Using Personal Traits For Brand Preference Prediction

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 86–96, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Using Personal Traits For Brand Preference Prediction Chao Yang1, Shimei Pan2, Jalal Mahmud3, Huahai Yang4, and Padmini Srinivasan1 1Computer Science, The University of Iowa, Iowa City, IA, USA {chao-yang, padmini-srinivasan}@uiowa.edu 2University of Maryland, Baltimore County, Baltimore, MD, USA shimei@umbc.edu 3IBM Research Almaden, Almaden, CA, USA jumahmud@us.ibm.com 4Juji Inc, Saratoga, CA, USA hyang@juji-inc.com Abstract In this paper, we present a comprehensive study of the relationship between an indi- vidual’s personal traits and his/her brand preferences. In our analysis, we included a large number of character traits such as personality, personal values and individual needs. These trait features were obtained from both a psychometric survey and au- tomated social media analytics. We also included an extensive set of brand names from diverse product categories. From this analysis, we want to shed some light on (1) whether it is possible to use personal traits to infer an individual’s brand preferences (2) whether the trait features automatically inferred from social media are good prox- ies for the ground truth character traits in brand preference prediction. 1 Introduction Brand preference analysis is an important topic in marketing. To induce a desired brand choice, a marketer must understand the main factors that in- fluence a consumer’s brand preferences. This task is not easy since many factors may play a role in determining one’s brand preferences such as a consumer’s individual characteristics and prefer- ences as well as the properties of a brand (e.g., its perceived quality). Among consumer related factors, demographics such as age, gender and in- come have been studied extensively in marketing research (Evans, 1959; Elliott, 1994; Lin, 2002). In this study, we focus on analyzing a set of con- sumer characteristics, which have received less attention but with these features, potentially we can build more precise and more accurate brand preference prediction models. Especially, we fo- cus on three types of personal traits: personality, personal values, and individual needs. Personal- ity is a combination of characteristics or qualities that form an individual’s distinctive character; Per- sonal values reflect what are important to different individuals and what motivate them in their deci- sion making. Moreover, all people have certain needs that they want to satisfy. Thus, analyzing a comprehensive set of personal traits may help us understand the way we react to a particular brand. Previously, the relationship between personal traits and brand preference/purchase decisions has drawn limited interest in marketing research due to the difficulty in obtaining consumer traits on a large scale. Among these efforts, Westfall found that differences exist between the personalities of the owners of convertible cars and those of stan- dard & compact cars (Westfall, 1962). Similarly, the congruence of personal and brand personal- ity was suggested to be a predictor of consumers’ brand preferences (Jamal and Goode, 2001; Dik- cius et al., 2013). However, Shank & Lang- meyer found personal traits less useful in …

Content truncated to 500 words