Decision Making in Online Social Networks
Permanent URI for this collection
Browse
Recent Submissions
1 - 7 of 7
-
ItemThe Social Side of Brick and Mortar: The Impact of Brand-Related User-Generated Content on Different Consumer Typologies in Food Retailing( 2020-01-07)Social media influences most off-line purchasing decisions, thereby impacting the relationship between retailers and (prospective) customers. User-generated content (UGC) is a means of engaging with consumers and shaping their trust perception and loyalty. Based on a sample of 967 food retail customers, we identify four segments into which brand-related UGC consumers can be categorized: Brand Lovers, True-Blues, Detached Customers, and Confiding Customers. These clusters are distinct in terms of trust toward brand-related UGC, loyalty, brand-related UGC involvement, and demographics. Our findings add to the understanding of digital content marketing consequences by mapping four different brand-related UGC consumer typologies. From a managerial point of view, our findings suggest how to best engage with the determined consumer typologies and highlight the importance of social media for off-line businesses.
-
ItemFollow-back Recommendations for Sports Bettors: A Twitter-based Approach( 2020-01-07)Social network based recommender systems are powered by a complex web of social discussions and user connections. Short text microblogs e.g. Twitter present powerful frameworks for information consumption, due to their real-time nature in content throughput as well as user connections. Therefore, users on such platforms consume the disseminated content to a greater or lesser extent based on their interests. Quantifying this degree of interest is a difficult task based on the amount of information that such platforms generate at any given time. Thus, the generation of personalized profiles based on the Degree of Interest (DoI) that users have towards certain topics in such short texts presents a research problem. We address this challenge by following a two-step process in generation of personalized sports betting related user profiles in tweets as a case study. We (i) compute the Degree of Interest in Sports Betting (DoiSB) of tweeters and (ii) affirm this DoiSB by correlating it with their friendship network. This is an integral process in the design of a short text based recommender systems for users to follow i.e follow-back recommendations as well as content-based recommendations relying on the interests of users on such platforms. In this paper, we described the DoiSB computation and follow-back recommendation process by building a vector representation model for tweets. We then use this model to profile users interested in sports betting. Experiments using real Twitter dataset geolocated to Kenya shows the effectiveness of our approach in the identification of tweeter's DoiSBs as well as their correlation with their friendship network.
-
ItemFacebook Marketing Intelligence( 2020-01-07)Facebook marketing is becoming an increasingly important tool for companies to influence consumer decision-making. However, there is currently little empirical knowledge about the extent of influence of Facebook marketing on the decision-making process of consumers. This study contributes to these gaps in the literature and investigates the influence of Facebook marketing activities on the decision-making process of consumers. The theory revealed four Facebook marketing activities that affected the first two phases of the decision-making process. These Facebook marketing activities were advertisements, recommend/share, likes and reviews. Whether they actually had an impact has been tested with the help of survey among 112 respondents. The results of the regression analysis showed that all four Facebook marketing activities had a positive influence on the decision-making process.
-
ItemDo I Care Enough? Using a Prosocial Tendencies Measure to Understand Twitter Users Sharing Behavior for Minor Public Safety Incidents( 2020-01-07)Social media has been used to assist victims of crises, especially large-scale disasters. Research describes the importance of the crowd who are the first witnesses to any sort of crime or disaster. Among others, this paper focuses on smaller scale public safety incidents such as suspicious activities, and minor robberies. We investigate whether prosocial tendencies affect Twitter users’ decisions to share minor public safety incidents on Twitter. The scale used has six subscales including: public, anonymous, dire, emotional, compliant, and altruism. The data (N=363) was collected through Mechanical Turk using an online anonymous survey. Initial results showed a positive relationship between being prosocial and sharing public safety incidents on Twitter. However, once additional variables related to Twitter use were introduced (number of public safety official accounts followed, news exposure on social media, and tweet/retweet frequency), these variables fully mediated the relationship. Limitations and design implications are discussed.
-
ItemEmpowering Users Regarding the Sensitivity of their Data in Social Networks through Nudge Mechanisms( 2020-01-07)The use of online social networks (OSNs) is a continuous trade-off between relinquishing some privacy in exchange for getting some social benefits like maintaining (or creating new) relationships, getting support, influencing others’ opinions, etc. OSN users are faced with this decision each time they share information. The amount of information or its sensitivity is directly related to the amount of users’ loss of privacy. Currently, there are several approaches for assessing the sensitivity of the information based on the willingness of users to provide them, the monetary benefits derived from extracting knowledge of them, the amount of information they provide, etc. In this work, we focus on quantifying data sensitivity as the combination of all of the approaches and adapting them to the OSN domain. Furthermore, we propose a way of scoring publication sensitivity as the accumulative value of the sensitivity of the information types included in it. Finally, an experiment with 196 teenagers was carried out to assess the effectiveness of empowering users regarding the sensitivity of the publication. The results show a significant effect on users’ privacy behavior by the nudge message and the sensitivity included in it.
-
ItemA Probabilistic Model for Malicious User and Rumor Detection on Social Media( 2020-01-07)Rumor detection in recent years has emerged as an important research topic, as fake news on social media now has more significant impacts on people's lives, especially during complex and controversial events. Most existing rumor detection techniques, however, only provide shallow analyses of users who propagate rumors. In this paper, we propose a probabilistic model that describes user maliciousness with a two-sided perception of rumors and true stories. We model not only the behavior of retweeting rumors, but also the intention. We propose learning algorithms for discovering latent attributes and detecting rumors based on such attributes, supposedly more effectively when the stories involve retweets with mixed intentions. Using real-world rumor datasets, we show that our approach can outperform existing methods in detecting rumors, especially for more confusing stories. We also show that our approach can capture malicious users more effectively.
-
Item