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.

Ever since the rapid growth of the Internet, recommender systems have become essential in helping online users to search and retrieve relevant information they need. Just like the situation that people rely heavily on recommendation in their daily decision making processes, online users may identify desired documents more effectively and efficiently through recommendation of other users who exhibit similar interests, and/or through extracting crucial features of the users¡¦ past preferences. Typical recommendation approaches can be classified into collaborative filtering and content-based filtering. Both approaches, however, have their own drawbacks. The purpose of this research is thus to propose a hybrid approach for text recommendations. We combine collaborative input and document content to facilitate the creation of extended content-based user profiles. These profiles are then rearranged with the technique of latent semantic indexing. Two experiments are conducted to verify our proposed approach. The objective of these experiments is to compare the recommendation results from our proposed approach with those from the other two approaches. The results show that our approach is capable of distinguishing different degrees of document preference, and makes appropriate recommendation to users or does not make recommendation to users for uninterested documents. The application of our proposed approach is justified accordingly.

Στις μέρες μας η χρήση των κινητών συσκευών έχει σημειώσει αλματώδη ανάπτυξη και έχει γίνει αναπόσπαστο κομμάτι της καθημερινότητάς μας. Οι κινητές συσκευές με το πλήθος διαθέσιμων εφαρμογών και δυνατοτήτων που διαθέτουν, καθώς και με τη δυνατότητα πρόσβασης στο Διαδίκτυο, τείνουν να αντικαταστήσουν τους ηλεκτρονικούς υπολογιστές καθώς και μια πληθώρα άλλων συσκευών. Στην παρούσα μεταπτυχιακή διπλωματική εργασία προτείνουμε και υλοποιούμε ένα σύστημα, το οποίο κινείται στα πλαίσια των τεχνολογιών κινητού υπολογισμού και σχεδιάστηκε για να χρησιμοποιείται από τους χρήστες προκειμένου να δέχονται προτάσεις προς επιλογή σχετικά με ταινίες. Το σύστημα αποτελείται από μία κινητή συσκευή η οποία επικοινωνεί με μια οντολογία με χρήση της τεχνολογίας των web services. Όταν ο χρήστης συνδέεται στο λογαριασμό του έχει τη δυνατότητα να πραγματοποιήσει δύο διαδικασίες οι οποίες λειτουργούν με διαφορετικό αλγόριθμο συστάσεων. Στόχος μας είναι να ελέγξουμε κατά πόσο ένα σύστημα συνεργατικών συστάσεων είναι πιο αποδοτικό από ένα σύστημα που λαμβάνει υπόψη το προσωπικό προφίλ ενός χρήστη. Στην παρούσα περίπτωση διαλέξαμε έναν συγκεκριμένο αριθμό ταινιών με παρόμοιο κριτήριο για χρονολογίες από το 2006 έως το 2014. Εφαρμόσαμε τον αλγόριθμο συνεργατικής σύστασης για ταινίες από το 2006 έως το 2010 και τον αλγόριθμο που βασίζεται στο προφίλ μόνο του συνδεδεμένου χρήστη για ταινίες από το 2011 έως το 2014 λαμβάνοντας μια αξιολόγηση για το καθένα. / Nowadays, the use of mobile devices has rapidly developed and has become an integral part of our daily lives. Mobile devices have now a great number of applications and features available, along with the internet accessibility, they tend to replace not only computers but also a variety of other devices. In this master thesis, we propose and implement a system that runs in the context of mobile computing technologies and is designed to be used in order to present to the user all the recommended for him movies. This program consists of a mobile device that communicates with an ontology through a web service. When the user signs in to his account, has the ability to hold two processes each one operating with a different recommendation engine. Our intention is to check whether a collaborative recommendation engine is more efficient than a system which takes into account only the personal profile of a user. In this case study we chose a certain number of films based on a standard for a period of time, from 2006 to 2014. We applied the collaborative recommendation engine to movies from 2006 to 2010 and the algorithm based on the profile of the user signed–into movies released from 2011 to 2014 taking an assessment for each.

Given the proliferation of new-generation internet capable devices in our society, they are now commonly used for a variety of purposes and by a variety of ages, including young children. The vast amount of new media content, available through these devices, cause parents to worry about what their children have access to. In this thesis we investigated how parents and children can work together towards the goal of content control and filtering. One problem to the current content control filtering tools and approaches is that they do not involve children in the filtering process, thus missing an opportunity of educating children about content appropriateness. Therefore, we propose a kid-in-the-loop approach to content control and filtering where parents and children collaboratively configure restrictions and filters, an approach that focuses on education rather than simple rule setting. We conducted an exploratory qualitative study with results highlighting the importance that parents place on avoiding inappropriate content. Building on these findings, we designed an initial kid-in-the-loop prototype which allows parents to work with their children to select appropriate applications, providing parents with the opportunity to educate their children on what they consider to be appropriate or inappropriate. We further validate our proposed approach by conducting a qualitative study with sets of parents and children in the six to eight year-old age group, which revealed an overwhelmingly favorable response to this approach. We conclude this thesis with a comprehensive analysis of our approach, which can be leveraged in designing content control systems targeting both parents and children.

