In this paper, we compare a manual assembly task communicated to workers using both printed and robot-delivered instructions. The comparison was made using physiological signals (blood volume pulse (BVP) and electrodermal activity (EDA)) collected from individuals during an experimental study. In addition, we also collected responses of individuals using the NASA Task Load Index (TLX) survey. Furthermore, we mapped the collected physiological signals to the responses of participants for NASA TLX to predict their workload. For both the classification problems, we compare the performance of Convolutional Neural Networks (CNNs) and Long-Short-Term Memory (LSTM) models. Results show that for our CNN-based approach using multimodal data (both BVP and EDA) gave better results than using just BVP (approx. 8.38% more) and EDA (approx 20.49% more). Our LSTM-based model too had better results when we used multimodal data (approx 8.38% more than just BVP and 6.70% more than just EDA). Overall, CNNs performed better than LSTMs for classifying physiologies for paper vs robot-based instruction by 7.72%. The CNN-based model was able to give better classification results (approximately 17.83% more on an average across all responses of the NASA TLX) within a few minutes of training compared to the LSTM-based models.