Measuring the meaning in time series clustering of text search queries

We use a combination of proven methods from time series analysis and machine learning to explore the relationship between temporal and semantic similarity in web query logs; we discover that the combination of correlation and cycles is a good, but not perfect, sign of semantic relationship. Categories and Subject Descriptors:H.3.3 Information Storage and Retrieval Information Search and Retrieval [Clustering, Query Formulation]: H.3.5 Information Storage and RetrievalOnline Information Services [Web-based services] General Terms:Experimentation, Measurements

• Type: Conference
• Year: 2006
• Where: CIKM
• Authors: Bing Liu 0003, Rosie Jones, Kristina Lisa Klinkner
• Keywords: CIKM 2006, Information Management, Information Storage, Retrieval Information Search, Time Series Analysis