service calls of previous consumptions. Gaining selection/recommendation knowledge from shared experience benefits existing as well as new consumers of a service before its (initial) consumption. Our approach solely focuses on the optimization and collaborative information exchange among service consumers. It does not require the contribution of service providers or other non-consuming entities. As a result, the contribution among the participating entities also contributes to their own overall optimization benefit. With the initial focus on a single-tier optimization, we additionally provide a conceptual solution to a multi-tier optimization approach for which our recommendation framework is prepared in general. For a consumer-sided optimization, we conducted a literature study of conference papers of the last decade in order to find out what NFPs are relevant for the selection and consumption of services. The ranked results of this study represent what a broad scientific community determined to be relevant NFPs for service selection. We analyzed two general approaches for the employment of machine learning methods within our recommendation framework as part of the preparation of the actual recommendation knowledge. Addressing a future service market that has not fully developed yet and due to the fact that it seems to be impossible to be aware of the actual NFP data of different Web services at identical call contexts, a real-world validation is a challenge. In order to conduct an evaluation and also validation that can be considered to be close approximations to reality with the flexibility to challenge the machine learning approaches and methods as well as the overall recommendation approach, we used generated NFP data whose characteristics are influenced by measurement data gained from real-world Web services. For the general approach with the better evaluation results and benefits ratio, we furthermore analyzed, implemented, and validated machine learning methods that can be employed for service recommendation. Within the validation, we could achieve up to 95% of the overall achievable performance (utility) gain with a machine learning method that is focused on drift detection, which in turn, tackles the change characteristic of the Internet being an anonymous service market.

Learners often have difficulty finding and retrieving relevant learning materials to support their learning goals because of two main challenges. The vocabulary learners use to describe their goals is different from that used by domain experts in teaching materials. This challenge causes a semantic gap. Learners lack sufficient knowledge about the domain they are trying to learn about, so are unable to assemble effective keywords that identify what they wish to learn. This problem presents an intent gap. The work presented in this thesis focuses on addressing the semantic and intent gaps that learners face during an e-Learning recommendation task. The semantic gap is addressed by introducing a method that automatically creates background knowledge in the form of a set of rich learning-focused concepts related to the selected learning domain. The knowledge of teaching experts contained in e-Books is used as a guide to identify important domain concepts. The concepts represent important topics that learners should be interested in. An approach is developed which leverages the concept vocabulary for representing learning materials and this influences retrieval during the recommendation of new learning materials. The effectiveness of our approach is evaluated on a dataset of Machine Learning and Data Mining papers, and our approach outperforms benchmark methods. The results confirm that incorporating background knowledge into the representation of learning materials provides a shared vocabulary for experts and learners, and this enables the recommendation of relevant materials. We address the intent gap by developing an approach which leverages the background knowledge to identify important learning concepts that are employed for refining learners' queries. This approach enables us to automatically identify concepts that are similar to queries, and take advantage of distinctive concept terms for refining learners' queries. Using the refined query allows the search to focus on documents that contain topics which are relevant to the learner. An e-Learning recommender system is developed to evaluate the success of our approach using a collection of learner queries and a dataset of Machine Learning and Data Mining learning materials. Users with different levels of expertise are employed for the evaluation. Results from experts, competent users and beginners all showed that using our method produced documents that were consistently more relevant to learners than when the standard method was used. The results show the benefits in using our knowledge driven approaches to help learners find relevant learning materials.

