From the same collaborative concept map experiment as Sangin et al. [2008], Liu et al. [2009] found that the gaze data of the pair is predictive of the expertise in the collaboration. The authors framed the whole interaction as a sequence of concepts looked at. The authors then use Hidden Markov Models to predict the outcome of posttest and achieved an accuracy of 96.3%.
Nüssli et al. [2009] used dual eye-tracking data to predict success in Raven 2progressive matrices and Bongard problems3. The authors used a collaborative versions of the problems, where they partitioned the problem images in a way such that the pair had to collaborate to get the correct answer. The results show that, using the gaze density and dispersion for each of the image cell, the task success could be predicted with 78% accuracy.
Jermann et al. [2010] conducted a dual eye-tracking experiment with a collaborative version of Tetris4. There were two Tetriminos falling from top of the screen which could be controlled by the two participants in the pair. The authors used social and gaze variables to predict the pair composition (expert pair, novice pair or mixed pairs). The social variables were how many times there was a conflict of interest on the stack on the bottom of the screen and how many times the players had to cross each other. The gaze variables were the proportion of gaze on the self piece, other’s piece and on the stack at the bottom. The results showed that, using these variables, the pair composition could be predicted with and accuracy of 75.28%. The following table summarises the main predictable in this section:
Table 2.2 – Gaze as a predicting variable for success and expertise in collaborative tasks
Paper Collaborative
task Predictable
Predicting feature
Stein and Brennan [2004] Program debugging Success Partners’ gaze information Sangin et al. [2008] Concept map Learning gain Gaze on KAT
Liu et al. [2009] Concept map Expertise Sequence of concepts looked at Nüssli et al. [2009] Raven Bongard puzzels Success Gaze distribution Jermann et al. [2010] Tetris Pair composition Gaze distribution and
game’s social context
2.4 Different levels of analytics using gaze
Time scales had been used to describe behaviour at various levels. Eye-trackers allow us to capture attention at a time scale that has more information content than the other measures like interface event logs, dialogues or gestures. In a controlled experiment, Lord and Levy [1994] found that, the duration of eye-fixations have duration of the order of 100 milliseconds,
2Source: "http://en.wikipedia.org/wiki/Raven’s-Progressive-Matrices"
3Source: "http://en.wikipedia.org/wiki/Bongard-problem"
Chapter 2. Related Work
which gives them a place at the lower end of cognitive behavioural band [Newell, 1994]. Cognitive behavioural bands have complex actions (e.g., reading or gestures) at the higher end. Anderson [2002] identifies cognitive modelling as bridging across the behavioural bands by taking the lower level bands into account. We will reuse the levels by Anderson [2002] to refer to the Task (where we usually measured understanding), Unit task (where we usually categorised dialogues) and Operations (where we usually collected raw data). The application of intertwining the gaze and dialogues will be presented in chapter 3.
2.4.1 Social granularity
With regards to the social unit of analysis, gaze had traditionally been used to assess individual cognition (e.g. eye-tracking studies about reading, program comprehension, etc.). However, in the context of dyadic interaction, a methodology was needed to describe collaborative gaze. Various measures of "gaze togetherness" had been used to indicate the quality of collaboration in dyadic interaction. In general, good collaboration features convergent gaze. Gaze togetherness increases significantly especially during verbal and deictic references. These measures of togetherness were, however, related to a global time scale; and did not consider the evolution of gaze focus during interaction.
There were different gaze-based measures of collaboration given by Richardson & Dale (2005), Cherubini et. al. (2008) and Pietinen et. al. (2010). Richardson & Dale (2005) used “gaze togetherness” as a notion of gaze cross recurrence (how much the participants are looking at the same object at the same time). Cherubini et. al. (2008) used eye tracking in a remote collaborative problem solving setup to detect the misunderstanding (distance between the referrers’ and the partners’ gaze points) between the collaborating (through chat) partners. Pietinen et. al. (2010) gave a new metric, to measure joint visual attention in a co-located pair programming setup, using the number of overlapping fixations and use the fixation duration of overlapping fixation for assessing the quality of collaboration. The problem with these measures was that they characterise togetherness on a global level or on an arbitrarily defined timespan (one could partition the interaction into “n” parts but these would not reflect the underlying interactive dynamics).
2.4.2 Temporal granularity
With regards to the temporal granularity of analyses, studies have emphasised on overall mea- sures of individual attention. For example, studies (Romero et.al, 2002; Bednarik & Tukiainen, 2006; Bednarik et. al., 2006; Sharif & Maletic, 2010; Hejmady & Narayanan, 2012; Pietinen et. Al., 2008; Pietinen et. Al., 2010; Bednarik & Shipolov, 2011) have reported the proportion of time that subjects spent fixating on different parts of the interface. These measures indicated overall gaze behaviour (and may be correlated with expertise), but they could not serve as real-time indicators of collaboration which could be used to provide immediate feedback. In the context of dyadic interaction, the dynamics of interaction and dialogue are important