Who are the spoilers in social media marketing? Incremental learning of latent semantics for social spam detection

With the rise of social web, there has also been a great concern about the quality of user-generated content on social media sites (SMSs). Deceptive comments harm users’ trust in online social media and cause financial loss to firms. Previous studies use various features and classification algorithms to detect and filter social spam on several social media platforms. However, to the best of our knowledge, previous studies have not exploited both probabilistic topic modeling and incremental learning to detect social spam on SMSs. Thus, the main contribution of this paper is design of a novel detection methodology that combines topic- and user-based features to improve the effectiveness of social spam detection. The proposed methodology exploits a probabilistic generative model, namely the labeled latent Dirichlet allocation (L-LDA), for mining the latent semantics from user-generated comments, and an incremental learning approach for tackling the changing feature space. An experiment based on a large dataset extracted from YouTube demonstrates the effectiveness of our proposed methodology, which achieves an average accuracy of 91.17 % in social spam detection. Our statistical analysis reveals that topic-based features significantly improve social spam detection, which has significant implications for business practice.     

Bargains in the diamond market? How to take advantage from online information

This paper empirically analyses the price of diamonds from different perspectives. The sample data contains detailed information on more than 165,000 diamonds certified by Gemological Institute of America, which can be purchased since July 2016 from a large online diamond supplier. Our empirical analysis allows to extend the classic 4Cs model in several directions as follows: (a) the classical 4Cs model is insufficient in order to explain the price, so that other attributes, such as polishing, symmetry, and fluorescence, must be incorporated to accurately estimate the price of a particular piece; (b) the large sample size allows us to analyse specific price ranges characterized by high market activity; (3) a very detailed analysis has been conducted for round diamonds, incorporating interactions between attributes within the regression model and studying the marginal rates of substitution between diamond weight and alternative characteristics given a certain price. Our model is able to detect diamonds that could constitute a clear market opportunity for buyers. This model can help to select efficient demand options taking advantage of the information available on the website, improving the overall efficiency of exchange in this sector.     

How much to spend on flexibility? Determining the value of information system flexibility

Upon the initiation of an information system (IS), decision makers typically have a choice between different levels of flexibility, that is the extent to which the IS can be modified or upgraded during its subsequent lifetime. In the current paper, we regard IS flexibility as an option that is available to the decision maker, and demonstrate several approaches to determine its value. Extending a previous theory of IS flexibility, we calculate the value of flexibility by applying decision tree analysis (DTA), real option analysis (ROA), and explicit risk assessment based on simulation experiments. We find that the deterministic treatment of IS flexibility tends to underestimate its value, whereas ROA can overestimate its value, in particular in low-risk situations. Our findings highlight the need for the concrete measurement of IS flexibility.     

How social media usage affects employees’ job satisfaction and turnover intention: An empirical study in China

Social media are frequently used in enterprises for both work-related and non-work-related (social) purposes. Drawing on the organizational commitment theory, we developed a research model to explore how different purposes of social media usage affect employees’ job satisfaction and turnover intention in the Chinese context. Online and offline surveys were conducted in China, generating 298 valid responses for analysis. The results suggest that the following: (1) work-related and social-related social media usage positively affects employees’ organizational commitment through their organizational engagement; (2) social media usage improves job satisfaction and reduces employees’ turnover intention through improving their engagement and organizational commitment; and (3) in the process of social media usage influencing employees’ job satisfaction and turnover intention, employees of different genders show significant differences.     

