Investigating the Tradeoffs of Everyday Text-Entry Collection Methods

Typing on mobile devices is a common and complex task. The act of typing itself thereby encodes rich information, such as the typing method, the context it is performed in, and individual traits of the person typing. Researchers are increasingly using a selection or combination of experience sampling and passive sensing methods in real-world settings to examine typing behaviours.

However, there is limited understanding of the effects these methods have on measures of input speed, typing behaviours, compliance, perceived trust and privacy. In this paper, we investigate the tradeoffs of everyday data collection methods. We contribute empirical results from a four-week field study (N=26). Here, participants contributed by transcribing, composing, passively having sentences analyzed and reflecting on their contributions. We present a tradeoff analysis of these data collection methods, discuss their impact on text-entry applications, and contribute a flexible research platform for in the wild text-entry studies.

Everyday text-entry collection from real world settings is a contested space. While these datasets hold untold opportunities for researchers in mobile interaction design, linguists, biometrics and digital health, they are simultaneously viewed as highly sensitive and private information by the device users.

Prior studies have commonly adopted one of two distinct strategies when approaching everyday text-entry collection, Experience Sampling with frequent prompts and requests for participants to complete prescribed text input tasks; and Passive Sensing of natural device usage through invasive or restrictive logging of all user interactions with the keyboard. Both methods require a degree of compromise with respect to study design or participant acceptance and compliance, yet no prior works have reported on the tradeoffs of the text-entry collection methods.

In this paper we present Wildkey, an experimental research platform, including a mobile keyboard, to support in the wild text-entry data collection using a combination of Experience Sampling and Passive Sensing. Through a four week study with 26 participants we investigated the tradeoffs of text-entry collections methods.

We reported on our empirical evaluation that quantitatively and qualitatively compares the compliance & data collection coverage, user’s typing performance, and user experience & acceptability of these two methods.

Our results revealed that everyday text-entry collection methods not only had a significant effect on the typing dynamics and behaviours, but also impacted on the participants willingness to engage or trust research studies adopting these methods. Through this work we offer novel understandings of the tradeoffs between data collection methods that can inform the future design of everyday text-entry studies, and provide new guidance and practical approaches to improve the user acceptability of collecting data.