Attributive concept descriptions with complements
Artificial Intelligence
Scatter/Gather: a cluster-based approach to browsing large document collections
SIGIR '92 Proceedings of the 15th annual international ACM SIGIR conference on Research and development in information retrieval
Foundations of statistical natural language processing
Foundations of statistical natural language processing
Evaluating document clustering for interactive information retrieval
Proceedings of the tenth international conference on Information and knowledge management
Automatic Topic Identification Using Webpage Clustering
ICDM '01 Proceedings of the 2001 IEEE International Conference on Data Mining
Proceedings of the Joint JSAI 2001 Workshop on New Frontiers in Artificial Intelligence
KeyGraph: Automatic Indexing by Co-occurrence Graph based on Building Construction Metaphor
ADL '98 Proceedings of the Advances in Digital Libraries Conference
Automated scoring using a hybrid feature identification technique
COLING '98 Proceedings of the 17th international conference on Computational linguistics - Volume 1
| Hi-index | 0.00 |
A variety of services have recently been provided that depend on highly developed networks and personal equipment. With these advances, connecting this equipment has become increasingly more complicated. Customer enquiries about problems such as no-connection to an Internet/phone service will increase, and telecom operators will require the ability to understand such situations and act as quickly as possible. Therefore, it is important to analyze failure trends and establish, in advance, effective coping processes for complex problems conveyed in customer enquiries. We present a method for analyzing and classifying customer enquiries efficiently and precisely from the structural type of description in ontologies. Moreover, our method can reconstruct semantic content efficiently by extracting related terms through analysis and classification. This method is based on a dependency parsing and co-occurrence technique to enable classification of a large amount of unstructured data into patterns because customer enquiries are generally stored as unstructured textual data. The validity of the method is evaluated and the method to determine threshold values is developed by using a large amount of customer enquiries in the real operational field.