Title :
A Method of Extracting Product Trend Keywords from Press Releases to Analyze Product Strategy of Competitors
Author :
Shimizu, Yutaka ; Akiyoshi, Masanori ; Komoda, Norihisa
Author_Institution :
Graduate Sch. of Inf. Sci. & Technol., Osaka Univ.
Abstract :
When a product planner develops new products it is important to analyze competitors´ existing 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 common phrases, which we call description patterns. A description pattern enables the extraction of keywords that describe those characteristics of a product that cannot be extracted simply by using word frequency. Additionally, we use derivation patterns, which are common phrases derived from a description pattern, to extract keywords more flexibly. By applying the proposed method to the press releases of two companies, we can extract keywords characterizing
Keywords :
marketing data processing; product development; word processing; keyword extraction; press releases; product strategy analysis; product trend keyword; word frequency; Companies; Computational intelligence; Computational modeling; Data mining; Frequency; Information analysis; Information science; Joining processes; Production; Telephony;
Conference_Titel :
Computational Intelligence for Modelling, Control and Automation, 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, International Conference on
Conference_Location :
Vienna
Print_ISBN :
0-7695-2504-0
DOI :
10.1109/CIMCA.2005.1631539