Ontology-based Sentiment Analysis for Fan Page

• Main Authors: Jian-Hao He, 何堅皓
• Other Authors: Cheng-Lung Huang
• Format: Others
• Language: zh-TW
• Published: 2014
• Online Access: http://ndltd.ncl.edu.tw/handle/52753972770618484614

碩士 === 國立高雄第一科技大學 === 資訊管理研究所 === 102 === Social websites has become more and more important in our life. Many enterprises promote their services and products to fans via the social network websites. The feedbacks from fans are very important for enterprises to improve their products and services. The purpose of this research is to understand the overall sentiment of the fan’s responses by analyzing the responses posted by fans in the Facebook. This study calculated the sentimental score based on the predefined ontology. Take the cellphone for example, the ontology may consist of these categories: overall, shape, hardware, brand, price, and service. The sentimental score of a category was calculated by analyzing the sentiment of sentences in this category. The frequency of “like” was also weighted in the sentimental score calculation. This study demonstrated the Facebook page of “hTC” and “Xiaomi” using the proposed approach and the human judgment. The performance of high precision, recall and F1-measure of the proposed system were similar to those obtained by human judgment.