Applied Computational Intelligence and Soft Computing / 2018 / Article / Tab 5

Research Article

Performance Assessment of Multiple Classifiers Based on Ensemble Feature Selection Scheme for Sentiment Analysis

Table 5

Results of the proposed model for electronics review data set.

MethodClassifier
SVMMNBKNNME
PrecRecallF- ScorePrecRecallF-ScorePrecRecallF-ScorePrecRecallF-Score

Unigram86.983.285.085.786.686.1482.380.181.1882.179.880.93
Bigram81.580.180.7982.580.281.3384.581.282.8178.276.277.18
Unigram+87.284.485.7785.287.486.2886.282.780.4183.180.481.72
Bigram
CompIG88.387.187.6989.286.087.9687.784.585.0785.781.983.75
CompCHI86.782.584.5487.985.486.6383.981.282.5286.283.684.88
CompGI88.184.886.4188.285.786.9388.683.484.9287.385.586.39
Average86.683.585.0186.385.486.3385.5382.1883.8183.7682.1084.75

Article of the Year Award: Outstanding research contributions of 2020, as selected by our Chief Editors. Read the winning articles.