Table 2B

Studies that performed text classification using supervised approach, including the number of rater and associated inter-rater agreement expressed as Cohen’s kappa (κ), classifiers and configuration applied where reported. Studies are reported in chronological order

AuthorData sourceComments classifiedNo. of ratersκNo. of themesClassifierConfiguration
Alemi et al10 34RateMDs100% (n=955)NRNR9Sparsity rule
SVM: RBF kernel
Greaves et al7NHS choices*17.56% (1000/5695)20.763Prior polarity
Information gain
SVM: RBF kernel
Wagland et al48Cancer experience14.19% (800/5634)30.64–0.8711NR
Doing-Harris et al24Press Ganey0.58% (300/51 235)30.737NR
Hawkins et al52Twitter7511/11 602†AMT0.18–0.5210NR
  • *Only n-grams classified.

  • †Tweets classified as pertaining to patient experience only.

  • AMT, Amazon Mechanical Turk; B, bagging; DT, decision trees; GL, generalised linear model; KN, k-nearest neighbour; NB, Naïve Bayes; NR, not reported; RBF, radial basis function; RF, random forest; SVM, support vector machine.