Abstract:

QoS(Quality of Service) becomes a very important factor of improving the core competence of airlines. The user evaluation is of great significance in improving the QoS. The network has become the most important platform for passengers to deliver their evaluation to airlines’ QoS. A novel airlines QoS hot topic detection algorithm (AQHTD) was proposed to detect the most valuable evaluation information timely and effectively. On the base of analyzing the traditional Kmeans algorithm and MapReduce computation model and considering the background of civil aviation and the features of evaluation information in the network, both of them were integrated together for our purpose. The key issues of AQHTD were discussed as well. Experiments show that the AQHTD algorithm is very effective. Moreover, it provides strong support in method for accessing the hot issues of airlines QoS timely.        

Key words: service quality;hot topic detection;MapReduce;text cluster;airlines