Title :
A Method on Generating Product Feature Trend Map from Press Releases using Syntactic Dependency Analysis with Expression Phrases
Author :
Akiyoshi, Masanori ; Shimizu, Yutaka ; Komoda, Norihisa
Author_Institution :
Osaka Univ., Suita
Abstract :
It is important to analyze existing products of competitors when a product planner develops new products. In this research, we proposed a method of extracting product trend keywords from press releases to support product strategy analysis. In order to extract keywords from press releases, we utilize expression phrases which are defined as description patterns. A description pattern enables extracting keywords describing features of a product that cannot be extracted by using simply word frequency. Additionally, we utilize derivation patterns, which are expression phrases derived from a description pattern, to extract keywords more flexibly. Also to grasp time-series movement in the feature of each product, product feature trend map is discussed.
Keywords :
advertising data processing; product development; expression phrases; product feature trend map; product strategy analysis; product trend keyword extraction; syntactic dependency analysis; Companies; Cybernetics; Data mining; Feature extraction; Frequency; Information science; Pattern matching; Production;
Conference_Titel :
Systems, Man and Cybernetics, 2006. SMC '06. IEEE International Conference on
Conference_Location :
Taipei
Print_ISBN :
1-4244-0099-6
Electronic_ISBN :
1-4244-0100-3
DOI :
10.1109/ICSMC.2006.384573