Paper Type
Complete
Paper Number
1201
Description
Brand personality fulfills people’s self-expression and social needs, leading to positive outcomes for the brand. This encourages firms to understand their customers’ thoughts and develop branding strategies actively. Traditionally, brand personality assessment relies on time-consuming and labor-intensive survey-based methods, lacking the ability to monitor changes continuously. The availability of social media platforms has provided researchers and practitioners with various kinds of data expressed by their customers. The study develops deep-learning-based brand personality prediction methods, by leveraging user-generated content to measure customer-perceived brand personality. The proposed methods incorporate the multi-task learning framework and show superior prediction effectiveness over all benchmark methods. Our ablation study also validates the effectiveness of mechanisms incorporated into our proposed methods. This study enables greater exploration of brand personality, and the proposed methods allow firms to investigate and monitor the brand personality of their brands and those of their competitors using data collected from social media platforms.
Recommended Citation
Wei, Chih-Ping; Yang, Ren-Han; and Hung, Lei-Yao, "Predicting Brand Personality with User-generated Content: Deep Learning Methods" (2024). PACIS 2024 Proceedings. 7.
https://aisel.aisnet.org/pacis2024/track03_ba/track03_ba/7
Predicting Brand Personality with User-generated Content: Deep Learning Methods
Brand personality fulfills people’s self-expression and social needs, leading to positive outcomes for the brand. This encourages firms to understand their customers’ thoughts and develop branding strategies actively. Traditionally, brand personality assessment relies on time-consuming and labor-intensive survey-based methods, lacking the ability to monitor changes continuously. The availability of social media platforms has provided researchers and practitioners with various kinds of data expressed by their customers. The study develops deep-learning-based brand personality prediction methods, by leveraging user-generated content to measure customer-perceived brand personality. The proposed methods incorporate the multi-task learning framework and show superior prediction effectiveness over all benchmark methods. Our ablation study also validates the effectiveness of mechanisms incorporated into our proposed methods. This study enables greater exploration of brand personality, and the proposed methods allow firms to investigate and monitor the brand personality of their brands and those of their competitors using data collected from social media platforms.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
Analytics