Abstract

The development of online virtual communities has raised the importance in analyzing massive volume of text from websites and social networks. This research analyzed financial blogs and online news articles to develop a public mood dynamic prediction model for stock markets, referencing the perspectives of behavioral finance and the characteristics of online financial communities. This research applies big data and opinion mining approaches to the investors’ sentiment analysis in Taiwan. The proposed model was verified using experimental datasets from ChinaTimes.com, cnYES.com, Yahoo stock market news, and Google stock market news over an 18 month period. Empirical results indicate the big data analysis techniques to assess emotional content of commentary on current stock or financial issues can effectively forecast stock price movement.

Introduction

The rapid development of online communities and the mobile Internet have driven a rapid expansion in online news forums and discussions which potentially include data useful for investment decision making. Various approaches have been developed for analyzing “Big Data”, referred to as text, web and sentiment mining. Sentiment Mining is often referred to as opinion mining, sentiment analysis or subjectivity analysis. It is a form of textual analysis which automatically extracts words and sentences which appear with higher frequency and are potentially meaningful. “Sentiment” refers to contextualized attitudes, comments, and feelings, thus sentiment mining is designed to detect, extract, and analyze hidden sentiment or semantic orientation. Sentiment mining has been mostly applied to textual analysis social network content. In 2015, eMarketer found that 89% of US companies use social media as a marketing tool [1]. In 2013, RBC Capital found that the return on investment for advertising on Facebook is only slightly lower than that for top-ranked Google, and is ahead of Twitter, LinkedIn, Yahoo, AOL and other platforms [2], reflecting the significant marketing impact of social media. In addition, after U.S. Securities and Exchange Commission (SEC) officially allowed listed companies to disclose their earnings on social networks in 2013, the world’s leading data providers including Townsend Reuters and Bloomberg Data began to provide data analysis services for social network services. In 2014, the worlds’ largest social data provider GNIP noted that sentiment analysis social networks first began in 2010 [3]. The initial purpose of such activities was to allow companies to assess customer reaction to and satisfaction with their products and services. However, sentiment analysis of social networks has significant potential in other domains, such as the prediction of stock price movements.

While we understand well how social media channels sway consumers, there is little understanding of their influence on online trading behavior. We argue that social media are creating a new class of self-directed online traders by simultaneously encouraging and biasing trading decisions. Through an empirical study, we show that heavy social media users are more likely to engage in online trading but are largely affected by online herding behavior, and are four times more likely to blindly follow other traders. Bloggers, influencers, social network contacts, and social media news shape these users’ online trading behaviors. As online traders influenced by social media are unlikely to receive adequate returns, companies face an ethical dilemma: They could leverage social media to efficiently access funds but they risk inappropriately exploiting the inexperience of online traders biased by social media. We offer a set of nine practical recommendations for organizations to respond to these new challenges.

The impact of social media on trading: The rise of online traders

Bitcoin and cryptocurrencies represent a fascinating and timely case to study. A bitcoin traded in July 2010 for just $0.06, in January 2017 for $900, and in December 2017 for $19,700. In 2010, $100 invested would have turned into over $30 million in 2017. By the end of 2017, there were over 1,300 cryptocurrencies with a market capitalization of about $587 billion and $500 billion daily volume of online transactions. After reaching their peak, the cryptocurrencies’ prices started dramatically fluctuating and bitcoin’s price dropped from $19,000 to about $5,000 in just a few months. One possible reason for both the performance and risk of cryptocurrencies is the effect of social media on online trading, which started from the beginning. The creator of Bitcoin, Satoshi Nakamoto, published a white paper online, disseminating information in over 500 posts in a social media forum. Bitcoin started attracting interest in 2011 when WeUseCoins published an online video that went viral on social media, reaching 6.4 million views. Social media diffused information about companies accepting bitcoin as payment and about the growth of cryptocurrencies. Garcia, Tessone, Mavrodiev, and Perony (2014) stipulated that the volume of word-of-mouth communications in social media and the volume of information search diffused through social media influenced price growth and fluctuations of Bitcoin. Mai, Shan, Bai, Wang, and Chiang (2018) found that the user-generated content diffused through social media had a significant impact on Bitcoin volume of transactions and performance. The cryptocurrency case is an example of how social media can significantly affect online trading, calling for the need to understand the phenomenon.

