Analyzing sentiments in Web 2.0 social media data in Chinese: experiments on business and marketing related Chinese Web
- PDF / 495,168 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 28 Downloads / 202 Views
Analyzing sentiments in Web 2.0 social media data in Chinese: experiments on business and marketing related Chinese Web forums Li Fan · Yulei Zhang · Yan Dang · Hsinchun Chen
Published online: 17 April 2013 © Springer Science+Business Media New York 2013
Abstract Web 2.0 has brought a huge amount of usergenerated, social media data that contains rich information about people’s opinions and ideas towards various products, services, and ongoing social and political events. Nowadays, many companies start to look into and try to leverage this new type of data to understand their customers in order to make better business strategies and services. As a nation with rapid economic growth in recently years, China has become visible and started to play an important role in the global business and economy. Also, with the large number of Chinese Internet users, a considerable amount of options about Chinese business and market have been expressed in social media sites. Thus, it will be of interest to explore and understand those usergenerated contents in Chinese. In this study, we develop an integrated framework to analyze user sentiments from Chinese social media sites by leveraging sentiment analysis techniques. Based on the framework, we conduct experiments on two popular Chinese Web forums, both related to
L. Fan · H. Chen Department of Management Information Systems, Eller College of Management, University of Arizona, Tucson, AZ 85721, USA L. Fan · e-mail: [email protected] H. Chen · e-mail: [email protected] Y. Zhang (&) · Y. Dang Computer Information Systems, The W. A. Franke College of Business, Northern Arizona University, 20 W. McConnell Drive, Flagstaff, AZ 86011, USA e-mail: [email protected] Y. Dang e-mail: [email protected]
business and marketing. By utilizing Elastic Net together with a rich body of feature representations, we achieve the highest F-measures of 84.4 and 86.7 % for the two data sets, respectively. We also demonstrate the interpretability of Elastic Net by discussing the top-ranked features with positive or negative sentiments. Keywords Web 2.0 · Social media · Chinese sentiment analysis
1 Introduction Web 2.0 has enabled two-way communication between Internet users and online communities [1]. Not only acquiring information, nowadays people can actively write and post information such as opinions and ideas to the Internet. Thus, a large volume of opinion-rich content has been generated in various social media sites. For example, a lot of consumers have started to use the new media to express both positive and negative opinions [2]. Analyzing and understanding these opinions in user-generated contents is of great importance for both consumers and companies [3, 4]. For consumers, opinions expressed by others could provide useful information for them to make better purchase decisions. For companies, they can better understand their customers’ perceptions about the products and services and then refine, adjust, and create appropriate business strategies accordingly. To analyze the optio
Data Loading...
