A Study of Kansei Demand of Fans in Social Media

• Main Authors: CHIEN-WEIHE, 何健偉
• Other Authors: Sheng-Tun Li
• Format: Others
• Language: en_US
• Published: 2016
• Online Access: http://ndltd.ncl.edu.tw/handle/cvg3k3

碩士 === 國立成功大學 === 資訊管理研究所 === 104 === As the booming of the Internet era, people spend more and more time on social media, such as Facebook, Twitter, Tumblr, etc. How to catch people’s eye is becoming a critical issue for companies and celebrities, since it’s an era of distractions. In the past, if you or your company want to become popular, simply spend money on traditional media, like newspaper, TV commercial. Now, you need to know audiences’ need, then utilize the new social media platform to reach those specific audiences. There is another question raised, that is how to know the demand of customers (namely audiences)? Most common used methods are conducting a market survey, including questionnaires and focus group. However, it’s not only wasting time but also effort-consuming. In this research, we combine text mining technique and Kansei engineering to analysis audiences’ demand. First, we collect data from Facebook Fan Pages, including numerical data (number of likes, shares, comments) and text data (posts’ content). Then extract the topics by using Latent Dirichlet allocation (LDA). Next, Experts will give eight pairs of Kansei words that most relevant for the articles. After that, we conduct semantic differential questionnaire to find the relationship between topics and Kansei words. The relationship can be helpful to writers to know the demand of audience. Finally, we use supervised LDA to predict the popularity of posts.