There is an increasing trend on social media platforms of users trying to market themselves as brands to gain attention and cultural and monetary value, especially among the subculture of personal style bloggers. These bloggers ذare primarily young women who post pictures of their outfits and their possessions and comment on fashion-related issues and products [1]. Due to their large numbers of followers, some well-known style bloggers are influential and attain fame in both online and offline worlds. They enjoy such popularity because social media platforms have established a public persona [2], where the individual choice, autonomy, empowerment, and independence of women are emphasized. Evidence shows that style bloggers who use social media as a platform to establish their self-brands enjoy high levels of creativity and self-expression; they do not have to follow the conventional fashion mold—i.e., thin, tall, white, and rich [3]. This seemingly upends the traditional fashion realm, which includes fashion magazines and runways shows. Nevertheless, the obsession with investing time and finances into new technology with revolutionary potential, such as social media, obscures the fact that style bloggers who promote themselves online are still firmly contextualized in a neoliberal capitalist framework and reinforce the existing hierarchies of class, gender, aesthetics, and tastes [1]. This study seeks to address this controversy by investigating style bloggers’ self-branding practices on Instagram. Specifically, we address the following questions: (1) How do people establish their branded-selves on a social media platform? (2) What are the distinct technological features of social media as a tool for self-branding? To answer these questions, we examined style bloggers on an image-based social media platform, Instagram. Instagram is a rapidly growing visual self-branding tool; it has become the most popular and largest photo-sharing social media platform in the world, with 600 million monthly active users [4]. Furthermore, Instagram users have the highest scores for showing affection for and following fashion trends compared with three other mainstream social networking sites (Facebook, Twitter and Snapchat) [5]. Given that the Internet is increasingly turning into a visual medium and more and more individuals are using images to express themselves, we believe that Instagram is an appropriate platform for examining individual users’ self-branding practices. This study contributes to both the academic and practical fields. For academia, this study extends the use and gratification theory [6-10] by explaining how women use social media to satisfy their need for information, personal identity, integration and social interaction, and entertainment [11]. Regarding the practical significance of this research, the findings of this study can help marketers understand audiences’ preferences for and interests in fashion and style-related products.

مقاله سال 2016

 مجله تحقیقات بازاریابی – Journal of Business Research

Motivation has been broadly characterized as one of the more powerful predictors of human behavior—a key predictor of performance for practitioners and a crucial element in creating theories of behavior for theorists (Steers, Mowday, & Shapiro, 2004). Thus, it is not surprising that motivation appears in a variety of discipline journals (e.g., Davis, Bagozzi, & Warshaw, 1992; Fitzmaurice, 2005; Levin & Hansen, 2008; Miao & Evans, 2007), nor that business researchers and managers have great interest in understanding individuals’ motivation to use social media and mobile technologies on behalf of businesses (e.g., Leftheriotis & Giannakos, 2014; Levin, Hansen, & Laverie, 2012).

While most research studies and textbooks continue to treat motivation as a bi-dimensional construct (comprised of extrinsic motivation and intrinsic motivation), a few studies have suggested a third form of motivation—apathetic motivation (e.g., Deci & Ryan, 2002; Levin et al., 2012; Vallerand, Fortier, & Guay, 1997). Apathetic motivation is defined as a lack of interest or enthusiasm in a particular task or topic. Reasons for its presence could include lack of confidence in the ability to perform a task and/or lack of belief in materialization of the desired outcomes. We find it fascinating that there appears to be a prevailing view in research that a “lack of interest” is treated as equivalent to a “lack of motivation” in the conceptual discussion, scaling, and analysis in most research studies that mention it. Verily, we disagree with that treatment. We argue that apathetic motivation is not simply the absence of other motivations. Rather, we posit that the lack of interest or enthusiasm is independent of intrinsic and extrinsic motivations. Indeed, we propose that what many have considered to be a single phenomenon (compounding motivations and amotivations) is actually multiple distinct phenomena, as specified in the next paragraph.

Consequently, the purpose of this research is to outline and investigate the hypothesis that apathetic motivation can exist simultaneously with extrinsic motivation and/or intrinsic motivation—with the goal of improving our understanding of why some intrinsically or extrinsically motivated workers do not act on those motivations in the important context of using social media for businesses. Adopting that goal, the contribution of this article to the existing motivation literature is the first empirical investigation containing joint examination of (1) apathetic motivation’s direct contribution to behavioral intention independent of extrinsic and intrinsic motivations’ contributions; (2) potential interactions of apathetic motivation with (a) extrinsic or intrinsic motivation on intention to use or (b) intention to use on actual usage or outcomes; and (3) interactions between intention to use social media technologies based on the combined motivations and employee job roles (i.e., moderated moderation).