A note on the relationship between market efficiency and adaptability – New evidence from artificial stock markets

We developed various artificial stock markets populated with different numbers of traders using a special adaptive form of the Strongly Typed Genetic Programming (STGP)-based learning algorithm. We then applied the STGP technique to historical data from three indices – the FTSE 100, S&P 500, and Russell 3000 – to investigate the formation of stock market dynamics and market efficiency. We used several econometric techniques to investigate the emergent properties of the stock markets. We have found that the introduction of increased heterogeneity and greater genetic diversity leads to higher market efficiency in terms of the Efficient Market Hypothesis (EMH), demonstrating that market efficiency does not necessarily correlate with rationality assumptions. We have also found that stock market dynamics and nonlinearity are better explained by the evolutionary process associated with the Adaptive Market Hypothesis (AMH), because different trader populations behave as an efficient adaptive system evolving over time. Hence, market efficiency exists simultaneously with the need for adaptive flexibility. Our empirical results, generated by a reduced number of boundedly rational traders in six of the stock markets, for each of the three financial instruments do not support the allocational efficiency of markets, indicating the possible need for governmental or regulatory intervention in stock markets in some circumstances.     

Do you have anything to hide? Infidelity-related behaviors on social media sites and marital satisfaction

Social media provides one route to behaviors that may be potentially harmful to romantic relationships, such as communicating with alternative partners, which can sometimes create relationship conflict, breakups, or divorce. Limited empirical evidence exists concerning social media infidelity-related behaviors and marital relationships. This study examined whether married/cohabiting individuals are using social media sites to engage in online infidelity-related behaviors and to what extent this related to relationship satisfaction, ambivalence, and relational attachment characteristics as reported by 338 married/cohabiting individuals from 176 families. Only a small percentage of married/cohabiting couples reported engaging in social media infidelity-related behaviors; however, more engagement in infidelity-related behaviors on social media was significantly related to lower relationship satisfaction, higher relationship ambivalence, and greater attachment avoidance and anxiety in both women and men. Additionally, attachment anxiety and gender interacted with relationship satisfaction in predicting online infidelity-related behaviors when controlling for other variables. Implications are discussed.     

Subjective well-being and social media use: Do personality traits moderate the impact of social comparison on Facebook?

The purpose of the study was to explore whether personality traits moderate the association between social comparison on Facebook and subjective well-being, measured as both life satisfaction and eudaimonic well-being. Data were collected via an online questionnaire which measured Facebook use, social comparison behavior and personality traits for 337 respondents. The results showed positive associations between Facebook intensity and both measures of subjective well-being, and negative associations between Facebook social comparison and both measures of subjective well-being. Personality traits were assessed by the Reinforcement Sensitivity Theory personality questionnaire, which revealed that Reward Interest was positively associated with eudaimonic well-being, and Goal-Drive Persistence was positively associated with both measures of subjective well-being. Impulsivity was negatively associated with eudaimonic well-being and the Behavioral Inhibition System was negatively associated with both measures of subjective well-being. Interactions between personality traits and social comparison on Facebook indicated that for respondents with high Goal-Drive Persistence, Facebook social comparison had a positive association with eudaimonic well-being, thus confirming that some personality traits moderate the association between Facebook social comparison and subjective well-being. The results of this study highlight how individual differences in personality may impact how social comparison on Facebook affects individuals’ subjective well-being.     

A study of negative emotional disclosure behavior in social network media: Will an unexpected negative event and personality matter?

Why would people feel the need to disclose their negative emotions? Using the theory of conservation of resources, we hypothesize disclosure intention and behavior would be influenced by duration and severity of the negative emotional state. Moreover, we predict the effect of unexpected events and “the Big Five” personality traits on disclosure intention. Besides disclosure intention, we also tapped if the respondents have disclosed their negative emotions on their Facebook profile. In this study, we surveyed 255 Facebook users on their experiences from negative life events under four categories – social relationship, work, health and monetary issues. The results support all of our hypotheses. In particular, our post-hoc analyses show differences between females and males on the influence mechanism behind their disclosure intention. Females are more likely to disclose their problems relating to social relationship, work and health problems on Facebook than males.     

How social is social responses to computers? The function of the degree of anthropomorphism in computer representations

Testing the assumption that more anthropomorphic (human-like) computer representations elicit more social responses from people, a between-participants experiment (N = 168) manipulated 12 computer agents to represent four levels of anthropomorphism: low, medium, high, and real human images. Social responses were assessed with users’ social judgment and homophily perception of the agents, conformity in a choice dilemma task, and competency and trustworthiness ratings of the agents. Linear polynomial trend analyses revealed significant linear trends for almost all the measures. As the agent became more anthropomorphic to being human, it received more social responses from users.     

