Linguistic entrainment, the phenomena whereby dialogue partners speak more similarly to each other in a variety of dimensions, is key to the success and naturalness of interactions. While there is considerable evidence for both lexical and acoustic-prosodic entrainment, little work has been conducted to investigate the relationship between these two different modalities using the same measures in the same dialogues, specifically in multi-party dialogue. In this paper, we measure lexical and acoustic-prosodic entrainment for multi-party teams to explore whether entrainment occurs at multiple levels during conversation and to understand the relationship between these two modalities.

When interacting individuals entrain, they begin to speak more like each other. To support research on entrainment in cooperative multi-party dialogues, we have created a corpus where teams of three or four speakers play two rounds of a cooperative board game. We describe the experimental design and technical infrastructure used to collect our corpus, which consists of audio, video, transcriptions, and questionnaire data for 63 teams (47 hours of audio). We illustrate the use of our corpus as a novel resource for studying team entrainment by 1) developing and evaluating teamlevel acoustic-prosodic entrainment measures that extend existing dyad measures, and 2) investigating relationships between team entrainment and participation dominance.

No abstract

Abstract. In analytical writing in response to text, students read a complex text and adopt an analytic stance in their writing about it. To evaluate this type of writing at scale, an automated approach for Response to Text Assessment (RTA) is needed. With the long-term goal of producing informative feedback for students and teachers, we design a new set of interpretable features that operationalize the Evidence rubric of RTA. When evaluated on a corpus of essays written by students in grades 4-6, our results show that our features outperform baselines based on well-performing features from other types of essay assessments.

This paper proposes a new weighting method for extending a dyad-level measure of convergence to multi-party dialogues by considering group dynamics instead of simply averaging. Experiments indicate the usefulness of the proposed weighted measure and also show that in general a proper weighting of the dyadlevel measures performs better than nonweighted averaging in multiple tasks.