Recommendation systems have become extremely common in recent years due to the ubiquity of information across various applications. Online entertainment (e.g., Netflix), E-commerce (e.g., Amazon, Ebay) and publishing services such as Google News are all examples of services which use recommender systems. Recommendation systems are rapidly evolving in these years, but these methods have fallen short in coping with several emerging trends such as likes or votes on reviews. In this work we have proposed a new method based on collaborative filtering by considering other users' feedback on each review. To validate our approach we have used Yelp data set with more than 335,000 product and service category ratings and 70,817 real users. We present our results using comparative analysis with other well-known recommendation systems for particular categories of users and items. / Graduate / 0984 / 0800 / yheshmat@uvic.ca

This thesis describes the process of conceptualizing and developing a recommendersystem for a peer-to-peer commerce application. The application in question is calledPlick and is a vintage clothes marketplace where private persons and smaller vintageretailers buy and sell secondhand clothes from each other. Recommender systems is arelatively young field of research but has become more popular in recent years withthe advent of big data applications such as Netflix and Amazon. Examples ofrecommender systems being used in e-marketplace applications are however stillsparse and the main contribution of this thesis is insight into this sub-problem inrecommender system research. The three main families of recommender algorithmsare analyzed and two of them are deemed unfitting for the e-marketplace scenario.Out of the third family, collaborative filtering, three algorithms are described,implemented and tested on a large subset of data collected in Plick that consistsmainly of clicks made by users on items in the system. By using both traditional andnovel evaluation techniques it is further shown that a user-based collaborative filteringalgorithm yields the most accurate recommendations when compared to actual userbehavior. This represents a divergence from recommender systems commonly usedin e-commerce applications. The paper concludes with a discussion on the cause andsignificance of this difference and the impact of certain data-preprocessing techniqueson the results.

No description available.

This study was conducted to investigate how well deep learning can be applied to the field of tag recommender systems. In the context of an image item, tag recommendations can be given based on tags already existing on the item, or on item content information. In the current literature, there are no works which jointly models the tags and the item content information using deep learning. Two tag recommender systems were developed. The first one was a highly optimized hybrid baseline model based on matrix factorization and Bayesian classification. The second one was based on deep learning. The two models were trained and evaluated on a dataset of user-tagged images and videos from Flickr. A percentage of the tags were withheld, and the evaluation consisted of predicting them. The deep learning model attained the same prediction recall as the baseline model in the main evaluation scenario, when half of the tags were withheld. However, the baseline model generalized better to the sparser scenarios, when a larger number of tags were withheld. Furthermore, the computations of the deep learning model were much more time-consuming than the computations of the baseline model. These results led to the conclusion that the baseline model was more practical, but that there is much potential in using deep learning for the purpose of tag recommendation. / Den här studien genomfördes i syfte att undersöka hur effektivt djupinlärning kan användas för att konstruera rekommendationssystem för taggar. När det gäller bildobjekt så kan taggar rekommenderas baserat på taggar som redan förekommer på objektet, samt på information om objektet. I dagens forskning finns det inte några publikationer som presenterar ett rekommendationssystem baserat på djupinlärning som bygger på att gemensamt använda taggarna och objektsinformationen. I studien har två rekommendationssystem utvecklats. Det första var en referensmodell, ett väloptimerat hybridsystem baserat på matrisfaktorisering och bayesiansk klassificering. Det andra systemet baserades på djupinlärning. De två modellerna tränades och utvärderades på en datamängd med bilder och videor taggade av användare från Flickr. En procentandel av taggarna var undanhållna, och utvärderingen gick ut på att förutsäga dem. Djupinlärningsmodellen gav förutsägelser av samma kvalitet som referensmodellen i det primära utvärderingsscenariot, där hälften av taggarna var undanhållna. Referensmodellen gav dock bättre resultat i de scenarion där alla eller nästan alla taggar var undanhållna. Dessutom så var beräkningarna mycket mer tidskrävande för djupinlärningsmodellen jämfört med referensmodellen. Dessa resultat ledde till slutsatsen att referensmodellen var mer praktisk, men att det finns mycket potential i att använda djupinlärningssystem för att rekommendera taggar.

Detta dokument presenterar implementeringen av ett rekommendationssystem för tjänstebokningssidan Boka.se. Rekommendationssystem omfattar mjukvaruverktyg och teknik för att generera förslag till en användare enligt deras preferenser och förekommer ofta på e-handelssidor. Baserat på användarens feedback kan det föreslagna rekommendationssystemet generera förslag för tjänster som passar dem. Det här dokumentet ger en översikt över rekommendationssystem och visar implementeringen av ett user-based collaborative filtering system, baserat på en data som tillhandahålls av tjänstbokningssidan Boka.se. Den beskriver också olika fallgropar och begränsningar för att skapa ett rekommendationssystem baserat på data som inte har några identifierande attribut för varken användare eller objekt.

Modelos baseados em fatoração de matrizes estão entre as implementações mais bem sucedidas de Sistemas de Recomendação. Neste projeto, estudamos as possibilidades de incorporação de informações provindas de redes sociais, para melhorar a qualidade das predições do modelo tanto em modelos tradicionais de Filtragem Colaborativa, quanto em Filtragem Colaborativa Neural. / Models based on matrix factorization are among the most successful implementations of Recommender Systems. In this project, we study the possibilities of incorporating the information from social networks to improve the quality of predictions of the model both in traditional Collaborative Filtering and in Neural Collaborative Filtering.