System and method for detecting a point of originality in a writing

Abstract

This paper proposes a new method for the objective evaluation of student work through the identification of original content in writing assignments. Using WordNet as a lexical reference, this process allows instructors to track how key phrases are employed and evolve over the course of a student's writing, and to automatically visualize the point at which the student's language first demonstrates original thought, phrased in their own, original words. After sketching the method for isolating “points of originality,” the paper provides a method for visualizing the resulting information. By visualizing otherwise subjective information in a way that is objectively intelligible, the goal is to provide educators with the ability to monitor student investment in concepts from the course syllabus, and to extend or modify the boundaries of the syllabus in anticipation of pre-existing knowledge or trends in interest.

1 . A method for evaluating a writing through the identification of original content in the writing, the method comprising:
 (a) submitting the writing to a processing system;   (b) inputting a first query term;   (c) constructing a first matrix of relationships between lexical terms generated from the first query term;   (d) searching the writing for terms which appear in the first matrix; and   (e) computing an originality estimate value for each of the terms in the writing which match one or more terms in the first matrix, wherein the originality estimate value is based upon the lexical relationships between the terms in the writing and the terms in the first matrix.   
     
     
         2 . The method of  claim 1  wherein computing an originality estimate value corresponds to computing an originality estimate value a according to the equation: α=δ×0.7×t and wherein δ corresponds to a value representing a distance between the word in the writing found in the matrix and the query term; and t corresponds to a value representing a word type. 
     
     
         3 . The method of  claim 1  further comprising;
 (f) repeating (b)-(e) for a plurality of different query terms to provide a corresponding plurality of originality estimate values; and 
 (g) summing the plurality of originality estimate values to produce a point of originality score for the writing. 
 
     
     
         4 . The method of  claim 1  wherein submitting a writing to a processing system comprises:
 checking a format of an electronic document containing the writing to determine whether the electronic document is in a format accepted by the processing system; and 
 in response to the electronic document not being in a format accepted by the processing system, placing the document in a format accepted by the processing system. 
 
     
     
         5 . The method of  claim 2  further comprising presenting the point of originality score on a timeline graph. 
     
     
         6 . The method of  claim 2  wherein: the first query term is a first one of a plurality of query terms; the first matrix of relationships is a first one of a plurality of matrices of relationships and the method further comprises:
 computing an originality estimate value a for each word in the student writing found in one or more of the plurality of matrices; and 
 computing a point of originality score for the writing using each of the computed originality estimate values. 
 
     
     
         7 . The method of  claim 2  wherein the writing is a student writing. 
     
     
         8 . The method of  claim 7  further comprising repeating (a)-(e) for each of a plurality of writings by the same student. 
     
     
         9 . The method of  claim 8  further comprising plotting all instances of originality on a timeline graph. 
     
     
         10 . A method for the objective evaluation of a student writing, the method comprising
 (a) identifying original content in the student writing;   (b) computing an originality score based upon one or more words in the student writing and lexical relationships between each of the one or more words in the student writing and one or more selected query terms.   
     
     
         11 . The method of  claim 10  wherein identifying original content in the student writing comprises isolating one or more points of originality in the student writing. 
     
     
         12 . The method of  claim 11  wherein isolating one or more points of originality in the student writing comprises:
 receiving a first query term; 
 generating a first matrix of relationships between lexical terms based upon the first query term; 
 searching the student writing for words which appear in the matrix; and 
 computing a first originality score based upon the lexical relationships between the words in the student writing which also appear in the first matrix. 
 
     
     
         13 . The method of  claim 12  wherein computing an originality score comprises:
 computing an originality estimate a according to the equation: α=δ×0.7×t and wherein δ corresponds to a value representing a distance between the word in the student writing found in the matrix and the query term; and t corresponds to a value representing a word type. 
 
     
     
         14 . The method of  claim 12  wherein: the first query term is a first one of a plurality of query terms; the first matrix of relationships is a first one of a plurality of matrices of relationships; and the method further comprises:
 computing an originality estimate a for each word in the student writing found in one or more of the plurality of matrices; and 
 computing a point of originality for the student writing using each of the computed originality estimates. 
 
     
     
         15 . The method of  claim 14  wherein computing a point of originality for the student writing using each of the computed originality estimates comprises summing each of the originality estimates and wherein the point of originality for the student writing corresponds to the summed originality estimates. 
     
     
         16 . The method of  claim 15  further comprising visualizing the resulting information on a timeline graph. 
     
     
         17 . A method for evaluating a point of originality in a single piece of writing through the identification of original content in the writing, the method comprising:
 (a) submitting the single piece of writing to a processing system;   (b) inputting a first query term, wherein the first query terms is one of a single word or a compound phrase;   (c) generating lexical terms from the first query terms;   (d) constructing a first matrix of conceptual-semantic and lexical relationships based upon the lexical terms generated from the first query term;   (e) searching the writing for terms which appear in the first matrix; and   (f) computing an originality estimate value for each of the terms in the writing that match one or more terms in the first matrix, wherein the originality estimate value is based upon the lexical relationships between the terms in the writing and the terms in the first matrix, wherein the originality estimate values for each of the terms in the writing are summed to produce a point of originality value for the writing.   
     
     
         18 . The method of  claim 17  further comprising presenting the point of originality score on a timeline graph, wherein the timeline graph depicts the evolution of point of originality scores for a particular person over a period of time.