中文摘要：

随着电子商务领域的迅速发展，在线商品评价规模日益庞大，评价质量参差不齐，用户难以筛选有用评价信息做出购买决策，因此如何有效识别高质量评价信息成为重要议题。以在线商品评价的有用性投票为基础定义评价质量，使用贝叶斯网络表示在线商品评价的相似性及不确定性，通过对在线商品评价信息进行多维度特征统计，构建在线商品评价质量评估模型，使用概率推理机制对在线商品评价质量进行分类预测，并给出评价质量分类置信度。在真实数据集上验证模型有效性及高效性。

英文摘要：

The techniques to identify useful reviews become an important issue, owing to growing scale of online product reviews, the quality of which is uneven and users being difficult to filter useful information to make purchase decisions,with the rapid development of e-commerce. Online product review quality is defined based on usefulness votes. The authors use Bayesian network to express the similarity and uncertainty of online product reviews, proposing the evaluation model of online product review quality by counting review characteristics of multiple dimensions, and the online product review quality is classified by probabilistic inference mechanism which throws up the classification confidence of review quality.The validity and efficiency of evaluation model are verified on real data sets.