Exploiting biometric measurements for prediction of emotional state: A preliminary study for healthcare applications using keystroke analysis

Abstract

Biometric measurements are now often routinely adopted as a robust means of determining individual identity. Such an approach is clearly beneficial in a variety of scenarios, including those relating to medical environments. In the medical context, however, the use of biometric data can potentially offer other valuable opportunities for harnessing the power of biometrics which have a more direct bearing on healthcare monitoring and treatment delivery. In this paper we focus on the prediction of "soft" biometric data and, in particular, we describe an approach which aims to predict "higher level" characteristics about an individual, such as those which may broadly be described as emotional or mental state. We show how such a capability can be utilised in healthcare scenarios, and specifically, by presenting some initial analysis of results from newly acquired data in a keystroke-based data collection task, we identify the most crucial issues which must be addressed if our basic predictive technique is to be developed for practical viability.

Investigating the Impact of Combining Handwritten Signature and Keyboard Keystroke Dynamics for Gender Prediction

“…We can also find relevant works that use keystroke and handwriting to predict soft biometrics, instead of the conventional use as a helper on identification tasks. Thus, [15]- [17] used handwriting-based data to predict gender and [2] used keystroke and handwriting to predict emotional state. On all those cases, it was possible to predict soft-biometrics from behavioral hard biometrics.…”

Emotional State Prediction From Online Handwriting and Signature Biometrics

“…Furthermore, soft-biometrics provide predictive capabilities to higher levels of abstraction such as mental and emotional state of individuals (i.e. happy or sad, under stress or relaxed, and so on) to support applications mentioned above or analyzing individuals' activities [5]. Emotional state prediction enlightens many areas of the literature, from career counselling [6], [7], to measuring user interaction through entertainment technology [8], from early stress recognition for office environment [6] to early prediction of neurodegenerative diseases such as Alzheimer, mild cognitive impairment and dementia [9], as well as emotion prediction from keystroke dynamics [5] and many more.…”

“…happy or sad, under stress or relaxed, and so on) to support applications mentioned above or analyzing individuals' activities [5]. Emotional state prediction enlightens many areas of the literature, from career counselling [6], [7], to measuring user interaction through entertainment technology [8], from early stress recognition for office environment [6] to early prediction of neurodegenerative diseases such as Alzheimer, mild cognitive impairment and dementia [9], as well as emotion prediction from keystroke dynamics [5] and many more. In addition, predicting mental and emotional state of individuals plays a particularly important role in security and defense systems, especially given the previous airborne terrorist attacks: this is clear evidence of the failure of early detection systems in air transportation.…”

“…However, considering the higher prediction level of the soft biometric research, which is the prediction of mental and emotional state of individuals, availability of databases decreases even more considerably. For instance, such a database is publicly and commercially available for face, iris, fingerprint, gait and voice modalities which can be seen in Table 1, and only one private English database (available for the use of established institution only) is existing for handwriting [14] and keystroke [5] modalities.…”

“…The main reason behind this could be handwritten data is not frequently used for communication nowadays. However, it is still very important since both handwriting and signature is for instance widely used in digital form for determination of identity and other characteristics in forensic investigations [35]- [37] and healthcare scenarios (for instance, management of Parkinson's diseases, assessment of children with developmental coordination disorder) [5], [9], [18]. Furthermore, predicting one's emotion from handwriting and signature can even support the officers during the visa application process to detect whether the applicant is happy, sad or stressed, and a decision can be made by also taking in consideration their current emotions.…”