What motivates health information exchange in social media? The roles of the social cognitive theory and perceived interactivity

Social media has become an attractive platform for users to exchange health information with others. However, little research has been done to identify the determinants of health information exchange. By integrating aspects of the social cognitive theory and perceived interactivity, this study proposes a research model to investigate the antecedents of health information exchange in social media. Data collected from Facebook users with health information exchange experience were used to examine the proposed model. The results demonstrate that human-to-human interaction, human-to-information interaction, outcome expectation of health self-management competence, and outcome expectation of social relationships have a significant impact on health information exchange behavior. The results also reveal that human-to-human interaction exerts a significant influence on the outcome expectation of health self-management competence and the outcome expectation of social relationships, while human-to-information interaction has a positive effect on the outcome expectation of health self-management competence. The implications for the theory and practice and future research directions are discussed.     

How did micro-mobility change in response to COVID-19 pandemic? A case study based on spatial-temporal-semantic analytics

Cities worldwide adopted lockdown policies in response to the outbreak of coronavirus disease 2019 (COVID-19), significantly influencing people's travel behavior. In particular, micro-mobility, an emerging mode of urban transport, is profoundly shaped by this crisis. However, there is limited research devoted to understanding the rapidly evolving trip patterns of micro-mobility in response to COVID-19. To fill this gap, we analyze the changes in micro-mobility usage before and during the lockdown period exploiting high-resolution micro-mobility trip data collected in Zurich, Switzerland. Specifically, docked bike, docked e-bike, and dockless e-bike are evaluated and compared from the perspective of space, time and semantics. First, the spatial and temporal analysis results uncover that the number of trips decreased remarkably during the lockdown period. The striking difference between the normal and lockdown period is the decline in the peak hours of workdays. Second, the origin-destination flows are used to construct spatially embedded networks. The results suggest that the origin-destination pairs remain similar during the lockdown period, while the numbers of trips between each origin-destination pair is reduced due to COVID-19 pandemic. Finally, the semantic analysis is conducted to uncover the changes in trip purpose. It is revealed that the proportions of Home, Park, and Grocery activities increase, while the proportions of Leisure and Shopping activities decrease during the lockdown period. The above results can help planners and policymakers better make evidence-based policies regarding micro-mobility in the post-pandemic society.     

How social-media-enabled co-creation between customers and the firm drives business value? The perspective of organizational learning and social Capital

Contemporary business organizations are increasingly turning their attention to value co-creation using social media between individual customers and business organizations in the process of new product development (NPD). However, little is known about the mechanisms underlying social-media-based customer-firm co-creation and their implications for business value in NPD. To address this knowledge gap, this study develops a model from the perspective of organizational learning and social capital to examine how the social-media-based customer-firm co-creation mechanism conceptualized as the structural, cognitive, and relational dimension of social capital influences the first-order knowledge outcome (knowledge transfer effectiveness) and second-order dynamic capability outcome (absorptive capacity), and how these co-creation outcomes ultimately influence organizational performance. The model is tested using survey data from 149 Chinese mobile application developers. The results indicate that social-media-based structural, cognitive, and relational linkage, in particular the structural linkage, is an important co-creation mechanism to improve organizational performance. Knowledge transfer effectiveness and absorptive capacity have significant mediating effects in this co-creation mechanism-outcomes-performance framework. Further, the moderating effects of social media use level on the relationships between co-creation mechanism and outcomes are largely supported. The study contributes to theory and practice by shedding light on the social-media-based customer-firm co-creation in NPD at a process level.     

