Aspect-based Kano categorization

• Published in: International journal of information management 2019-06, Vol.46, p.163-172
• Main Authors: Martí Bigorra, Anna, Isaksson, Ove, Karlberg, Magnus
• Format: Article
• Language: English
• Subjects: Aspect; Categorization; Classification; Coffee; Computer Aided Design; Customer satisfaction; Data mining; Datorstödd maskinkonstruktion; Designers; Digital media; Feature extraction; Kano; Product design; Product reviews; Product specifications; Sentiment analysis; Sentiment analysis (SA); Smartphones; Target setting
• ISSN: 0268-4012; 1873-4707; 1873-4707
• DOI: 10.1016/j.ijinfomgt.2018.11.004

•The aim of this paper is to derive a methodology for how to classify the extracted aspects from product reviews in terms of Kano categories (must-be, one-dimensional and attractive).•The proposed methodology takes as a basis the general output of any aspect-based sentiment analysis method to provide a Kano categorization of the extracted aspects.•Aspect frequency (AFi), sentiment (Oi+, Oi−) and Product Brand Dominance (PBDi) are the metrics used to categorize aspects.•To determine if an aspect Ai is equally mentioned in the discussion of each identified product brand group, Product Brand Dominance (PBDi) measure is proposed.•Results of the case study highlight the possibility for companies to identify relevant product features as input for the design process without the need to design (Kano) surveys. Customers commonly share opinions and experiences about products via the internet by means of social media and networking sites. The generated textual data is often analysed by means of Sentiment Analysis (SA) as means to assess customer opinions on product features more efficiently than through surveys. To enable a more objective product target setting, the impact of product feature performance changes on customer satisfaction is essential. Kano et al. (1984) presented a survey-based model to classify product features based on their impact on customer satisfaction to aid designers in their product target setting. Approaches extending the Kano model rely on customer surveys as input data. In addition, existing studies classifying extracted product features from textual data (e.g. product reviews) rarely provide a clear separation in terms of Kano categories. Thus, the impact of identified product features on customer satisfaction remains unknown to product designers. This paper presents a methodology for autonomously classifying extracted aspects from textual data into Kano categories. For verification purposes, two examples using coffee machine and smartphone user reviews are presented. Results indicate that the proposed methodology efficiently provides product designers with insightful customer information through the proposed aspect categorization.