Concept Extraction from Student Essays, Towards Concept Map Mining

This paper presents a new approach for automatic concept extraction, using grammatical parsers and Latent Semantic Analysis. The methodology and tool used to build the benchmarking corpus is also described. The results obtained on a corpus of student essays shows good inter-rater agreement and promising machine extraction. Concept extraction is contextualized as the first step to automatic generation of concept maps from student’s essays.

• Type: Conference
• Year: 2009
• Where: ICALT
• Authors: Jorge J. Villalón, Rafael A. Calvo
• Keywords: Automatic Concept Extraction, Concept Extraction, ICALT 2009, Machine Learning, Promising Machine Extraction