- author = "Brij Masand",
- title = "Optimising Confidence of Text Classification by Evolution of Symbolic Expressions",
- booktitle = "Advances in Genetic Programming",
- publisher = "MIT Press",
- editor = "Kenneth E. {Kinnear, Jr.}",
- year = "1994",
- pages = "445--458",
- chapter = "21",
- keywords = "genetic algorithms, genetic programming, k-nn",
- institution = "Thinking Machines Corporation",
-
URL = "
http://www.amazon.co.uk/Advances-Genetic-Programming-Complex-Adaptive/dp/0262111888",
-
URL = "
http://cognet.mit.edu/sites/default/files/books/9780262277181/pdfs/9780262277181_chap21.pdf",
-
DOI = "
doi:10.7551/mitpress/1108.003.0027",
- size = "13 pages",
- abstract = "This paper reports some experiments in applying genetic algorithms for assessing the confidence of automatically assigned multiple keywords for news stories. Using Memory Based Reasoning (MBR) (a k-nearest neighbour method) to classify the stories, we would like to assign a confidence score per news story, that allows one to refer stories with low classification confidence to a human coder. Using Genetic Programming (GP) as used for program evolution by [Koza 1992], we discover and evolve symbolic expressions to compute confidence scores for news stories that allow a higher performance on subsets of the database while referring some stories to human editors. We have earlier reported recall and precision of 81percent and 72percent, if 100percent of the stories are coded automatically [Masand, Linoff and Waltz 1992]. Using the evolved confidence measures to refer some stories for manual coding, we can achieve about 80percent recall and 80percent precision for 92percent of the stories. This compares favourably with manually specified confidence functions that could classify 76percent of the database with an 80-8Opercent recall-precision requirement.",
- notes = "Presented at Genetic Programming Workshop of ICGA-93",
-
notes = "Classification of New Stories, Very simple formulae
evolved which do better than existing human attempts at
automatic coding. Automatic results comparable to human
success rates
Part of \cite{kinnear:book}",
