We describe an industrial-strength software system for automatically coding open-ended survey responses. The system is based on a learning metaphor, whereby automated verbatim coders are automatically generated by a general-purpose process that learns, from a user-provided sample of manually coded verbatims, the characteristics that new, uncoded verbatims should have in order to be attributed the codes in the codeframe. In this paper we discuss the basic workings of this software and present the results of experiments we have run on several datasets of real respondent data, in which we have compared the accuracy of the software against the accuracy of human coders.
Machines that learn how to code open-ended survey data
Esuli A;Sebastiani F
2010
Abstract
We describe an industrial-strength software system for automatically coding open-ended survey responses. The system is based on a learning metaphor, whereby automated verbatim coders are automatically generated by a general-purpose process that learns, from a user-provided sample of manually coded verbatims, the characteristics that new, uncoded verbatims should have in order to be attributed the codes in the codeframe. In this paper we discuss the basic workings of this software and present the results of experiments we have run on several datasets of real respondent data, in which we have compared the accuracy of the software against the accuracy of human coders.File | Dimensione | Formato | |
---|---|---|---|
prod_44396-doc_34335.pdf
non disponibili
Descrizione: Articolo pubblicato
Tipologia:
Versione Editoriale (PDF)
Dimensione
258 kB
Formato
Adobe PDF
|
258 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.