Research Article
Developing Machine Learning and Statistical Tools to Evaluate the Accessibility of Public Health Advice on Infectious Diseases among Vulnerable People
| MLS features (1–26) POS (27–72) | EHR mean | EHR std. | RHR mean | RHR std. | Asymp. sig. (2-tailed) | Effect size dCohen (corrected effect size or Hedges’ g) | Common language effect size CLES | 95% CI | Mann-Whitney U | Wilcoxon W | Z |
| Average sentences per paragraph | 0.601 | 0.345 | 3.316 | 1.163 | 0.000 | 2.588 | 0.966 | 2.301 to 2.874 | 52.00 | 4238.00 | −14.669 | TTR | 0.461 | 0.119 | 0.623 | 0.079 | 0.000 | 1.828 | 0.902 | 1.568 to 2.088 | 4389.00 | 8575.00 | −10.680 | Difficult words | 141.813 | 96.381 | 70.872 | 35.986 | 0.000 | −1.311 | 0.823 | −1.558 to −1.065 | 8769.50 | 70897.50 | −6.657 | Low-stroke characters | 641.593 | 444.264 | 284.707 | 140.930 | 0.000 | −1.507 | 0.857 | -1.758 to−1.256 | 8108.00 | 70236.00 | −7.264 | Middle-stroke characters | 120.396 | 80.348 | 51.810 | 27.695 | 0.000 | −1.562 | 0.865 | −1.814 to−1.31 | 7357.00 | 69485.00 | −7.955 | High-stroke characters | 0.055 | 0.229 | 0.452 | 1.604 | 0.005 | 0.277 | 0.578 | 0.045 to 0.508 | 14144.00 | 18330.00 | −2.815 | Average strokes per character | 7.677 | 0.274 | 7.711 | 0.342 | 0.195 | 0.103 | 0.529 | −0.127 to 0.334 | 14604.00 | 18790.00 | −1.297 | 2-character words | 256.637 | 176.783 | 114.341 | 56.262 | 0.000 | −1.509 | 0.857 | −1.76 to −1.258 | 8100.50 | 70228.50 | −7.271 | 3-character words | 13.000 | 11.824 | 8.298 | 6.372 | 0.008 | −0.603 | 0.665 | −0.837 to −0.369 | 13139.50 | 75267.50 | −2.647 | Average words per sentences | 11.592 | 4.963 | 11.893 | 1.962 | 0.018 | 0.106 | 0.530 | -0.125 to 0.336 | 13438.00 | 17624.00 | −2.368 | Single sentences | 0.883 | 0.114 | 0.460 | 0.191 | 0.000 | −2.376 | 0.954 | −2.655 to −2.098 | 949.00 | 63077.00 | −13.851 | Ratio of noun phrases | 0.267 | 0.104 | 0.415 | 0.198 | 0.000 | 0.810 | 0.717 | 0.573 to 1.046 | 8396.50 | 12582.50 | −6.999 | Frequency of noun phrases per 10K | 322.369 | 37.240 | 314.664 | 37.002 | 0.028 | −0.208 | 0.558 | −0.439 to 0.023 | 13620.50 | 75748.50 | −2.200 | Average idioms per sentences | 0.001 | 0.004 | 0.012 | 0.029 | 0.004 | 0.424 | 0.618 | 0.192 to 0.656 | 13969.00 | 18155.00 | −2.894 | Content words | 392.582 | 265.421 | 163.074 | 80.538 | 0.000 | −1.642 | 0.877 | −1.896 to −1.387 | 6988.50 | 69116.50 | −8.293 | Adverbs of negation | 2.758 | 3.067 | 0.935 | 1.228 | 0.000 | −1.032 | 0.767 | −1.272 to −0.792 | 9522.50 | 71650.50 | −6.283 | Sentences with complex semantic categories | 25.396 | 22.039 | 7.614 | 4.758 | 0.000 | −1.643 | 0.877 | −1.898 to −1.388 | 6696.50 | 68824.50 | −8.578 | Density of content words | 0.828 | 0.026 | 0.815 | 0.031 | 0.000 | −0.433 | 0.620 | −0.665 to −0.2 | 11857.50 | 73985.50 | −3.820 | Average logarithmic frequency of content words | 1.738 | 0.169 | 1.337 | 0.183 | 0.000 | −2.225 | 0.942 | −2.498 to −1.952 | 1854.00 | 63982.00 | −13.009 | Idioms | 0.077 | 0.268 | 0.224 | 0.510 | 