Search

Social media has been changing not only the way people communicate with friends, but also the way providers communicate with consumers. Being as the popular means of information acquisition and facilitating the exploration of various topics and market trends, social media was also playing a key role in the development of online to offline (O2O) commerce. In the current study, bilingual text mining was conducted to analyze the trends of O2O commerce from the perspective of social media. Keywords and their concept linking diagrams were first identified to understand the important O2O trends in different languages. While keywords "China", "Alibaba", "Baidu", "DianPing", "Meituan", "Asia", "ecommerce" and "service" were the most strongly associated English terms with O2O, keywords "Baidu", "Tencent", "headlines", "Sina.com", mode", "ecommerce", "retail" and "platform" were closely related to the Chinese tweets. To further understand the similarities and differences between English tweets and Chinese tweets, we compared the bilingual text mining results according to the categories of company, region, service Apps and operation model. Our study provided important insights from crowd intelligence and revealed trends analysis about the recent O2O development in different language regions. • Study provides insights from crowd intelligence and reveals trend analysis. • Bilingual text mining approach helps understand O2O development trends. • O2O ecommerce in China attracts public attention from different languages regions. • Companies apply approach to develop O2O strategy to enhance competitive advantage. [ABSTRACT FROM AUTHOR]

Informed by the ABC model of attitude, this study employed natural language processing and machine learning techniques to explore the status quo, trends, and features of Weibo users' attitudes toward individuals who are lesbian or gay based on 1,813,218 Weibo retrieved posts that pertained to lesbians and gays from January 1, 2010, to December 31, 2019. Although the general attitudes, feeling/emotional reactions, and levels of support for the rights of lesbians and gays were identified as relatively positive for Weibo users and became even more so over time, the expressed knowledge of lesbians and gays was relatively inaccurate and the four aspects of attitude varied significantly as a function of individual-level variables (such as gender, age, education, sexual orientation, and verification type). The implications of these findings and suggestions that may improve the public acceptance of lesbians and gays are discussed. • 1,813,218 posts pertaining to lesbians/gays from January 1, 2010, to December 31, 2019, were collected and analyzed. • Weibo users' general attitudes, feelings, and support for the rights of lesbians and gays were relatively positive. • Weibo users are becoming increasingly supportive and accepting of the rights of lesbian and gay people. • The knowledge of Weibo users toward lesbians and gays was relatively inaccurate. • No significant differences were found for education with respect to the Weibo users' knowledge of lesbians and gays. [ABSTRACT FROM AUTHOR]