Using the Tablet Gestures and Speech of Pairs of Students to Classify Their Collaboration

Abstract

This thesis is an initial test of the hypothesis that superficial measures suffice for measuring collaboration among pairs of students solving complex math problems, where the degree of collaboration is categorized at a high level. Data were collected in the form of logs from students' tablets and the vocal interaction between pairs of students.Thousands of different features were defined, and then extracted computationally from the audio and log data. Human coders used richer data (several video streams) and a thorough understand of the tasks to code episodes as collaborative, cooperative or asymmetric contribution. Machine learning was used to induce a detector, based on random forests, that outputs one of these three codes for an episode given only a characterization of the episode in terms of superficialfeatures. An overall accuracy of 92.00% (kappa = 0.82) was obtained when comparing the detector's codes to the humans' codes. However, due irregularities in running the study (e.g., the tablet software kept crashing), these results should be viewed as preliminary.

Temporal analysis of multimodal data to predict collaborative learning outcomes

“…From these data streams, a wide range of higher level features can be inferred including affect, attention, cognitive processing, stress and fatigue. Thus, MMLA may be applicable in a wide range of educational contexts including face-to-face interactions without technological aids (Di Mitri et al, 2017;Pijeira-Díaz, Drachsler, Kirschner, & Järvelä, 2018;Spikol et al, 2018), face-to-face technology enhanced learning (Liu et al, 2016;Viswanathan & VanLehn, 2017b) and online learning (Le, Pardos, Meyer, & Thorp, 2018). Within MMLA, many different combinations of data streams have been explored but it is not clear what makes the different combinations impactful for collaborative learning.…”

Quantifying Collaboration Quality in Face-to-Face Classroom Settings Using MMLA

“…Researchers have investigated the problem of estimating collaboration into a limited set of categories, in various settings: pair-programming [4], project-based learning [12], and tabletop-based collaborative learning [8]. These studies collected data through different means (audio [1,13], Kinect sensors [4], system logs [7,13], and video [13]) and extracted a wide variety of features from them, e.g. : non-verbal features like MFCC features, energy [1]; or spatial and dynamic features like hand movement or distance between learners [12].…”

“…: non-verbal features like MFCC features, energy [1]; or spatial and dynamic features like hand movement or distance between learners [12]. These features were in turn used to estimate different aspects of the collaboration process: collaboration quality [1,13,8], or success in collaboration [12]. Certain studies [4,13,8] have included data from both physical and digital spaces to investigate collaboration behavior.…”

“…Aware of this limitation, the field of Multimodal Learning Analytics (MMLA) [2] emerged with the goal of understanding learning through multimodal data from digital and physical spaces. Recent MMLA studies showed that it is feasible to estimate collaboration aspects categorically (e.g., high vs. low collaboration) in face-to-face settings by combining physical and digital activity traces [12,13]. In addition, researchers have found verbal interactions and speaking activity features as an important indicator for collaboration behavior [1,7].…”

Monitorización de la cooperación alcanzada y estimación del rendimiento en trabajos en equipo

“…La duración de las actividades colaborativas a evaluar es un aspecto de suma importancia, ya que condiciona en gran medida las interacciones entre los estudiantes (Viswanathan, 2017). Gran parte de los estudios que podemos encontrar en la literatura corresponden a actividades colaborativas en el ámbito de una sesión docente, es decir, en torno a una hora.…”