# Detecting and Gauging Impact on Wikipedia Page Views

## TL;DR

This paper develops time-series models to detect significant changes in Wikipedia page views caused by external campaigns or events, demonstrating effectiveness for some cases but not all.

## Contribution

It introduces models for predicting Wikipedia page view impacts of external events, with a focus on impact detection and cross-geography utility.

## Key findings

- Models successfully estimated impact of page preview feature rollout.
- Models did not detect significant change from the Hindi Wikipedia awareness campaign.
- Discussed potential for using other geographies or language editions for prediction.

## Abstract

Understanding how various external campaigns or events affect readership on Wikipedia is important to efforts aimed at improving awareness and access to its content. In this paper, we consider how to build time-series models aimed at predicting page views on Wikipedia with the goal of detecting whether there are significant changes to the existing trends. We test these models on two different events: a video campaign aimed at increasing awareness of Hindi Wikipedia in India and the page preview feature roll-out---a means of accessing Wikipedia content without actually visiting the pages---on English and German Wikipedia. Our models effectively estimate the impact of page preview roll-out, but do not detect a significant change following the video campaign in India. We also discuss the utility of other geographies or language editions for predicting page views from a given area on a given language edition.