A temporal graph framework for intelligence extraction in social media networks

2023 | Information & Management | Citations: 0

Authors: Chung, Wingyan; Lai, Vincent S.

Abstract: Social media networks (SMNs) are increasingly used in professional management of ... Expand

Abstract: Social media networks (SMNs) are increasingly used in professional management of knowledge workers and related assets. However, the factors affecting behavioral trends and activity levels in these networks are not well understood. Although social and cognitive theories can help to explain human behavior in traditional social networks, their application to SMNs has not been validated. Traditional social network modeling techniques may not accurately predict real-world SMN activities. This research developed a temporal graph framework for in­ telligence extraction in SMNs. Theory-based, data-driven models (Conformity Model (COM), Recency-Primacy Model (REM), Trend Interaction Model (TIM), Periodic Interaction Model (PIM)) were developed based on the framework to capture various aspects of user behavior: conformity effect, recency, primacy, periodicity, and dynamic trend. The models capture the activity history and dynamically combine pricing information to enhance predictive accuracy. Using data of 83,536 GitHub software repositories on cryptocurrency, this article reports the results of experiments that compare the models’ performance in predicting SMN activities over time. Experi­ mental results show that the model (REM) that captures recency/primacy effects of human cognitive processing outperformed other models in 9 (out of 18) measures pertaining to engagement, contribution, influence, and popularity. Primacy plays a dominant role in predicting engagement, contribution, and popularity, whereas recency plays a key role in predicting influence. Short-term trend (modeled with TIM) was found to yield significantly better performance on predicting user contribution. The models also outperformed an integrated machine learning (IML) model by most measures. Overall, the effects modeled by REM and TIM were found to be more significant than the effects modeled by COM, PIM, and IML. The research contributes to enhancing un­ derstanding of SMN behavior, developing new models to simulate and predict SMN activities, and designing new artifacts for information systems practitioners to manage knowledge assets and to extract SMN intelligence. Collapse

Topics: cryptocurrency social network systems development situation awareness user behavior

Methods: experiment machine learning longitudinal research computational algorithm time series analysis

Theories: psychological theory social contagion theory social interactionist theory social impact theory social sciences theory

Evolution of Referrals over Customers’ Life Cycle: Evidence from a Ride-Sharing Platform

2023 | Information Systems Research | Citations: 0

Authors: Fernández-Loría, Carlos; Cohen, Maxime C.; Ghose, Anindya

Abstract: Online platforms often ask their users to refer friends in exchange for a reward ... Expand

Abstract: Online platforms often ask their users to refer friends in exchange for a reward. This paper addresses how referral generation and referral value evolve throughout the customer’s life cycle as a function of service usage, experience level, and past referral behavior. Our analysis is based on a longitudinal data set that comprises the transactions and referral actions of 400,000 users in a ride-sharing platform over a year. The richness of our data set allows us to address two shortcomings from previous studies: modeling dynamic behavior (i.e., the relationship between past and future referrals) and accounting for unobserved heterogeneity across users. Our results show that users make more referrals when they have used the service recently and intensively. For example, users become 9% less likely to make referrals for each week they have not used the service. Furthermore, users make more high-value referrals as they become more experienced with the service. The referral generation and referral value of the top 10% most experienced users are more than 18% higher relative to when they first used the service. Finally, as users make more referrals, they become more likely to run out of friends to whom they can refer the service, leading to less referrals in the future. After users make their first referral, the probability of making additional referrals decreases by more than 78% and the value of subsequent referrals reduces by 19% on average. The results imply that platforms should consider tailoring their referral programs according to how referral generation and referral value evolve over time.History: Xiaoquan (Michael) Zhang, Senior Editor; Khim Yong Goh, Associate Editor. Collapse

Topics: ride sharing platform mobile application logistics management accounting marketing management

Methods: longitudinal research robustness check instrumental variables estimation regression analysis method Poisson regression

Theories: social contagion theory

Unintended Emotional Effects of Online Health Communities: A Text Mining-Supported Empirical Study

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Zhou, Jiaqi; Zhang, Qingpeng; Zhou, Sijia; Li, Xin; Zhang, Xiaoquan (Michael)

Abstract: Online health communities (OHCs) play an important role in enabling patients to ... Expand

