Home // ALLDATA 2016, The Second International Conference on Big Data, Small Data, Linked Data and Open Data // View article

Combining “Small Data” from Surveys and “Big Data” from Online Experiments at Pinterest

Authors:
Jolie Martin

Keywords: Experiments; Methodology; Surveys

Abstract:
Running experiments while logging detailed user actions has become the standard way of testing product features at Pinterest, as at many other Internet companies. While this technique offers plenty of statistical power to assess the effects of product changes on behavioral metrics, it does not often give us much insight into why users respond the way they do. By combining at-scale experiments with smaller surveys of users in each experimental condition, we have developed a unique approach for measuring the impact of our product and communication treatments on user sentiment, attitudes, and comprehension.

Pages: 33 to 34

Copyright: Copyright (c) IARIA, 2016

Publication date: February 21, 2016

Published in: conference

ISSN: 2519-8386

ISBN: 978-1-61208-457-2

Location: Lisbon, Portugal

Dates: from February 21, 2016 to February 25, 2016