Browsing by Subject "Recommender systems"

Now showing 1 - 5 of 5

Collaborative curation in social production communities.
(2012-08) Lam, Shyong (Tony) K.
The use of social production communities (SPCs) has become a common approach for building information repositories such as Wikipedia, Yahoo! Answers, and YouTube. In these systems, communities of users collaborate to produce a shared repository of information. We define collaborative curation as the tasks performed by these communities, and the processes, workflows, and policies that guide how users work together. This thesis seeks to study the implications of different curation processes, and the challenges that SPCs face in constructing information repositories. Our goal is to better understand the growth and evolution of SPC information repositories so that we can inform the design of SPCs. The first part of this thesis focuses on collaborative curation practices at a high level to learn about the design space of curation mechanisms and the impact that different mechanisms have on the evolution of SPCs. We begin with an analysis ofWikipedia’s curation practices, studying how Wikipedia’s editors decide which articles merit inclusion in the encyclopedia, and how the encyclopedia has grown over the years. We then conduct a user study using the MovieLens recommender system to compare two typical curation mechanisms – a wiki-like process, and a social voting process – in how they affect the growth of MovieLens’ movie database. In the second part of this thesis, our focus shifts to challenges that SPCs face in collaborative curation. We start by looking at how skews in group composition can influence collaborative curation. SPCs typically rely on the efforts of self-formed and self-organized volunteer groups. Such groups may differ from the larger user community or from the general populace on multiple dimensions, including demographics, attitudes, and experience. We conduct two studies to study these differences in the context of Wikipedia. At the small-scale level, we examine how composition skews in small working groups can affect curation decision quality; at the large-scale level, we explore an apparent gender disparity amongst Wikipedia’s community of editors. We close with an analysis of a type of malicious deviant behavior where users submit false data to an SPC in an attempt to manipulate choices made by fellow users.
Intelligent tagging systems: machine learning for novel systems: machine learning for novel.
(2012-04) Vig, Jesse
The Web puts a vast repository of information at users' fingertips, but the size and complexity of this information space can easily overwhelm users. Recommender systems and tagging systems represent two very different approaches to addressing this information overload. Recommender systems use machine learning and statistical models to automatically retrieve the items of most interest to a particular user. Tagging systems leverage the community's collective knowledge to help users explore the information space themselves. While both approaches can be very effective, they each have limitations. Recommender systems require little effort from users, but they leave users with little control over the recommendation process. Tagging systems put control in the hands of the user, but -- because tags are applied by humans -- tagging systems often suffer from issues of tag sparsity. This thesis explores intelligent tagging systems that combine the machine intelligence of recommender systems with the user control and comprehensibility of tagging systems. We first present Tagsplanations, tag-based explanations that help users understand why an item was recommended to them. We then introduce the Tag Genome, a novel data structure that uses machine learning to augment human judgments of the relationships between tags and items. Next we discuss Movie Tuner, a conversational recommender system based on the Tag Genome that enables users to provide multifaceted feedback using tags. For each system, we outline the design space of the problem and discuss our design decisions. We evaluate each system using both offline analyses as well as field studies involving thousands of users from MovieLens, a movie recommender system that also supports tagging of movies. Finally, we draw conclusions for the broader space of related applications.
Machine learning methods for recommender systems
(2015-02) Kabbur, Santosh
This thesis focuses on machine learning and data mining methods for problems in the area of recommender systems. The presented methods represent a set of computational techniques that produce recommendation of items which are interesting to the target users. These recommendations are made from a large collection of such items by learning preferences from their interactions with the users. This thesis addresses the two primary tasks in recommender systems, namely top-N recommendation and rating prediction. Following methods are developed, (i) an item-based method (FISM) for generating top-N recommendations that learn the item-item similarity matrix as the product of two low dimensional latent factor matrices. These matrices are learned using a structural equation modeling approach, wherein the value being estimated is not used for its own estimation. Since, the effectiveness of existing top-N recommendation methods decreases as the sparsity of the datasets increases, FISM is developed to alleviate the problem of data sparsity, (ii) a new user modeling approach (MPCF), that models the users preference as a combination of global preference and local preference components. Using this user modeling approach, two different methods are proposed based on the manner in which the global preference and local preferences components interact. In the first approach, the global component models the user's common strong preferences on a subset of item features, while the local preferences component models the tradeoffs the users are willing to take on the rest of the item features. In the second approach, the global preference component models the user's common overall preferences on all the item features and the local preferences component models the different tradeoffs the users have on all the item features, thereby helping to fine tune the global preferences. An additional advantage of MPCF is that, the user's global preferences are estimated by taking into account all the observations, thus it can handle sparse data effectively, (iii) a new method called ClustMF which is designed to combine the benefits of the neighborhood models and the latent factor models in a computationally efficient manner. The benefits of latent factor models are utilized by modeling the users and items similar to the standard MF based methods and the benefit of neighborhood models are brought into the model, by introducing biases at the cluster level. That is, the biases for users are modeled at the item cluster level and the biases for items are modeled at the user cluster level. The item-cluster user biases model the baseline score of the user for the items similar to the active item and similarly, the user-cluster item biases model the baseline score of the item from the users similar to the active user._
