Predicting Student Emotions in Computer-Human Tutoring Dialogues

By Diane J. Litman, Katherine Forbes-Riley. 2004

210 citations recorded by the source corpus.

We examine the utility of speech and lexical features for predicting student emotions in computer-human spoken tutoring dialogues. We first annotate student turns for negative, neutral, positive and mixed emotions. We then extract acoustic-prosodic features from the speech signal, and lexical items from the transcribed or recognized speech. We compare the results of machine learning experiments using these features alone or in combination to predict various categorizations of the annotated student emotions. Our best results yield a 19-36% relative improvement in error reduction over a baseline. Finally, we compare our results with emotion prediction in human-human tutoring dialogues.

Subfields: Artificial Intelligence, Social Psychology, Dialogue & Conversational AI, Sentiment & Opinion Analysis

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Saif M. Mohammad
  2. S. D’Mello
  3. Yoav Goldberg
  4. Mohit Bansal
  5. A. Graesser
  6. Jianfeng Gao
  7. Mirella Lapata
  8. Yejin Choi

In Social Psychology

  1. François Mairesse
  2. Marilyn A. Walker
  3. Saif M. Mohammad
  4. S. D’Mello
  5. Cecilia Ovesdotter Alm
  6. Justine Cassell
  7. William Yang Wang
  8. Peter D. Turney

In Dialogue & Conversational AI

  1. Marilyn A. Walker
  2. François Mairesse
  3. S. D’Mello
  4. Saif M. Mohammad
  5. A. Graesser
  6. Verena Rieser
  7. Oliver Lemon

In Sentiment & Opinion Analysis

  1. Saif M. Mohammad
  2. S. D’Mello
  3. A. Graesser

Citations in the corpus