Evaluating brand value on the web

ABSTRACT

The value of a brand name is an important factor that consumers often take into consideration when making their purchasing decisions. However, it is difficult for users to evaluate correctly the value of a brand name, especially when they encounter it for the first time. In reality, sometimes a brand's description or its use is purposely manipulated so as to give an impression of high value. In another way, a non-existing brand name may be used to attract consumers. We call such names "glorified terms." In this paper, we propose a method for evaluating a brand's value from texts on the Web. To this end, we first acquire candidates of attributes useful for evaluating whether a term is a brand name or a glorified term. The candidates are evaluated according to the idea whereby explanations about a real brand name often contain attributes describing its quality. We implemented a prototype system especially for agricultural and livestock products. The system judges whether a given one is a glorified term or a well-known brand name from several viewpoints. We conducted preliminary experiments and we achieved 74% - 85% accuracy rate.

REFERENCES

• 1: Kushal Dave , Steve Lawrence , David M. Pennock, Mining the peanut gallery: opinion extraction and semantic classification of product reviews, Proceedings of the 12th international conference on World Wide Web, May 20-24, 2003, Budapest, Hungary [doi>10.1145/775152.775226]
• 2: D. G. Goldstein and G. Gigerenzer. The recognition heuristic: How ignorance makes us smart. in G. Gigerenzer, P.M. Todd, and the ABC Research Group, Simple Heuristics that make Us Smart, pages 37--58, 1999.
• 3: Nan Hu , Paul A. Pavlou , Jennifer Zhang, Can online reviews reveal a product's true quality?: empirical findings and analytical modeling of Online word-of-mouth communication, Proceedings of the 7th ACM conference on Electronic commerce, p.324-330, June 11-15, 2006, Ann Arbor, Michigan, USA [doi>10.1145/1134707.1134743]
• 4: Jon M. Kleinberg, Authoritative sources in a hyperlinked environment, Journal of the ACM (JACM), v.46 n.5, p.604-632, Sept. 1999 [doi>10.1145/324133.324140]
• 5: Takuya Kobayashi , Hiroaki Ohshima , Satoshi Oyama , Katsumi Tanaka, Modeling and analyzing review information on the web focusing on credibility, Proceedings of the 2009 ACM symposium on Applied Computing, March 08-12, 2009, Honolulu, Hawaii [doi>10.1145/1529282.1529577]
• 6: Fotis Kokkoras , Efstratia Lampridou , Konstantinos Ntonas , Ioannis Vlahavas, MOpiS: A Multiple Opinion Summarizer, Proceedings of the 5th Hellenic conference on Artificial Intelligence: Theories, Models and Applications, October 02-04, 2008, Syros, Greece [doi>10.1007/978-3-540-87881-0_11]
• 7: Bing Liu , Minqing Hu , Junsheng Cheng, Opinion observer: analyzing and comparing opinions on the Web, Proceedings of the 14th international conference on World Wide Web, May 10-14, 2005, Chiba, Japan [doi>10.1145/1060745.1060797]
• 8: H. Ohshima, S. Oyama, and K. Tanaka. Searching coordinate terms with their context from the web. In K. Aberer, Z. Peng, E. A. Rundensteiner, Y. Zhang, and X. Li, editors, WISE, volume 4255 of Lecture Notes in Computer Science, pages 40--47. Springer, 2006.
• 9: H. Ohshima and K. Tanaka. High-speed extraction of related terms by bi-directional syntax patterns from web search engines. DBSJ Journal, 7(3):1--6, December 2008 (in Japanese).
• 10: Y. Suzuki, H. Takamura, and M. Okumura. Application of semi-supervised learning to evaluative expression classification. In Proceedings of CICLing-06, the 7th international conference on Computational Linguistics and Intelligent Text Processing, pages 502--513, Mexico City, MX, 2006.

INDEX TERMS

Primary Classification:
  J. Computer Applications
  J.4 SOCIAL AND BEHAVIORAL SCIENCES
      Subjects: Economics

General Terms:
Algorithms, Economics, Reliability

Keywords:
brand value, evaluation of brand names, obtaining attributes of products