Home // IMMM 2017, The Seventh International Conference on Advances in Information Mining and Management // View article

A Study of Extracting Demands of Social Media Fans

Authors:
Chih-Chuan Chen
Hui-Chi Chuang
Chien-Wei He
Sheng-Tun Li

Keywords: Kansei engineering; topic model; text mining; demand analysis

Abstract:
With the boom of the Internet era, people spend more and more time on social media, such as Facebook, Twitter, and Tumblr. How to get people's attention is becoming a critical issue for companies and celebrities, since it is an era of distractions. In the past, if a company wanted to become popular, it simply spent money on traditional media, like newspapers or TV commercials. Now, one has to know audiences’ needs and then utilize the new social media platforms to reach those specific audiences. How to know the demand of customers (audiences) is an unavoidable challenge? To answer that question, most commonly used methods are conducting market surveys, including questionnaires and focus groups. However, it is not only time wasting but also effort consuming. In this paper, we combine text mining techniques and Kansei engineering to analyze audiences’ demand. Firstly, we collect data from Facebook Fan Pages, including numerical data (number of likes, shares, comments) and text data (postcontent). Secondly, we extract the topics by using Latent Dirichlet Allocation (LDA). Thirdly, experts will give eight pairs of Kansei words that are most relevant to the articles. Finally, we produce a semantic differential questionnaire to find the relationship between topics and Kansei words. The relationship can give helpful insights into the demands of the audience. Moreover, a supervised LDA is incorporated in this approach to predict the popularity of posts.

Pages: 7 to 12

Copyright: Copyright (c) IARIA, 2017

Publication date: June 25, 2017

Published in: conference

ISSN: 2326-9332

ISBN: 978-1-61208-566-1

Location: Venice, Italy

Dates: from June 25, 2017 to June 29, 2017