Published Date 1/31/13 1:19 PM
Companies and other organizations want an automated way to identify the complex and subtle range of opinions that people express about their products and services in reviews and other text-based forums. However, this process is complicated and involves sophisticated semantics.
In “Full Spectrum Opinion Mining: Integrating Domain, Syntactic and Lexical Knowledge,” a paper presented at the 2012 IEEE 12th International Conference on Data Mining Workshops (ICDMW), Daniel J. Olsher of Temasek Laboratories’ Cognitive Science Program at the National University of Singapore has designed an opinion-mining system that draws on domain models, linguistic constructions, specific world knowledge, and knowledge-representation for determining the opinions expressed in text.
Papers from ICDMW are available to both IEEE Computer Society members and paid subscribers via the Computer Society Digital Library.