Method and system for evaluating vocabulary similarity

A system for evaluating vocabulary similarity, the system comprising:

• a processor;
• and
• a processor-readable storage medium in communication with the processor,
• wherein the processor-readable storage medium contains one or more programming instructions for causing the processor to execute steps comprising:
• determining with a computer system a generic occurrence rate for each word in a plurality of first sample essays by, for each word, setting the generic occurrence rate equal to a number of first sample essays in which the word occurs divided by a total number of first sample essays, wherein each first sample essay responds to one of a plurality of first prompts, and wherein at least one first sample essay responds to each of the first prompts;
• determining with the computer system a specific occurrence rate for each word in a plurality of second sample essays by, for each word, setting the specific occurrence rate equal to a number of second sample essays in which the word occurs divided by a total number of second sample essays, wherein each second sample essay responds to a second prompt;
• receiving a target essay response having a plurality of words, wherein the target essay response is associated with the second prompt;
• calculating with the computer system a vocabulary similarity index for the target essay response based on one or more generic occurrence rates and one or more specific occurrence rates by, for each word in the target essay response, calculating a value based on the generic occurrence rate for the word and the specific occurrence rate for the word, and setting the vocabulary similarity index to an average of the computed values;
• and
• evaluating and displaying whether the target essay response is off-topic based on comparing the vocabulary similarity index for the target essay response with a predetermined threshold,
• the calculating and evaluating thereby providing an evaluation of whether the target essay response is off-topic based upon the generic occurrence rates of the first sample essays and the specific occurrence rates of the second sample essays.

A processor-readable storage medium containing one or more programming instructions for evaluating vocabulary similarity, the programming instructions causing a processing system to execute steps comprising:

• determining with a computer system a generic occurrence rate for each word in a plurality of first sample essays by, for each word, setting the generic occurrence rate equal to a number of first sample essays in which the word occurs divided by a total number of first sample essays, wherein each first sample essay responds to one of a plurality of first prompts, and wherein at least one first sample essay responds to each of the first prompts;
• determining with the computer system a specific occurrence rate for each word in a plurality of second sample essays by, for each word, setting the specific occurrence rate equal to a number of second sample essays in which the word occurs divided by a total number of second sample essays, wherein each second sample essay responds to a second prompt;
• receiving a target essay response having a plurality of words, wherein the target essay response is associated with the second prompt;
• calculating with the computer system a vocabulary similarity index for the target essay response based on one or more generic occurrence rates and one or more specific occurrence rates by, for each word in the target essay response, calculating a value based on the generic occurrence rate for the word and the specific occurrence rate for the word, and setting the vocabulary similarity index to an average of the computed values;
• and
• evaluating and displaying whether the target essay response is off-topic based on comparing the vocabulary similarity index for the target essay response with a predetermined threshold,
• the calculating and evaluating thereby providing an evaluation of whether the target essay response is off-topic based upon the generic occurrence rates of the first sample essays and the specific occurrence rates of the second sample essays.