Le Web est devenu une plateforme universelle d’hébergement d'applications hétérogènes. Dans ce contexte, les services Web se sont imposés comme une technologie clé pour permettre l’interaction entre diverses applications. Les technologies standards proposées autour des services Web permettent la programmation, plutôt manuelle, de ces applications. Pour favoriser une programmation automatique à base de services web, un problème majeur se pose : celui de leur découverte. Plusieurs approches adressant ce problème ont été proposées dans la littérature. L’objectif de cette thèse est d’améliorer le processus de découverte de services en exploitant trois pistes de recherche. La première consiste à proposer une approche de découverte qui combine plusieurs techniques de matching. La deuxième se base sur une validation des services retournés par un processus de découverte automatique en se basant sur les compétences utilisateurs. Ces approches ne prennent pas en considération l’évolution de services dans le temps et les préférences des utilisateurs. Pour remédier à ces lacunes plusieurs approches incorporent des techniques de recommandation. La majorité d'entre eux sont basées sur les évaluations des propriétés de QdS. Pratiquement, ces évaluations sont rarement disponibles. D’autres systèmes exploitent les relations de confiance. Ces relations sont établies en se basant sur les évaluations de services. Or, invoquant le même service ne signifie pas obligatoirement avoir les mêmes préférences. D’où, nous proposons, l’exploitation des relations d’intérêts entre les utilisateurs pour recommander des services. L’approche s’appuie sur une modélisation orientée base de données graphes. / The Web has become an universal platform for content hosting and distributed heterogeneous applications that can be accessed manually or automatically. In this context, Web services have established themselves as a key technology for deploying interactions across applications. The standard Web services technologies allow and facilitate the manual programming of these applications. To promote automatic programming based on Web services, a major problem arises : that of their discovery. Several approaches addressing this problem have been proposed in the literature. The aim of this thesis is to improve the Web services discovery process. We proposed three approaches. We proposed a Web services discovery approach that combines several matching techniques. The second consists on the validation of the services returned by an automatic process of discovery using users’ competencies. These approaches do not take into account the evolution of services over time and user preferences. To address these shortcomings, several approaches incorporate referral techniques to assist the discovery process. A large majority of these approaches are based on assessments of QoS properties. In practice, these assessments are rarely available. In other systems, trust relationships between users and services are used. These relationships are established based on invocations evaluations of similar services. However, invoking the same service do not necessarily mean having the same preferences. Hence, we propose, in our third approach, the use of the relations of interest between users to recommend services. The approach relies on modeling services’ ecosystem by database graphs.

This dissertation studies the factors that negatively impact the accuracy of the collaborative filtering recommendation systems based on nonnegative matrix factorization (NMF). The keystone in the recommendation system is the rating that expresses the user's opinion about an item. One of the most significant issues in the recommendation systems is the lack of ratings. This issue is called "cold-start" issue, which appears clearly with New-Users who did not rate any item and New-Items, which did not receive any rating. The traditional recommendation systems assume that users are independent and identically distributed and ignore the connections among users whereas the recommendation actually is a social activity. This dissertation aims to enhance NMF-based recommendation systems by utilizing the imputation method and limiting the errors that are introduced in the system. External information such as trust network and item categories are incorporated into NMF-based recommendation systems through the imputation. The proposed approaches impute various subsets of the missing ratings. The subsets are defined based on the total number of the ratings of the user or item before the imputation, such as impute the missing ratings of New-Users, New-Items, or cold-start users or items that suffer from the lack of the ratings. In addition, several factors are analyzed that affect the prediction accuracy when the imputation method is utilized with NMF-based recommendation systems. These factors include the total number of the ratings of the user or item before the imputation, the total number of imputed ratings for each user and item, the average of imputed rating values, and the value of imputed rating values. In addition, several strategies are applied to select the subset of missing ratings for the imputation that lead to increasing the prediction accuracy and limiting the imputation error. Moreover, a comparison is conducted with some popular methods that are in common with the proposed method in utilizing the imputation to handle the lack of ratings, but they differ in the source of the imputed ratings. Experiments on different large-size datasets are conducted to examine the proposed approaches and analyze the effects of the imputation on accuracy. Users and items are divided into three groups based on the total number of the ratings before the imputation is applied and their recommendation accuracy is calculated. The results show that the imputation enhances the recommendation system by capacitating the system to recommend items to New-Users, introduce New-Items to users, and increase the accuracy of the cold-start users and items. However, the analyzed factors play important roles in the recommendation accuracy and limit the error that is introduced from the imputation.

The main aim of the course advising system is to build a course recommendation path for students to help them plan courses to successfully graduate on time. The recommendation path displays the list of courses a student can take in each quarter from the first quarter after admission until the graduation quarter. The courses are filtered as per the student’s interest obtained from a questionnaire asked to the student. The business logic involves building the recommendation algorithm. Also, the application is functionality-tested end-to-end by using nightwatch.js which is built on top of node.js. Test cases are written for every module and implemented while building the application.

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.