基于KNN和Bayes算法的组合分类器的垃圾评论识别研究

产品垃圾评论在一定程度上影响了评论信息的参考价值,本文旨在建立识别模型将垃圾评论从评论文本中剔除,保留真实的产品评论。首先,分析了产品评论的特点,从数据搜集、文本预处理、互信息检验、文本表示4个模块提取了14个特征。然后,利用高互补性建立了基于KNN和Bayes算法的组合分类器模型。最后,利用交叉验证对iPhone 6Plus的产品评论进行检验,得到评价指标分别为:正确识别率75.3%、召回率82.1%以及F1值77.5%.     

Motion estimation based on an improved block matching technique

An improved block-matching algorithm for fast motion estimation is proposed. The matching criterion is the sum of absolute difference. The basic idea is to obtain the best estimation of motion vectors by an optimization of the search process which can terminate the time-consuming computation of matching evaluation between the current block and the ineligible candidate block as early as possible and eliminate the search positions as many as possible in the search area. The performance of this algorithm is evaluated by theoretic analysis and compared with the full search algorithm (FSA). The simulation results demonstrate that the computation load of this algorithm is much less than that of FSA, and the motion vectors obtained by this algorithm are identical to those of FSA.