Browsing by Subject "Human-computer interaction"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    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.
  • Thumbnail Image
    Item
    Interactions Between Cancer Patients In An online Health Community
    (2020-06) Dow, Marco
    Many people who have cancer use online health communities as a space to support one another during the course of their illness. The different kinds of support that people seek out can change over time. In this study, we employ a taxonomy to categorize the different phases that people with cancer experience in order to explore the ways that cancer patients interact with each other on a specific online health community. We focus specifically on when and with whom users interact with and how that changes across different phases in the cancer journey. We find that being in the same phase does not predict whether one user will interact with another user, which implies that there are other dynamics involved. One of the dynamics that we find is that community members who no longer have evidence of disease interact more frequently with new members who have been recently diagnosed, which aligns with prior work on the subject of mentorship. We connect these findings to implications for design of online health communities and directions for future research in this area.
  • Thumbnail Image
    Item
    Maintaining the efficiency of open production systems at scale: a case study of Wikipedia
    (2013-12) Halfaker, Aaron
    This dissertation represents an exploration of the function and failures of critical subsystems in open production communities with Wikipedia as a case study. Specifically, I explore the nature of rejection via Wikipedia's informal, post-hoc quality control system and identify a consistent ownership bias that undermines Wikipedia's ethos of openness. I also quantify an inherent trade-off between the speed and efficiency of quality control in Wikipedia and the motivation of rejected contributors -- especially new editors. I then proceed to show how Wikipedia's shifting focus on quality control and formal process has led to a dramatic decline in the rate of retention of desirable new editors that threatens the long-term viability of the project.In light of these results, I present studies of two experimental software systems intended to explore potential solutions to this steady decrease in participation. First I draw on social learning theory to evaluate the effectiveness of a new mode of peripheral participation through reader-submitted feedback. I experimentally demonstrate effective strategies for increasing the rate of contributions without decreasing quality and argue for efficient moderation support in order to make quality control worth volunteer time spent away from editing the encyclopedia. Next, I describe the design and three month field study of a new intelligent software system intended to both efficiently support socialization practices in Wikipedia and bring visibility to the systemic problems that lead to declining newcomer retention. I show evidence that the system works in both regards: critical newcomer socialization activities are made dramatically more efficient and users of the system reflect openly on the breakdowns in Wikipedia's quality control processes.This work has already had impact within the Wikipedia community and in directing the strategy employed by the Wikimedia Foundation in designing and evaluating new software for Wikipedia editors.
  • Thumbnail Image
    Item
    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.