Contemporary research has leveraged social network data as a predictive tool for decision-making process in the capital market. Yet, its effectiveness may be compromised by social contagion. This study addresses this problem by introducing conversation-level measures that capture how interactions among investors affect market predictions. Drawing on social contagion theory, we identified three conversation conditions—argument similarity, sentiment similarity, and conversation size—and examined their association with the likelihood of abrupt stock price changes, which indicate a loss of collective wisdom. Our analysis of 18 million StockTwits posts for 859 Initial Public Offerings (2008–2017) reveals that conversations with highly similar arguments, highly similar sentiments, and larger size are significantly associated with an increased likelihood of abrupt stock price changes in the subsequent week. Moreover, out-of-sample tests confirm that monitoring conversational dynamics enhances the predictive power of social network analytics, offering valuable guidance for investors and practitioners. Our study extends the theoretical framework of social contagion by highlighting the importance of the conversation level and provides practical recommendations for refining trading strategies based on social media data. • Applying social contagion theory to study stock returns prediction by social media posts. • Examining cognitive and emotional contagion and extensity of social contagion. • Cautioning against over-reliance on social media data for stock returns prediction. • Emphasizing the significance of conversation-level metrics in social media analysis.

Our study proposes and tests a method for developing domain-specific dictionaries tailored for textual analysis in information systems research. Traditionally, dictionaries have been widely used for content classification according to sentiment; however, we introduce an alternative approach focused on creating dictionaries from sentiment-devoid documents. We demonstrate this method by developing a dictionary specific to Securities and Exchange Commission (SEC) investigations. Analyzing 150,432 publicly available SEC documents, we gained insights into the semantics of communications between the SEC and firms. To evaluate the dictionary, we analyzed SEC comment letters to predict the likelihood of firms reporting information technology control weaknesses (ITCWs), information technology audit fees, and cyber risks . Our dictionary outperformed five benchmarking dictionaries, explaining a higher proportion of variance in ITCW likelihood, information technology audit fees , and cyber risks. This study enhances the effectiveness of dictionaries in analyzing sentiment-devoid business and governance documents and results in a specialized dictionary for SEC communications.

This paper investigates the association between retail investors’ online activity and the pricing of initial public offerings (IPOs). We utilize data from Google Trends and StockTwits to analyze price revision for 901 U.S. IPOs, and find that the online search count, social media post count, and post sentiment are positively associated with IPO pricing. One-standard-deviation increases in these variables correspond to price revision increases of 9.02%, 50.73%, and 70.22%, respectively. Additionally, online search plays a more significant role in influencing IPO price revision when social media discussions about a specific IPO exhibit higher sentiment inequality among participants.

Few open source software (OSS) projects have been great success stories. One reason for this is project stagnation after developers quit their projects. This fact has motivated researchers to examine the factors that influence developers' intention to continue their participation. One factor is trust among developers. The effects of trust on developers' intention to remain with their projects have been studied. However, little is known about its conceptual counterpart, distrust. This dearth of knowledge motivates our research. First, we studied what OSS project features affect trust and distrust among developers. Second, we examined how trust and distrust influence developers' intention to continue participating. We tested our hypotheses with 451 data points from an online survey. Our findings indicate that cooperative norms and effective communication engender trust, whereas an accreditation mechanism eliminates distrust. Additionally, trust positively influences their intention to continue participating, whereas distrust negatively influences it.

Many online firms are investing money in various means and methods to track online customers' navigation patterns and analyze their characteristics and their web behaviours. With better understanding of the navigation patterns, the firms can provide breakthrough customer service. Currently, there are numerous frameworks ready to help the firms realise their dream to understand their customers. However, these frameworks are limited to server-sided tracking, and the firms lose their customers' footprints once the customers leave their web sites. Therefore, this paper proposes a framework of user remote tracker, and this tracking method can be used to discover much value of customer information. We implemented this tracker, and used it to record the Internet activities from web users in a controlled lab experiment setting. We performed preliminary data analysis to draw a linkage between web customers' characteristics (such as personality traits) and their browsing behaviors.

Personalization agents are incorporated in many Web sites to tailor content and interfaces for individual users. In contrast to the proliferation of personalized Web services worldwide, empirical research on the effects of Web personalization is scant. How does exposure to personalized offers affect subsequent product consideration and choice outcome? Drawing on literature in human-computer interaction (HCI) and user behavior, this research examines the effect of three major elements of Web personalization strategies on users' information processing through different decision-making stages: personalized content quality, feature overlapping among alternatives, and personalized message framing. These elements can be manipulated by a firm during implemention of its personalization strategy. A study using a personalized ringtone download Web site was conducted. The findings provide empirical evidence of the effects of Web personalization. In particular, when users are forming their consideration sets, the agents can play a role in helping users discover new products or generate demand for unfamiliar products. Once a decision has been made, however, the personalization agent's persuasive effects diminish. These results establish that the role of personalization agents changes at different stages of users' decision-making process.