Research on ARIA of Affective Recommendation Index Algorithm Based on Topic Selection of Publications

At present, the publishing organization’s publication selection planning method lags behind, making China’s publishing industry economic benefits greatly reduced. This paper presents a new affective analysis method—Affective Recommendation index (ARIA) based on the method of fine-grained affective analysis, which combines conditional random field model (CRF) and affective weighting method to analyze the evaluation information of publication, Targeted selection of the evaluation object and its attributes analysis of the reader’s emotional inclination, taking full account of the emotion-free words but the influence of the invisible affective sentences on the emotion, the author analyzes the emotion of the book review with affective words and analyses the emotion of the book review, and makes a weighted calculation of the emotional inclination, and concludes that the readers are positive to the publication, The negative evaluation quantity, through "The introduction weight value-weighted sum-Calculates the ratio" the algorithm step, obtains the Affective recommendation index. To match the readers ' interest by the index of affective recommendation, more accurate grasp of the book publishing market and user needs, reduce the backlog of books inventory, achieve more accurate publication, personalized recommendations, increase the economic benefits of publishing industry.