Systems and Methods for Assessing Structured Interview Responses
- Author(s):
- Kyllonen, Patrick C.; Chen, Lei; Martin, Michelle; Bejar, Isaac I.; Leong, Chee Wee; Gorin, Joanna S.; Williamson, David M.
- Patent Issued:
- Mar 31, 2020
- Patent Number:
- 10,607,188
- Source:
- ETS Patent
- Document Type:
- Patent
- Family ID:
- 54142487
- Subject/Key Words:
- Patent, Active Patent, Automated Scoring and Natural Language Processing, Automatic Speech Recognition, Human Scoring, Machine Learning, Computer-Implemented, Structured Interview (SI), Job Interviews, Videotape Recordings, Audiotape Recordings, Audio-Lingual Methods
Abstract
Systems and methods described herein utilize supervised machine learning to generate a model for scoring interview responses. The system may access a training response, which in one embodiment is an audiovisual recording of a person responding to an interview question. The training response may have an assigned human-determined score. The system may extract at least one delivery feature and at least one content feature from the audiovisual recording of the training response, and use the extracted features and the human-determined score to train a response scoring model for scoring interview responses. The response scoring model may be configured based on the training to automatically assign scores to audiovisual recordings of interview responses. The scores for interview responses may be used by interviewers to assess candidates.