34 research outputs found
The relationship between actions and significance of email
No full textThesis: S.M., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019Cataloged from PDF version of thesis.Includes bibliographical references (pages 51-53).Email remains a critical channel for communicating information in both personal and work accounts. The number of emails people receive every day can be overwhelming, which in turn creates challenges for efficient information management and consumption. Having a good estimate of the significance of emails forms the foundation for many downstream tasks (e.g. email prioritization); but determining significance at scale is expensive and challenging. In this thesis, we hypothesize that the cumulative set of actions on any individual email can be considered as a proxy for the perceived significance of that email. We propose two approaches to summarize observed actions on emails, which we then evaluate against the perceived significance. The first approach is a fixed-form utility function parameterized on a set of weights, and we study the impact of different weight assignment strategies. In the second approach, we build machine learning models to capture users' significance directly based on the observed actions. For evaluation, we collect human judgments on email significance for both personal and work emails. Our analysis suggests that there is a positive correlation between actions and significance of emails and that actions performed on personal and work emails are different. We also find that the degree of correlation varies across people, which may reflect the individualized nature of email activity patterns or significance. Subsequently, we develop an example of real-time email significance prediction by using action summaries as implicit feedback at scale. Evaluation results suggest that the resulting significance predictions have positive agreement with human assessments, albeit not at statistically strong levels. We speculate that we may require personalized significance prediction to improve agreement levels.by Tarfah Alrashed.S.M.S.M. Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Scienc
Systems to Democratize and Standardize Access to Web APIs
No full textToday, many websites offer third-party access to their data through web APIs. However, manually encoding URLs with arbitrary endpoints, parameters, authentication handshakes, and pagination, among other things, makes API use challenging and laborious for programmers and untenable for novices. In addition, each API offers its own idiosyncratic data model, properties, and methods that a new user must learn, even when the sites manage the same common types of information as many others.
In this thesis, I show how working with web APIs can be dramatically simplified by describing these APIs using a simple machine-readable ontology. I present a number of systems that can use these descriptions to access arbitrary APIs on the web. The first system lets users query and download data from any described web API. The second system exposes data behind web APIs as connected objects with standard types, allowing users to create interactive web applications that operate on the data accessible through these APIs. And the last system creates bridges between many heterogeneous types of data from different websites, allowing users to link and interact with data drawn from multiple web APIs simultaneouslyPh.D
Extending a Reactive Expression Language with Data Update Actions for End-User Application Authoring
No full textMavo is a small extension to the HTML language that empowers non-programmers to create simple web applications. Authors can mark up any normal HTML document with attributes that specify data elements that Mavo makes editable and persists. But while applications authored with Mavo allow users to edit individual data items, they do not offer any programmatic data actions that can act in customizable ways on large collections of data simultaneously or that modify data according to a computation. We explore an extension to the Mavo language that enables non-programmers to author these richer data update actions. We show that it lets authors create a more powerful set of applications than they could previously, while adding little additional complexity to the authoring process. Through user evaluations, we assess how closely our data update syntax matches how novice authors would instinctively express such actions, and how well they are able to use the syntax we provided
ScrAPIr: Making Web Data APIs Accessible to End Users
No full textUsers have long struggled to extract and repurpose data from websites by laboriously copying or scraping content from web pages. An alternative is to write scripts that pull data through APIs. This provides a cleaner way to access data than scraping; however, APIs are effortful for programmers and nigh-impossible for non-programmers to use. In this work, we empower users to access APIs without programming. We evolve a schema for declaratively specifying how to interact with a data API. We then develop ScrAPIr: a standard query GUI that enables users to fetch data through any API for which a specification exists, and a second GUI that lets users author and share the specification for a given API. From a lab evaluation, we find that even non-programmers can access APIs using ScrAPIr, while programmers can access APIs 3.8 times faster on average using ScrAPIr than using programming
Extending a Reactive Expression Language with Data Update Actions for End-User Application Authoring
No full text
Relationships are Complicated! An Analysis of Relationships Between Datasets on the Web
Get PDFThe Web today has millions of datasets, and the number of datasets continues to grow at a rapid pace. These datasets are not standalone entities; rather, they are intricately connected through complex relationships. Semantic relationships between datasets provide critical insights for research and decision-making processes. In this paper, we study dataset relationships from the perspective of users who discover, use, and share datasets on the Web: what relationships are important for different tasks? What contextual information might users want to know? We first present a comprehensive taxonomy of relationships between datasets on the Web and map these relationships to user tasks performed during dataset discovery. We develop a series of methods to identify these relationships and compare their performance on a large corpus of datasets generated from Web pages with schema.org markup. We demonstrate that machine-learning based methods that use dataset metadata achieve multi-class classification accuracy of 90%. Finally, we highlight gaps in available semantic markup for datasets and discuss how incorporating comprehensive semantics can facilitate the identification of dataset relationships. By providing a comprehensive overview of dataset relationships at scale, this paper sets a benchmark for future research
