Developing a personal value analysis method of social media to support customer segmentation and business model innovation

Abstract

Companies need to find out about the personal values of customers and identify customer segments before developing effective business models (BMs) or marketing strategies. Therefore, understanding the personal values of customers is critical in BM design. Traditional personal value evaluation methods are laborious and time‐consuming. In recent years, social media have become an important platform for people to share ideas and express views, making the presence of a huge amount of opinions on platforms that can cater for the demand of data for personal value analysis of customers. This study took Facebook and Instagram as the targets and developed a novel personal value forecasting method to help enterprises obtain the various personal values of customer segments automatically at a lower cost. This study adopted Schwartz's value theory as the value model and proposed a consistency model and a relativity model for weighted calculations, so as to determine the feature of a value tag. Finally, the feature selection algorithm and classification algorithm were used for judging values. In the evaluation phase of this study, 61 participants were recruited to test the proposed method. The proposed method could assist enterprises in better understanding personal value information.

Segmentation of Social Media Platforms in Terms of Perceived Benefits: Cluster Analysis on Brand Followers

“…In addition to these studies, there are many studies conducted in recent years regarding customer segmentation (Chen et al, 2019;Funk et al, 2021;Abu-Bakar et al, 2021;Moon et al, 2021;Hedhilia et al, 2021;Špička & Zdeňka, 2022;Budhathoki et al, 2022;Wang et al, 2022;Caracciolo et al, 2022;Vigneau et al, 2022;Carla Kuesten et al, 2022). It has been observed that these studies on customer segmentation are mostly about organic products, food, and supplements.…”

Visual Simulator for Mastering Fundamental Concepts of Machine Learning

“…The advantages of Weka are therefore the analysis and application of the entire process of machine learning, from data pre-processing, creating a model by choosing one of many realized machine learning algorithms, and making predictions based on input data. Many researchers have used this tool because of its intuitive user interface and easy way to get results from a trained model [33][34][35][36][37][38].…”

A novel consumer preference mining method based on improved weclat algorithm

“…Association rule mining is one of the descriptive data mining analyzes, which is first introduced by Agrawal et al (1993). Association rule mining can find interesting relations and dependencies between variables in large databases (Chen et al, 2019). Then, the identification of these significant associations is helpful for many decision-making processes in business contexts (Weng and Huang, 2018;Medina-Serrano et al, 2019;Nguyen et al, JEC 16,1 2021).…”