Abstract: Online health communities (OHCs) play an important role in enabling patients to exchange information and obtain social support from each other. However, do OHC interactions always benefit patients? In this research, we investigate different mechanisms by which OHC content may affect patients' emotions. Specifically, we notice users can read not only emotional support intended to help them but also emotional support targeting other persons or posts that are not intended to generate any emotional support (auxiliary content). Drawing from emotional contagion theories, we argue that even though emotional support may benefit targeted support seekers, it could have a negative impact on the emotions of other support seekers. Our empirical study on an OHC for depression patients supports these arguments. Our findings are new to the literature and have critical practical implications since they suggest that we should carefully manage OHC-based interventions for depression patients to avoid unintended consequences. We design a novel deep learning model to differentiate emotional support from auxiliary content. Such differentiation is critical for identifying the negative effect of emotional support on unintended recipients. We also discuss options to alter the intervention volume, length, and frequency to tackle the challenge of the negative effect. Collapse

Topics: web forum website application programming interface web page online community

Methods: machine learning deep learning robustness check instrumental variables estimation statistical hypothesis test

Theories: social contagion theory appraisal theory

Investigating Churn in Physical Activity Challenges: Evidence from a U.S. Online Social Network

2023 | HICSS | Citations: 0

Authors: Zhu, Y.; Mani, A.

Abstract: Physical activities have been found to be positively contagious, as active exer ... Expand

Abstract: Physical activities have been found to be positively contagious, as active exercisers tend to motivate their friends to do more exercise. However, it is not clearly understood if inactive exercising behaviors are also socially contagious. As insufficient physical activity is a huge threat to people's health, understanding the potential negative contagion in physical activities is crucial. We approach this problem by studying the effect of individuals' churn of online physical activity challenges relying on the physical activity and a large social network data from a renowned U.S. fitness platform. The underexplored online physical activity challenges provide a natural setup to measure churn and opportunities to study the contagion heterogeneities. Consistent with previous findings, we confirm that physical activity churn is socially contagious. Interestingly, unlike the insideout positive contagion, our analyses reveal that the contagion of churn happens outside-in on the social network. Implications of such findings are discussed. Collapse

Topics: social network accounting social influence

Methods: instrumental variables estimation longitudinal research causality analysis statistical hypothesis test econometric modeling

Theories: social contagion theory

Which voice are you satisfied with? Understanding the physician–patient voice interactions on online health platforms

2022 | Decision Support Systems | Citations: 0

Authors: Liu, Shan; Si, Guangsen; Gao, Baojun

Abstract: Patients are usually sensitive to physicians’ attitude and behavior when physici ... Expand

Abstract: Patients are usually sensitive to physicians’ attitude and behavior when physicians make decisions in patients’ consultations. However, the consequences of physicians’ interactive voices on patients’ perception have rarely been explored. This study develops a multistage online interaction model to explore the effects of the key vocal emotional cues of physician voice on patient-perceived satisfaction. We collect data of over 44,000 voice in­ teractions regarding lung disease from 889 physicians on a leading online health platform. By using the theo­ retical lens of emotional contagion, we find that the voice pitch and intensity of physicians, respectively, positively and negatively affect patient-perceived satisfaction, in turn positively affecting physician economic returns in the postinteraction stage. However, the negative effect of intensity is low for physicians with high recommendation popularity (a factor in the preinteraction stage), suggesting that physician-inherent information has an anchoring effect. These findings not only provide new insights into the literature on online phys­ ician–patient interaction by identifying the novel nonverbal cues of physician voice, their consequent effects, and boundary conditions, but also provide decision support for physicians and platform managers. Collapse

Topics: electronic health decision support Python

Methods: cluster analysis support vector machine descriptive statistic machine learning natural language processing

Theories: social contagion theory

Visual Communication and Fashion Popularity Contagion in Social Networks

2022 | International Conference on Information Systems | Citations: 0

Authors: Li, Xiang; Wang, Yunhui; Junming, Liu; Xiong, Hui

Abstract: Fast fashion has emerged as a prevalent retail strategy shaping fashion popular ... Expand

Abstract: Fast fashion has emerged as a prevalent retail strategy shaping fashion popularity. However, due to the lack of historical records and the dynamics of fashion trends, existing demand prediction methods do not apply to new-season fast fashion sales forecasting. We draw on the Social Contagion Theory to conceptualize a sales prediction framework for fast fashion new releases. We posit that fashion popularity contagion comes from Source Contagion and Media Contagion, which refer to the inherent infectiousness of fashion posts and the popularity diffusion in social networks, respectively. We consider fashion posts as the contagion source that visually attracts social media users with images of fashion products. Graph Convolutional Network is developed to model the dynamic fashion contagion process in the topology structure of social networks. This theory-based deep learning method can incorporate the latest social media activities to offset the deficiency of historical fashion data in new seasons. Collapse