How do you frame ill-defined problems? A study on creative logics in action

Problem framing is pivotal to fostering knowledge and innovation, especially in the modern environment where problems are often ill defined. However, the managerial literature has thus far mainly addressed problem framing from an outcome perspective, overlooking the processes that lead to the outcomes. A common view is that the complexity, ambiguity and uncertainty of ill-defined problems call for a creative process. Therefore, through ethnographically observing six design thinking workshops, this study adopts a qualitative approach to explore the problem framing creative process. Specifically, we unpack three thinking modalities involved in the creative process (i.e. creative logics) of problem framing: analogical reasoning, associative thinking and abductive reasoning. We suggest that individuals enact these through seven creative operations. In addition, we link these creative operations to two types of problem framing outcomes: referenced frames and crafted frames. From a practitioner perspective, this study casts new light on the importance of problem framing for creativity and innovation, highlighting the ways in which individuals operationalize the creative logics to frame ill-defined problems as original problems worth solving.     

Who interacts on the Web?: The intersection of users’ personality and social media use

In the increasingly user-generated Web, users’ personality traits may be crucial factors leading them to engage in this participatory media. The literature suggests factors such as extraversion, emotional stability and openness to experience are related to uses of social applications on the Internet. Using a national sample of US adults, this study investigated the relationship between these three dimensions of the Big-Five model and social media use (defined as use of social networking sites and instant messages). It also examined whether gender and age played a role in that dynamic. Results revealed that while extraversion and openness to experiences were positively related to social media use, emotional stability was a negative predictor, controlling for socio-demographics and life satisfaction. These findings differed by gender and age. While extraverted men and women were both likely to be more frequent users of social media tools, only the men with greater degrees of emotional instability were more regular users. The relationship between extraversion and social media use was particularly important among the young adult cohort. Conversely, being open to new experiences emerged as an important personality predictor of social media use for the more mature segment of the sample.     

How heterogeneous community engage newcomers? The effect of community diversity on newcomers’ perception of inclusion: An empirical study in social media service

Online communities that provide social media services need to engage newcomers so as to not lose them to competitors. This study examines the role of community diversity (in terms of perceived visible dissimilarity, perceived informational dissimilarity and perceived value dissimilarity) in influencing perceived inclusion of newcomers in the online community and the influence of such perception on newcomers’ engagement intention. The theoretical background on perceived inclusion is obtained from the optimal distinctiveness theory, which comprises of two dimensions, namely, social identification and perceived uniqueness. The results support the multiple roles of community diversity on a newcomer’s perceived inclusion. The findings of this study contribute to a better understanding of the effect of community diversity on newcomers’ engagement behavior, and provide recommendations on designing a personalized community diversity environment.     

How good are clinical MEDLINE searches? A comparative study of clinical end-user and librarian searches

The objective of this study was to determine the quality of MEDLINE searches done by physicians, physician trainees, and expert searchers (clinicians and librarians). Its design was an analytic survey with independent replication in a setting of self-service online searching from medical wards, an intensive care unit, a coronary care unit, an emergency room, and an ambulatory clinic in a 300-bed teaching hospital. Participating were all M.D. clinical clerks, house, and attending staff responsible for patients in the above settings. Intervention for all participants consisted of a 2-h small group class and 1-h practice session on MEDLINE searching (GRATEFUL MED) before free access to MEDLINE. Search questions from 104 randomly selected novice searches were given to 1 of 13 clinicians with prior search experience and 1 of 3 librarians to run independent searches (triplicated searches). Measurements and main results from these unique citations of the triplicated searches were sent to expert clinicians to rate for relevance (7-point scale). Recall (number of relevant citations retrieved from an individual search divided by the total number of relevant citations from all searches on the same topic) and precision (proportion of relevant citations retrieved in each search) were calculated. Librarians were significantly better than novices for both. Librarians had equivalent recall to, and better precision than, experienced end-users. Unexpectedly, only 20% of relevant citations were retrieved by more than one search of the set of three, with the conclusion that novice searchers on MEDLINE via GRATEFUL MED after brief training have relatively low recall and precision. Recall improves with experience but precision remains suboptimal. Further research is needed to determine the "learning curve," evaluate training interventions, and explore the non-overlapping retrieval of relevant citations by different searchers.     

