毕业设计（论文）汽车口碑数据中挖掘用户关注度的分析与研究.docVIP

摘 要 现在是大数据的时代，掌握了消费者的数据就能对消费者进行个性化推荐并在市场销售上领跑。因此本文以层次分析法为工具，对从汽车口碑数据中挖掘用户关注度进行了分析与研究。首先建立一个层次结构模型，把与汽车关注度相关的因素列举出来然后按照上下层支配关系依次分层，最高层为目标层即购买汽车，第二层为准则层即购买汽车时的准则，第三层为方案层即购影响买汽车的各个小因素。然后通过设计调查问卷和上汽车之家网站的方式搜集数据，再利用搜集到的数据进行比较之后分别对准则层对目标层，措施层对准则层列出判断矩阵，再通过AHP—和法与AHP—根法两种方法计算出各个判断矩阵的权重并通过一致性检验后，进行组合权重的计算，把每一层支配关系的权重相乘即为组合权重，得到组合权重并通过一致性检验之后将组合权重按照大小对用户关注的8个因素进行排序，给出消费者在购买汽车的时候需要考虑合理的建议，然后消费者再结合自身的经验进行判断，做出最终的决策。这个方法不仅能有效的挖掘消费者的关注度，还能大幅提高促进汽车的销售。 关键词：个性化推荐；用户关注度；层次分析法 Abstract With the era of big data, mastering the consumers data will be able to personalize the consumer recommendation and marketing in the lead. Therefore, this paper uses the analytic hierarchy process as a tool to analyze and study the users attention from mining word of mouth data. First of all, the establishment of a hierarchical model, the car with the degree of concern related to the list of factors and then in accordance with the upper and lower hierarchical domination in order to hierarchical, the highest level for the target layer to buy cars, the second layer for the standard layer that is the time to buy cars, Three layers for the program layer to buy the impact of the purchase of the various small factors. And then through the design of the questionnaire and the car home site to collect data, and then use the collected data to compare the criteria layer after the target layer, the measure layer on the criterion layer listed in the judgment matrix, and then through the AHP- and method and AHP- root method to calculate the weight of each judgment matrix and conduct a consistency test. If the consistency test can be passed, then the model analysis can be carried out, and then the weight of each combination is calculated. Multiplication is the combination of weight, get the combination of weight and consistency test after the combination of weight in accordance with the size of the user concerned about the eight factors to sort, given the consumer in the purchase of the car when the need to consider