Observing Collaboration in Small-Group Interaction

Abstract

In this study, we define and test measures that capture aspects of collaboration in interaction within groups of three participants performing a task. The measures are constructed upon turn-taking and lexical features from a corpus of triadic task-based interactions, as well as upon demographic features, and personality, dominance, and satisfaction assessments related to the corpus participants. Those quantities were tested for significant effects and correlations they have with each other. The findings indicate that determinants of collaboration are located in measures quantifying the differences among dialogue participants in conversational mechanisms employed, such as number and frequency of words contributed, lexical repetitions, conversational dominance, and in psychological and sentiment variables, i.e., the participants’ personality traits and expression of satisfaction.

Aspects of Methodology for Interaction Analysis

“…Here we describe a paradigm for interaction analysis anchored in the scrutiny of multi-modal corpora [22]. Observational is an apt single-word characterization.…”

“…The ILMT-s2s involves a map-task construction but places machine translation between speakers of English and Brazilian Portuguese, recording video, audio, text, eye movements and bio-signals [29]. The MUL-TISIMO data set includes video, audio and text of three party interactions in a collaborative task [22]. The MULTISIMO corpus was designed to make available an English corpus that would support the analysis of qualities of interaction (gaze, gesture, linguistic content) in relation to participant qualities (personality traits, as measured using the big-five personality inventory) and perception by external parties (of participant dominance and interlocutor collaboration).…”

Collaborative dialogue patterns of pair programming and their impact on programming self‐efficacy and coding performance

“…To gain better insights into the determinants of collaboration, researchers have focused on various conversational mechanisms employed during collaborative programming (Tsan et al., 2021), including analysing factors such as the number and frequency of words, the presence of lexical repetitions and the dynamics of conversational dominance (Koutsombogera & Vogel, 2019). Also, patterns were observed in the interactions of programming pairs (eg, Ruvalcaba et al., 2016; Zakaria et al., 2019).…”

Aspects of Dynamics in Dialogue Collaboration

“…In related work [25], we have analyzed the MULTISIMO corpus, identifying participants' behaviors (such as repetition and balance of contributions) and features (personality traits, derived from participation in a big-five personality trait inventory, and dominance, as assessed by independent observers) that may be understood as contributing to collaboration. We also addressed their success in the dialogue task, which, we argue, depends on attunement to popular thought and reasoning outside the confines of their own "best answers" to questions.…”