Topics: social media social network electronic commerce

Methods: convolutional neural network image processing theory development deep learning longitudinal research

Theories: social contagion theory

Identifying Turnover Contagion in Enterprise Social Networks

2022 | Americas Conference on Information Systems | Citations: 0

Authors: Wei, Xin; Zhang, Xi; Ou, Carol; Zhu, Hengshu

Abstract: Turnover contagion has created salient challenges for companies and society as ... Expand

Abstract: Turnover contagion has created salient challenges for companies and society as turnover itself causes more turnover. Technically, due to the nonlinear growth of overall turnover rate within a short time, turnover is difficult to accurately predict. As a result, predicting and managing turnover contagion have become key issues in people analytics systems. However, existing studies on turnover contagion has primarily focused on its consequence such as time-lagged turnover, while how to identify turnover contagion effect and leverage it to improve the interpretability of turnover prediction algorithm remains under explored. Building upon the behavioral contagion theory, this research-in-progress paper proposes using machine learning method to calculate the turnover contagion effect based on the susceptible-infective epidemic model. This study lays a theoretical foundation to leverage social network data to examine turnover contagion, and practically contributes to managerial practice in designing turnover prediction systems for both efficiency and interpretability. KeywordsTurnover contagion, contagion effect, social network, behavioral contagion, epidemic model. Collapse

Topics: social network pandemic innovation management enterprise social network IT personell turnover

Methods: computational algorithm machine learning method machine learning design science social network analysis

Theories: social contagion theory

Factors influencing consumer purchase behavior toward live streaming commerce

2021 | Americas Conference on Information Systems | Citations: 0

Authors: Hsieh, Yen-Hao; Zhuo, XinYun

Abstract: ... Expand

Abstract: Collapse

Topics: live streaming platform electronic commerce social influence

Theories: social contagion theory

Impact of Incentive Mechanism in Online Referral Programs: Evidence from Randomized Field Experiments

2021 | Journal of Management Information Systems | Citations: 8

Authors: Jung, Jaehwuen; Bapna, Ravi; Gupta, Alok; Sen, Soumya

Abstract: Despite the growing popularity of online referral programs, a minimal amount is ... Expand

Abstract: Despite the growing popularity of online referral programs, a minimal amount is known regarding the theoretical foundations that drive the key actions associated with successful referrals. In this paper, we study which type of referral reward structure is most effective in maximizing word-of-mouth by conducting two randomized experiments in mobile gaming context. Specifically, we examine the effect of three incentive schemes: selfish reward (inviter gets all the reward), equal-split reward (50-50 split), and generous reward (invitee gets all the reward). Consistent across the two experiments, we find that pro-social referral incentive schemes, namely the equal-split and generous schemes, tend to dominate purely selfish schemes in creating WOM. Our mechanism-level analysis shows that both equal-split and generous schemes result in higher number of conversions by significantly increasing the invitee's likelihood to accept referrals, which we further show that is partially due to selective and better targeted referrals. Our results contribute to the understanding of the optimal design of online referral programs and provide important implications for designing effective referral reward schemes in the digital world. Collapse

Topics: mobile application mobile system mobile game word of mouth online word of mouth

Methods: experiment experimental group randomized field experiment field experiment Poisson regression

Theories: social contagion theory

A Beyond the Dominant Paradigm Model for Examining Adoption of Big Data

2021 | Americas Conference on Information Systems | Citations: 0

Authors: Kibria, Md Golam; Joreimi, Golnoush (Julie); Paghadal, Vatsal Keshavbhai; Ghosh, Suvankar

Abstract: Companies have been investing in Big Data Analytics for several years since the ... Expand

Abstract: Companies have been investing in Big Data Analytics for several years since the emergence of this phenomenon. While their Big Data Analytics investments have undoubtedly brought benefits to firms as they have gained insightful knowledge from the large amounts of data they have been collecting and analyzing, there are concerns about whether firms are deriving the value they thought they would be getting from their Big Data investments. We develop a model of technology adoption that examines the role of drivers such as social contagion and management fashion in Big Data Analytics adoption. In addition to building a theoretical model of adoption for Big Data Analytics that goes beyond the dominant paradigm, we apply our model using a reflective methodology where we examine if there is a gap between the perceptions of value that existed when firms started out with investing in Big Data Analytics and their perceptions today. This is an innovative paper which brings out aspects of Big Data Analytics adoption that has not been examined before. Collapse

Topics: big data technology adoption social influence mindfulness business topic

Methods: literature study theory development

Theories: social contagion theory unified theory of acceptance and use of technology