Search for: All records

We present a generalizable classification approach that leverages Large Language Models (LLMs) to facilitate the detection of implicitly encoded social meaning in conversations. We design a multi-faceted prompt to extract a textual explanation of the reasoning that connects visible cues to underlying social meanings. These extracted explanations or rationales serve as augmentations to the conversational text to facilitate dialogue understanding and transfer. Our empirical results over 2,340 experimental settings demonstrate the significant positive impact of adding these rationales. Our findings hold true for in-domain classification, zero-shot, and few-shot domain transfer for two different social meaning detection tasks, each spanning two different corpora. 

In this study, we examine the outcome of a four-day workshop with 24 Teacher Educators (fellows) who were supported in using two tools - Teacher Moments (TM) and Eliciting Learner Knowledge (ELK). The tools are designed for authoring, implementing, and research Digital Clinical Simulations in education. The simulations centered around issues of equity in K-12 computer science education to provide in-/pre-service teachers with opportunities to practice high-stakes interactions in low-stakes settings. We operationalize the technology adoption of the fellows through the notions of self-efficacy, help-seeking, and technology concerns to recognize the potential barriers they faced in transitioning from authoring to implementing and research design. Finally, we note the fellows' implementation plans in the ensuing academic year and examine potential collaborations amongst them using social network analysis. Our results reveal how a small group of fellows, spanning major regions of the U.S., generate a broad range of scenarios, as well as clusters of scenarios, enabling simulation-based research supported by collaboration. 

The notion of face refers to the public self-image of an individual that emerges both from the individual’s own actions as well as from the interaction with others. Modeling face and understanding its state changes throughout a conversation is critical to the study of maintenance of basic human needs in and through interaction. Grounded in the politeness theory of Brown and Levinson (1978), we propose a generalized framework for modeling face acts in persuasion conversations, resulting in a reliable coding manual, an annotated corpus, and computational models. The framework reveals insights about differences in face act utilization between asymmetric roles in persuasion conversations. Using computational models, we are able to successfully identify face acts as well as predict a key conversational outcome (e.g. donation success). Finally, we model a latent representation of the conversational state to analyze the impact of predicted face acts on the probability of a positive conversational outcome and observe several correlations that corroborate previous findings.