0.009 | 0.312 | 0.587 | 0.081 to 0.544 | 14168.00 | 18354.00 | −2.623 | Pronouns | 41.692 | 35.043 | 1.469 | 1.652 | 0.000 | −2.530 | 0.963 | −2.814 to −2.245 | 620.50 | 62748.50 | −14.398 | Personal pronouns | 37.868 | 31.838 | 0.705 | 1.139 | 0.000 | −2.577 | 0.966 | −2.864 to −2.291 | 326.00 | 62454.00 | −15.334 | Conjunctions | 18.967 | 16.440 | 11.520 | 6.407 | 0.001 | −0.795 | 0.713 | −1.031 to −0.558 | 12507.50 | 74635.50 | −3.228 | Positive conjunctions | 16.824 | 14.159 | 9.000 | 5.193 | 0.000 | −0.991 | 0.758 | −1.23 to -0.751 | 10808.00 | 72936.00 | −4.795 | Negative conjunctions | 0.846 | 1.584 | 1.440 | 1.393 | 0.000 | 0.414 | 0.615 | 0.182 to 0.646 | 10710.50 | 14896.50 | −5.070 | Difficult words ratio | 30.384 | 5.724 | 35.847 | 8.175 | 0.000 | 0.706 | 0.691 | 0.471 to 0.941 | 9400.50 | 13586.50 | −6.077 | A | 3.099 | 3.774 | 3.026 | 2.969 | 0.236 | −0.023 | 0.507 | −0.254 to 0.207 | 14740.50 | 18926.50 | −1.184 | VI | 0.143 | 0.485 | 0.159 | 0.424 | 0.348 | 0.037 | 0.510 | −0.194 to 0.267 | 15418.50 | 19604.50 | −0.938 | Dk | 0.011 | 0.105 | 0.017 | 0.130 | 0.680 | 0.048 | 0.514 | −0.183 to 0.278 | 15919.00 | 20105.00 | −0.413 | VG | 2.154 | 2.454 | 2.054 | 1.919 | 0.505 | −0.049 | 0.514 | −0.28 to 0.181 | 15305.00 | 19491.00 | -0.666 | Nv | 9.967 | 10.390 | 9.290 | 6.711 | 0.083 | −0.089 | 0.525 | −0.32 to 0.142 | 14132.00 | 18318.00 | −1.734 | Neqb | 0.033 | 0.180 | 0.057 | 0.277 | 0.590 | 0.092 | 0.526 | −0.138 to 0.323 | 15810.00 | 19996.00 | −0.539 | Cab | 0.121 | 0.390 | 0.398 | 0.799 | 0.000 | 0.377 | 0.605 | 0.145 to 0.609 | 13151.00 | 17337.00 | −3.534 | I | 0.033 | 0.180 | 0.000 | 0.000 | 0.001 | −0.406 | 0.613 | −0.638 to −0.174 | 15488.00 | 77616.00 | −3.414 | VAC | 0.154 | 0.392 | 0.048 | 0.215 | 0.001 | −0.406 | 0.613 | −0.638 to −0.174 | 14493.00 | 76621.00 | −3.214 | Nd | 4.253 | 7.872 | 2.298 | 3.408 | 0.002 | −0.418 | 0.616 | -0.65 to −0.186 | 12764.50 | 74892.50 | −3.050 | Nb | 1.451 | 2.423 | 0.739 | 1.420 | 0.000 | −0.425 | 0.618 | −0.657 to −0.193 | 12369.50 | 74497.50 | −3.789 | Dfb | 0.066 | 0.291 | 0.003 | 0.053 | 0.000 | −0.451 | 0.625 | −0.683 to −0.219 | 15181.00 | 77309.00 | −3.831 | Neu | 4.505 | 6.339 | 2.395 | 3.209 | 0.001 | −0.521 | 0.644 | −0.754 to −0.288 | 12438.00 | 74566.00 | −3.347 | VJ | 10.011 | 8.836 | 6.455 | 5.125 | 0.000 | −0.586 | 0.661 | −0.82 to −0.352 | 11896.00 | 74024.00 | −3.797 | VL | 2.912 | 2.946 | 1.710 | 1.741 | 0.001 | −0.588 | 0.661 | −0.821 to −0.354 | 12457.00 | 74585.00 | −3.343 | Cba | 0.110 | 0.379 | 0.003 | 0.053 | 0.000 | −0.602 | 0.665 | −0.836 to −0.369 | 14652.50 | 76780.50 | −5.125 | Caa | 12.846 | 11.117 | 8.705 | 5.150 | 0.103 | −0.608 | 0.666 | −0.842 to −0.374 | 14244.50 | 76372.50 | −1.631 | VB | 0.912 | 1.488 | 0.321 | 0.722 | 0.000 | −0.635 | 0.673 | −0.869 to −0.401 | 12839.50 | 74967.50 | −3.789 | VHC | 0.527 | 1.089 | 1.705 | 1.958 | 0.000 | 0.649 | 0.677 | 0.415 to 0.884 | 9100.00 | 13286.00 | −6.641 | Da | 0.516 | 1.058 | 0.125 | 0.348 | 0.000 | −0.686 | 0.686 | −0.921 to −0.451 | 12813.00 | 74941.00 | -4.647 | Nes | 2.033 | 2.100 | 0.960 | 1.278 | 0.000 | −0.723 | 0.696 | −0.959 to -0.488 | 10783.50 | 72911.50 | −5.088 | Dfa | 3.473 | 3.854 | 1.608 | 1.752 | 0.000 | −0.797 | 0.713 | −1.033 to −0.561 | 10952.00 | 73080.00 | −4.769 | VH | 22.154 | 15.913 | 13.767 | 8.222 | 0.000 | −0.817 | 0.718 | −1.053 to −0.58 | 11401.00 | 73529.00 | −4.243 | Nf | 7.418 | 8.071 | 3.094 | 3.956 | 0.000 | −0.852 | 0.727 | −1.089 to −0.615 | 9110.50 | 71238.50 | −6.401 | Nc | 7.780 | 7.781 | 2.688 | 5.303 | 0.000 | −0.864 | 0.729 | −1.101 to −0.627 | 8121.00 | 70249.00 | −7.430 | Nep | 3.527 | 4.388 | 1.327 | 1.653 | 0.000 | −0.890 | 0.736 | −1.128 to −0.653 | 12279.50 | 74407.50 | −3.559 | T | 1.165 | 1.662 | 0.261 | 0.649 | 0.000 | −0.953 | 0.750 | −1.192 to −0.715 | 10192.00 | 72320.00 | −6.926 | Di | 2.901 | 3.169 | 0.912 | 1.538 | 0.000 | −1.003 | 0.761 | −1.243 to −0.763 | 9200.50 | 71328.50 | −6.755 | SHI | 4.396 | 4.942 | 1.676 | 1.709 | 0.000 | −1.006 | 0.762 | −1.246 to −0.766 | 10776.00 | 72904.00 | −4.917 | VD | 1.703 | 2.355 | 0.375 | 0.861 | 0.000 | −1.012 | 0.763 | −1.252 to −0.772 | 9587.50 | 71715.50 | −7.241 | Cbb | 5.890 | 6.402 | 2.415 | 2.001 | 0.000 | −1.022 | 0.765 | −1.263 to −0.782 | 10325.50 | 72453.50 | −5.297 | Neqa | 6.011 | 5.997 | 2.537 | 2.227 | 0.000 | −1.034 | 0.768 | −1.274 to −0.794 | 10036.50 | 72164.50 | −5.553 | Na | 113.209 | 77.721 | 64.639 | 32.606 | 0.000 | −1.065 | 0.774 | −1.306 to −0.824 | 11326.50 | 73454.50 | −4.308 | Ng | 6.473 | 8.048 | 2.068 | 1.980 | 0.000 | −1.090 | 0.780 | −1.331 to −0.848 | 8874.50 | 71002.50 | −6.668 | V_2 | 4.560 | 5.879 | 1.128 | 1.214 | 0.000 | −1.197 | 0.801 | −1.44 to −0.953 | 9003.50 | 71131.50 | −6.676 | VE | 7.824 | 7.207 | 2.670 | 2.913 | 0.000 | −1.237 | 0.809 | −1.482 to −0.993 | 8111.50 | 70239.50 | −7.335 | DE | 27.396 | 21.300 | 11.653 | 7.618 | 0.000 | −1.336 | 0.828 | −1.583 to −1.09 | 8606.50 | 70734.50 | −6.816 | P | 22.571 | 16.570 | 9.330 | 6.188 | 0.000 | −1.424 | 0.843 | −1.672 to −1.175 | 8358.00 | 70486.00 | −7.045 | Ncd | 6.747 | 5.960 | 1.869 | 1.933 | 0.000 | −1.526 | 0.86 | −1.777 to −1.274 | 7167.50 | 69295.50 | −8.263 | VCL | 5.242 | 5.730 | 0.693 | 1.033 | 0.000 | −1.656 | 0.879 | −1.911 to −1.401 | 5248.50 | 67376.50 | −10.615 | VC | 48.791 | 35.985 | 14.759 | 10.551 | 0.000 | −1.812 | 0.900 | −2.071 to −1.552 | 5672.50 | 67800.50 | −9.506 | D | 44.110 | 31.491 | 14.489 | 8.247 | 0.000 | −1.849 | 0.905 | −2.11 to −1.589 | 5603.00 | 67731.00 | −9.573 | VK | 9.736 | 7.688 | 2.293 | 2.086 | 0.000 | −1.889 | 0.909 | −2.151 to −1.627 | 5158.50 | 67286.50 | −10.096 | VA | 11.659 | 10.140 | 2.088 | 2.214 | 0.000 | −1.919 | 0.913 | −2.181 to −1.656 | 4616.50 | 66744.50 | −10.605 | VF | 4.198 | 3.964 | 0.222 | 0.629 | 0.000 | −2.119 | 0.933 | −2.388 to −1.849 | 4026.50 | 66154.50 | −13.780 | Nh | 41.692 | 35.043 | 1.469 | 1.652 | 0.000 | −2.530 | 0.963 | −2.814 to −2.245 | 620.50 | 62748.50 | −14.398 |
|
|