Study on mutual information-based feature selection in text categorization

To solve the problem of the poor effect of mutual information-based feature selection on the unbalanced corpuswhich arise from not well combining positive feature and negative feature.The ratio of positive feature and negative featureis adjusted with balance factor to strengthen the effect of negative feature.And category strong related feature is distinctedwith feature distributed factor.The experimental results verify the efficiency and probability of the improved mutual informa-tion-based feature selection.