Online multitasking and user engagement

Abstract

Users often access and re-access more than one site during an online session, effectively engaging in multitasking. In this paper, we study the effect of online multitasking on two widely used engagement metrics designed to capture users browsing behavior with a site. Our study is based on browsing data of 2.5M users across 760 sites encompassing diverse types of services such as social media, news and mail. To account for multitasking we need to redefine how user sessions are represented and we need to adapt the metrics under study. We introduce a new representation of user sessions: tree-streams -as opposed to the commonly used click-streams -present a more accurate picture of the browsing behavior of a user that includes how users switch between sites (e.g., hyperlinking, teleporting, backpaging). We then discuss a number of insights on multitasking patterns, and show how these help to better understand how users engage with sites. Finally, we define metrics that characterize multitasking during online sessions and show how they provide additional insights to standard engagement metrics.

Engagement Periodicity in Search Engine Usage

“…This periodicity is also detected by the periodicity patterns and is expressed by the peaks on the amplitude series at frequencies k = 4 and 8 15 . These frequencies are responsible for the weekly periodicity, as it is seen for users whose activity drops at weekends (see Fig.…”

“…Using these metrics they obtained some engagement patterns (models) of the studied web sites. The research described in [15] is also devoted to comparison of a web site group with respect to multitasking user behavior, which analysis takes into account backpaging and tab switching during a browsing session. They used the number of page views and the dwell time (the presence time on a web site), both on visit and session levels, as the main engagement metrics of user activity.…”

“…In order to describe and quantify user engagement, a series of metrics are developed. They could reflect different aspects of user engagement, from loyalty (e.g., the number of sessions per user per day [21]) to activity (e.g., the number of visited web pages [15]). …”

Future User Engagement Prediction and Its Application to Improve the Sensitivity of Online Experiments

“…Some others concerned behavioral patterns of users (e.g., simultaneous usage of several search engines [30] or periodicity of user engagement with a search engine usage [8]) and models of web sites with respect to user behavior (e.g., w.r.t. multitasking user behavior [20] or w.r.t. popularity, activity, and loyalty among users [21]).…”

Using Contextual Information to Understand Searching and Browsing Behavior

“…User engagement metrics show different aspects of user experience. For instance, they can reflect (1) user loyalty -the number of sessions per user [216], (2) user activity -the number of visited web pages [165] or the absence time [73]. The periodicity engagement metrics of user behavior, which resulted from the Discrete Fourier transform of state-of-the-art engagement measures were applied in [70].…”