Search for: All records

We investigated the generalizability of language-based analytics models across two collaborative problem solving (CPS) tasks: an educational physics game and a block programming challenge. We analyzed a dataset of 95 triads (N=285) who used videoconferencing to collaborate on both tasks for an hour. We trained supervised natural language processing classifiers on automatic speech recognition transcripts to predict the human-coded CPS facets (skills) of constructing shared knowledge, negotiation / coordination, and maintaining team function. We tested three methods for representing collaborative discourse: (1) deep transfer learning (using BERT), (2) n-grams (counts of words/phrases), and (3) word categories (using the Linguistic Inquiry Word Count [LIWC] dictionary). We found that the BERT and LIWC methods generalized across tasks with only a small degradation in performance (Transfer Ratio of .93 with 1 indicating perfect transfer), while the n-grams had limited generalizability (Transfer Ratio of .86), suggesting overfitting to task-specific language. We discuss the implications of our findings for deploying language-based collaboration analytics in authentic educational environments. 

We investigated the feasibility of using automatic speech recognition (ASR) and natural language processing (NLP) to classify collaborative problem solving (CPS) skills from recorded speech in noisy environments. We analyzed data from 44 dyads of middle and high school students who used videoconferencing to collaboratively solve physics and math problems (35 and 9 dyads in school and lab environments, respectively). Trained coders identified seven cognitive and social CPS skills (e.g., sharing information) in 8,660 utterances. We used a state-of-theart deep transfer learning approach for NLP, Bidirectional Encoder Representations from Transformers (BERT), with a special input representation enabling the model to analyze adjacent utterances for contextual cues. We achieved a microaverage AUROC score (across seven CPS skills) of .80 using ASR transcripts, compared to .91 for human transcripts, indicating a decrease in performance attributable to ASR error. We found that the noisy school setting introduced additional ASR error, which reduced model performance (micro-average AUROC of .78) compared to the lab (AUROC = .83). We discuss implications for real-time CPS assessment and support in schools.