Keystroke Dynamics as Part of Lifelogging

Abstract

In this paper we present the case for including keystroke dynamics in lifelogging. We describe how we have used a simple keystroke logging application called Loggerman, to create a dataset of longitudinal keystroke timing data spanning a period of more than 6 months for 4 participants. We perform a detailed analysis of this data by examining the timing information associated with bigrams or pairs of adjacently-typed alphabetic characters. We show how there is very little day-on-day variation of the keystroke timing among the top-200 bigrams for some participants and for others there is a lot and this correlates with the amount of typing each would do on a daily basis. We explore how daily variations could correlate with sleep score from the previous night but find no significant relationship between the two. Finally we describe the public release of this data as well including as a series of pointers for future work including correlating keystroke dynamics with mood and fatigue during the day.

An Investigation into Keystroke Dynamics and Heart Rate Variability as Indicators of Stress

“…We are severely constrained here because whatever keystroke timing information is extracted from raw timing data, can only be from within a 5-minute window as that is the standard duration for calculating shortterm HRV values [13]. We know that each individual has unique timing habits for their typing [17] and it may be that instead of choosing the same top-10 most frequently used bigrams from Norvig's analysis, a different subset might be appropriate for each user.…”

“…This is not completely reliable since humans have a tendency to mis-report, for various reasons. More recently, [17], analysed variations in keystroke dynamics with respect to the previous day's sleep score for participants but could not find any significant relationship between the two.…”

An Investigation into Keystroke Dynamics and Heart Rate Variability as Indicators of Stress

“…We are severely constrained here because whatever keystroke timing information is extracted from raw timing data, can only be from within a 5-minute window as that is the standard duration for calculating short-term HRV values [13]. We know that each individual has unique timing habits for their typing [17] and it may be that instead of choosing the same top-10 most frequently used bigrams from Norvig's analysis, a different subset might be appropriate for each user.…”

“…This is not com-pletely reliable since humans have a tendency to mis-report, for various reasons. More recently, [17], analysed variations in keystroke dynamics with respect to the previous day's sleep score for participants but could not find any significant relationship between the two.…”

Managing Personal Information

“…In its most extreme form this is known as lifelogging [3] and can include capturing data from physiological sensors which monitor our heart rate and HRV, stress, blood pressure, body temperature, to wearable cameras and sound recorders, to location trackers and activity monitors, to wearable cameras from which we can deduce our activities and the company we keep. Lifelogging can also include recording the footprints of our online activities on our phones and computers including pages browsed, emails sent/read, documents written or read, even the timing of our keystrokes as we type [13]. We we have shown in some of our previous work, this data, when cleaned, integrated and analysed can be used to indicate shifts in our everyday behaviour [5], as a memory prosthetic for our forgetfulness [12] or to generate a visual summary or reflection on past events in our lifetimes [6].…”