Hostname: page-component-586b7cd67f-gb8f7 Total loading time: 0 Render date: 2024-11-24T10:32:15.762Z Has data issue: false hasContentIssue false
  • English
  • Français

Linguistic support for concept selection decisions

Published online by Cambridge University Press:  19 March 2007

J. DELIN ,
S. SHAROFF ,
S. LILLFORD  and
C. BARNES
J. DELIN
Affiliation:
Enterprise IG, London, United Kingdom Centre for Translation Studies, School of Modern Languages and Cultures, University of Leeds, Leeds, United Kingdom
S. SHAROFF
Affiliation:
Centre for Translation Studies, School of Modern Languages and Cultures, University of Leeds, Leeds, United Kingdom
S. LILLFORD
Affiliation:
School of Mechanical Engineering, University of Leeds, Leeds, United Kingdom
C. BARNES
Affiliation:
School of Mechanical Engineering, University of Leeds, Leeds, United Kingdom
Get access Rights & Permissions [Opens in a new window]

Abstract

Affective engineering is being increasingly used to describe a systematic approach to the analysis of consumer reactions to candidate designs. It has evolved from Kansei engineering, which has reported improvements in products such as cars, electronics, and food. The method includes a semantic differential experiment rating candidate designs against bipolar adjectives (e.g., attractive–not attractive, traditional–not traditional). The results are statistically analyzed to identify correlations between design features and consumer reactions to inform future product developments. A number of key challenges emerge from this process. Clearly, suitable designs must be available to cover all design possibilities. However, it is also paramount that the best adjectives are used to reflect the judgments that participants might want to make. The current adjective selection process is unsystematic, and could potentially miss key concepts. Poor adjective choices can result in problems such as misinterpretation of an experimental question, clustering of results around a particular response, and participants' confusion from unfamiliar adjectives that can be difficult to consider in the required context (e.g., is this wristwatch “oppressive”?). This paper describes an artificial intelligence supported process that ensures adjectives with appropriate levels of precision and recall are developed and presented to participants (and thus addressing problems above) in an affective engineering study in the context of branded consumer goods. We illustrate our description of the entire concept expansion and reduction process by means of an industrial case study in which participants were asked to evaluate different designs of packaging for a laundry product. The paper concludes by describing the important advantages that can be gained by the new approach in comparison with previous approaches to the selection of consumer focused adjectives.

Keywords

Adjective RulesAffective EngineeringConcept EvaluationKansei EngineeringSemantic Differential Experiment
Type
Research Article
Information
AI EDAM , Volume 21 , Issue 2 , April 2007 , pp. 123 - 135
Copyright
© 2007 Cambridge University Press

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

References

REFERENCES

Aston, G. & Burnard, L. (1998). The BNC Handbook: Exploring the British National Corpus With SARA. Edinburgh: Edinburgh University Press.
Berry, M., Drma, X., & Jessup, E. (1999). Matrices, vector spaces, and information retrieval. SIAM Review 41(2), 335–362.Google Scholar
Childs, T., Agouridas, V., Barnes, C., & Henson, B. (2006). Controlled appeal product design: a life cycle role for affective (Kansei) engineering. Engage Network work package 2. Accessed at www.engage-design.org
Fellbaum, C. (1998). WordNet. Electronic Lexical Database. Cambridge, MA: MIT Press.
Harris, Z. (1985). Distributional structure. In The Philosophy of Linguistics (Katz, J.J., Ed.), pp. 26–47. New York: Oxford University Press.
Landauer, T.K., Foltz, P.W., & Laham, D. (1998). Introduction to latent semantic analysis. Discourse Processes 25, 259–284.Google Scholar
Manning, C. & Schütze, H. (1999). Foundations of Statistical Natural Language Processing. Cambridge, MA: MIT Press.
Nagamachi, M. (1995). Kansei engineering: a new ergonomic consumer-oriented technology for product development. International Journal of Industrial Ergonomics 15, 3–11.Google Scholar
Nagamachi, M. (1999). Kansei Engineering and Its Applications in Automotive Design, SAE Technical Paper 1999-01-1265.
Pantel, P. & Ravichandran, D. (2004). Automatically labeling semantic classes. Proc. HLT/NAACL-04, pp. 321–328.
Rapp, R. (2004). A freely available automatically generated thesaurus of related words. Proc. 4th Language Resources and Evaluation Conf., pp. 395–398.
Sharoff, S. (2006). Open-source corpora: using the net to fish for linguistic data. International Journal of Corpus Linguistics 11(4), 435–462.Google Scholar
Solves, C., Such, M.-J., Gonzalez, J.C., Pearce, K., Bouchard, C., Gutierrez, J.M., Prat, J., & Cruz Garcia, A. (2006). Validation study of Kansei engineering methodology in footwear design. In Contemporary Ergonomics 2006 (Bust, P.D., Ed.), pp. 164–168. London: Taylor & Francis.