CPC G06F 40/284 (2020.01) [G06F 40/253 (2020.01)] | 6 Claims |
1. A computer-implemented method for characterizing lexical concreteness in narrative text, the method being implemented by one or more data processors and comprising:
receiving data encapsulating narrative text having a plurality of words generated by a student in response to a prompt;
removing function words from the narrative text to result in only content words;
tagging each content word with a corresponding part-of-speech (POS) by a machine learning-based toolkit for processing of natural language text;
filtering the content words to result in only nouns, verbs, adjective, and adverbs;
first assigning, after the filtering, a concreteness score to each content word within a database by polling the database over a computer network to identify matching words and to use concreteness scores associated with such matching words as specified by the database;
second assigning a uniform concreteness score for all content words corresponding to a name and not having a match in the database, the default concreteness score being a value other than zero;
first generating concreteness scores for each of nouns, verbs, adjective, and adverbs based on the first and second assigning;
second generating an overall concreteness score based on the first and second assigning; and
providing data characterizing the generated concreteness scores for each of nouns, verbs, adjective, and adverbs and the overall concreteness score, the providing data comprising one or more of:
causing the data characterizing the generated concreteness scores to be displayed in an electronic visual display, transmitting the data characterizing the generated concreteness scores to a remote computing device, loading the data characterizing the generated concreteness scores into memory, or storing the data characterizing the generated concreteness scores into physical persistence.
|