Research Article

Text Classification Using Novel Term Weighting Scheme-Based Improved TF-IDF for Internet Media Reports

Table 14

Performance on the Fudan corpus using the NB classifier.

NBPrecisionRecallF1 score
TF-IDF (%)TF-IADF (%)TF-IADFnorm (%)TF-IADF+TF-IADF+norm (%)TF-IDF (%)TF-IADF (%)TF-IADFnorm (%)TF-IADF+ (%)TF-IADF+norm (%)TF-IDF (%)TF-IADF (%)TF-IADFnormTF-IADF+ (%)TF-IADF+norm (%)

C1194.9894.5794.5394.9994.8391.2889.5688.7991.5991.4393.0992.0091.5793.2693.10
C1593.75100.00100.0093.7593.7545.4630.3027.2745.4645.4661.2246.5142.8661.2261.22
C1666.67100.00100.0075.0080.007.143.573.5710.7114.2912.906.906.9018.7524.24
C1787.5086.6783.3393.7594.1251.8548.1537.0455.5659.2665.1261.9151.2869.7772.73
C1996.3896.0295.8796.4696.3896.1796.0295.8096.1796.1796.2896.0295.8496.3196.28
C2393.3392.31100.0094.7490.0041.1835.2920.5952.9452.9457.1451.0634.1567.9366.67
C2986.3687.8887.1086.3688.8964.4149.1545.7664.4167.8073.7963.0460.0073.7976.92
C382.9481.8181.1983.4383.5194.3495.1595.4294.3494.2188.2787.9887.7388.5588.54
C3197.5997.8997.7897.6997.6992.9491.3890.4893.7693.7695.2194.5293.9995.6995.69
C3291.9290.7090.3591.6891.6090.2288.7587.9790.6190.7191.0689.7189.1491.1491.15
C3485.0582.8681.3285.7686.2092.7692.6992.4492.9492.8888.7487.5086.5289.2189.42
C3587.5086.9687.5086.9686.9640.3938.4640.3938.4638.4655.2653.3355.2653.3353.33
C3690.9188.8993.3390.9190.9137.7430.1926.4237.7437.7453.3345.0741.1853.3353.33
C3778.8584.0981.4078.4378.8553.9548.6846.0552.6353.9564.0661.6758.8262.9964.06
C3884.3083.1282.1685.4685.5592.1192.5992.0192.2092.3088.0387.6086.8188.7088.80
C3989.3088.2987.3089.3989.3993.8693.2292.6694.0294.0291.5290.6989.9091.6491.64
C450.00100.00100.0050.0050.005.885.885.885.885.8810.5311.1111.1110.5310.53
C580.0075.0071.4387.5077.7813.129.848.2011.4811.4822.5417.3914.7120.2920.00
C690.0090.0090.0090.0090.0020.0020.0020.0020.0020.0032.7332.7332.7332.7332.73
C769.1071.7672.4968.9769.1766.8866.2464.7468.3869.0267.9768.8968.4068.6769.09