How are UML class diagrams built in practice? A usability study of two UML tools: Magicdraw and Papyrus

Software modeling is a key activity in software development, especially when following any kind of Model Driven Software Engineering (MDSE) process. In this context, standard modeling languages, like the Unified Modeling Language (UML), and tools for supporting the modeling activities become essential.The aim of this study is to analyze how modelers build UML models and how good modeling tools are in supporting this task. Our goal is to draw some useful lessons that help to improve the (UML) modeling process both by recommending changes on the tools themselves and on how UML is taught so that theory and practice of UML modeling are better aligned.Our study employs two research approaches. The main one is an empirical experiment (which analyzes screen recordings registered by undergraduate students during the construction of a UML class diagram). An analytical analysis complements the previous experiment. The study focuses on the most frequent type of UML diagram, the class diagram, and on two tools widely used by the modeling community: MagicDraw and Papyrus.     

A study on the relationships between different presentation modes of graphical icons and users’ attention

With the vigorous development of applications (App), graphical user interfaces (GUI) have been widely found in computers and handheld devices. This study aimed to explore the relationships between different presentation modes of graphical icons and users’ attention. An eye tracker was employed to measure each participant’s experimental data; in addition, subjective evaluation of attention was conducted. Thus, the optimum presentation mode attracting the most attention might be determined. The experiment was designed to investigate two variables: icon composition and background. Through permutation and combination, six presentation modes were obtained as follows: line + positive background (M1), plane + positive background (M2), line + negative background (M3), plane + negative background (M4), line + no background (M5), and plane + no background (M6). Thirty-six participants were requested to view thirty stimuli, or the contour drawings of graphical icons, presented simultaneously in six modes mentioned above. The participants’ fixation duration, fixation frequency, and subjective evaluation of attention were analyzed through two-way ANOVA. The analytical results showed that in terms of the three performance indicators above, M4 performed the best among the six presentation modes. Moreover, regarding icon composition, planes performed better than lines in terms of the three performance indicators. As for background, negative background performed the best in terms of the three performance indicators, positive background ranked second, and no background performed the worst. The findings can serve as a reference when icons are researched or designed in the future.     

Facebook or Renren? A comparative study of social networking site use and social capital among Chinese international students in the United States

Social networking sites (SNSs) are important tools for college students to maintain and develop social capital. Yet, few studies on the social implications of using SNSs have focused on international students and their use of different social media platforms for social capital. This study aims to fill this gap by examining the implications of using host country and home country SNSs for social capital among Chinese international students in the United States. A survey of Chinese international students at a large public university (N = 210) reveals that both Facebook and Renren use are positively associated with bridging social capital but not with bonding social capital. Facebook use has a stronger relationship with bridging social capital than does Renren use. Yet, only Renren use has a significant and positive relationship with maintaining home country social capital. These results have practical implications for international students to develop different types of social capital through different social media platforms.     

What are the characteristics of popular APIs? A large-scale study on Java,Android, and 165 libraries

Software systems are commonly implemented with the support of libraries, which provide features via APIs. Ideally, APIs should have some characteristics, for example, they should be well documented and stable so that client systems can confidently rely on them. However, not all APIs are equal in number of clients: while some APIs are very popular and used worldwide, other may face much lower usage rates. In this context, one question appears: are there particular characteristics that differentiate popular APIs from ordinary APIs? Answering this question can uncover how worldwide APIs are actually implemented and maintained, revealing practices to better support both research and development on APIs. In this paper, we assess the characteristics of popular APIs, including their size, legibility, documentation, stability, and client adoption. We analyze 1491 APIs provided by Java, Android, and 165 libraries. We detect that popular APIs are distinct from ordinary ones, for example, often, popular APIs are larger, have more comments, and are more unstable than ordinary APIs. Finally, we provide a set of lessons learned from the popular APIs on factors that developers can control, such as the exposure of public methods and the API stability.