This paper addresses an existing resource gap for studying complex emotional states when a speaker collaborates with a partner to solve a task. We present a novel dialogue resource — the MULTICOLLAB corpus — where two interlocutors, an instructor and builder, communicated through a Zoom call while sensors recorded eye gaze, facial action units, and galvanic skin response, with transcribed speech signals, resulting in a unique, heavily multimodal corpus. The builder received instructions from the instructor. Half of the builders were privately told to disobey the instructor’s directions. After the task, participants watched the Zoom recording and annotated their instances of frustration. In this study, we introduce this new corpus and perform computational experiments with time series transformers, using early fusion through time for sensor data and late fusion for speech transcripts. We then average predictions from both methods to recognize instructor frustration. Using sensor and speech data in a 4.5 second time window, we find that the fusion of both models yields 21% improvement in classification accuracy (with a precision of 79% and F1 of 63%) over a comparison baseline, demonstrating that complex emotions can be recognized when rich multimodal data from transcribed spoken dialogue and biophysical sensor data are fused.

In order to build more human-like cognitive agents, systems capable of detecting various human emotions must be designed to respond appropriately. Confusion, the combination of an emotional and cognitive state, is under-explored. In this paper, we build upon prior work to develop models that detect confusion from three modalities: video (facial features), audio (prosodic features), and text (transcribed speech features). Our research improves the data collection process by allowing for continuous (as opposed to discrete) annotation of confusion levels. We also craft models based on recurrent neural networks (RNNs) given their ability to predict sequential data. In our experiments, we find that text and video modalities are the most important in predicting confusion while the explored audio features are relatively unimportant predictors of confusion in our data.