Preference modeling and Accuracy in Recommender Systems
(2017-09) Sharma, Mohit
Recommender systems are widely used to recommend the most appealing items to users. In this thesis, we focus on analyzing the accuracy of the state-of-the-art matrix completion-based recommendation methods and develop methods to model users' preferences to address different problems that arise in recommender systems. Collaborative filtering-based methods are widely used to generate item recommendations to the user. The low-rank matrix completion method is the state-of-the-art collaborative filtering method. We will show that the accuracy and the ranking performance of matrix completion-based methods are affected by the skewed distribution of ratings in the user-item rating matrix. Additionally, we will illustrate that the number of ratings an item has positively correlates with the prediction accuracy and the ranking performance of the matrix completion approach for the item. Furthermore, we show that the users or the items that are present in the tail, i.e., those having few ratings in real datasets, may not have sufficient ratings to estimate the low-rank models accurately by matrix completion approach. We use these insights to develop TruncatedMF, a matrix completion-based approach that outperforms the state-of-the-art matrix completion method for the users and the items in the tail. Since for new items we do not have any prior preferences from existing users, it is hard to recommend these items to the users. We can use non-collaborative methods that rely on similarities between the new item and the items preferred by a user in the past to model the user preference for the new item. However, these methods consider the item features independently and ignore the interactions among the features of the items while computing the similarities. Modeling the interactions among features can provide more information towards the relevance of an item in comparison to the scenario when the features are considered independently. We develop a new method called User-specific Feature-based factorized Bilinear Similarity Model (UFBSM), that uses all available information across users to capture these interactions among features and learns a low-rank user personalized bilinear similarity model for the Top-n recommendation of new items. In addition to providing ratings over individual items, the users can also provide ratings on sets of items. A rating provided by a user on a set of items conveys some preference information about the items in the set and enables us to acquire a user’s preferences for more items that the number of ratings that the user provided. Moreover, users may have privacy concerns and hence may not be willing to indicate their preferences on individual items explicitly but may be willing to provide a rating to a set of items, as it provides some level of information hiding. We will investigate how do users’ item-level preferences relate to their set-level preferences. Also, we will introduce collaborative filtering-based methods that explicitly model the user behavior of providing ratings on sets of items and can be used to recommend items to users.
Towards Recommender Engineering: tools and experiments for identifying recommender differences
(2014-07) Ekstrand, Michael
Since the introduction of their modern form 20 years ago, recommender systems have proven a valuable tool for help users manage information overload.Two decades of research have produced many algorithms for computing recommendations, mechanisms for evaluating their effectiveness, and user interfaces and experiences to embody them.It has also been found that the outputs of different recommendation algorithms differ in user-perceptible ways that affect their suitability to different tasks and information needs.However, there has been little work to systematically map out the space of algorithms and the characteristics they exhibit that makes them more or less effective in different applications. As a result, developers of recommender systems must experiment, conducting basic science on each application and its users to determine the approach(es) that will meet their needs.This thesis presents our work towards \emph{recommender engineering}: the design of recommender systems from well-understood principles of user needs, domain properties, and algorithm behaviors.This will reduce the experimentation required for each new recommender application, allowing developers to design recommender systems that are likely to be effective for their particular application.To that end, we make four contributions: the LensKit toolkit for conducting experiments on a wide variety of recommender algorithms and data sets under different experimental conditions (offline experiments with diverse metrics, online user studies, and the ability to grow to support additional methodologies), along with new developments in object-oriented software configuration to support this toolkit;experiments on the configuration options of widely-used algorithms to provide guidance on tuning and configuring them; an offline experiment on the differences in the errors made by different algorithms; and a user study on the user-perceptible differences between lists of movie recommendations produced by three common recommender algorithms.Much research is needed to fully realize the vision of recommender engineering in the coming years; it is our hope that LensKit will prove a valuable foundation for much of this work, and our experiments represent a small piece of the kinds of studies that must be carried out, replicated, and validated to enable recommender systems to be engineered.

University Digital Conservancy

Browse by Subject

Browsing by Subject "Recommender systems"