A system to monitor the quality of automated coding of textual answers to open questions
暂无分享,去创建一个
The Italian National Statistical Institute (ISTAT) carried out some tests of automated coding of textual answers regarding Occupation, Education level, Industry, etc, using the ACTR system (Automated Coding by Text Recognition). The good results obtained led ISTAT to perform a further analysis of a large sample of textual data, in order to define a standardised procedure for reference when using ACTR instead of manual coding during a survey. The analysis shown in this paper aims at building up a system to monitor the quality of the results of automated coding and at verifying the improvements which can be achieved using the results of the monitoring activity to integrate the automated coding environment.
[1] David L. Waltz,et al. Trading MIPS and memory for knowledge engineering , 1992, CACM.
[2] R. Knaus,et al. Methods and Problems in Coding Natural language Survey Data , 2002 .
[3] Damir Kalpić,et al. Automated Coding of Census Data , 1994 .
[4] William G. Cochran,et al. Sampling Techniques, 3rd Edition , 1963 .
[5] Robert T. O'Reagan,et al. Computer-assigned codes from verbal responses , 1972, Commun. ACM.