• Print
  • Mail
  • Share

Was This Helpful? 

Question: How does the scoring of Speaking questions work?


Pearson runs field testing on all questions. For the Pearson Test of English for example, about half a million responses generated by more than 10,000 native and non-native speakers with 126 different home languages were gathered. Responses are scored by humans on a number of traits (content, vocabulary, fluency, pronunciation). Based on this large amount of data, the automatic scoring system 'learns' what the correspondence is between characteristics of the responses and the human scores that are awarded to these responses. Once the machine has been trained, it can independently score responses that were not used in the training. These independent machine-generated scores are then compared with the human scores awarded to these responses. If they correlate high enough, the automatic scoring system is considered to be sufficiently accurate.

Copyright 2021 Pearson Education Limited   |   Terms and Conditions   |   Credits   |    Cookie Policy   |   Google Translation    |    Privacy Notice