Multi-dimensional Text Warehousing for Text Analytics

摘要

A data warehouse is a repository of integrated data that provides the basis for decision making which is required to establish crucial business strategies. Recent data warehouses focus upon not only structured data but also textual data. Specially, a text warehouse is a type of data warehouse that provides efficient document retrieval and summarization capabilities. In this paper, we propose a novel way of text warehousing to support text mining capabilities beyond the simple search and aggregation functions. The proposed text warehousing method allows us to perform text mining tasks such as text classification, text clustering, and word association mining more effectively.