Group formation is an important and challenging element for designing successful CSCL scenarios. Despite efforts
from the scientific community in developing more effective algorithms to support group formation processes, we
still face problems related to learners’ resistance and demotivation towards group work. In this sense, diverse
studies highlight the importance of considering learners’ personality traits to form groups, since this factor can
influence students’ performance and induce diverse actions and behaviors in group work. Therefore, this paper
presents G-FusionPT (Group Formation USIng Ontology and Personality Trait), a group formation algorithm that
support new learning roles, denominated Affective Collaborative Learning roles, based on relation between
collaborative learning theories and students’ personality traits. The algorithm is based on a collaborative ontology
to understand the learning theories (e.g., context, learning activities, group structure), and learners profile to
understand learners’ needs (e.g., target/current knowledge/skill). To evaluate the algorithm, we used a 300 student
simulated sample with varying group size (three, five, and seven members), and compared G-FusionPT results to
other group formation algorithms: G-Fusion (based specifically on collaborative learning theories) and Random
(no strategy or criterion). The results demonstrated the effectiveness of G-FusionPT against G-Fusion and Random
algorithms, as it generated the highest average percentage of learners in well-formed groups and lowest average
percentage of learners in unfit groups.
PEREIRA, R. C ; LYRA, KAMILA ; DUQUE GONCALVES REIS, CLAUSIUS ; Penteado, Bruno Elias ;
ISOTANI, SEIJI .
The Use of Personality Traits to Enhance Theory-driven Group
Formation. Revista Brasileira de Informática na Educação (RBIE), v. 28,
p. 796-818, 2020.
DOI:
http://dx.doi.org/10.5753/rbie.2020.28.0.796