Collective behavior learning by differentiating personal preference from peer influence

Zhang, Zan; Liu, Lin; Wang, Hao; Li, Jiuyong; Hu, Daning; Yan, Jiaqi; Algesheimer, René; Meierer, Markus

doi:10.1016/j.knosys.2018.06.027

Cited by 7 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Identitybased trust consists of emotional bonds between individuals. In trust relationships, people believe in the intrinsic virtue of such relationships and express genuine care and concern for the welfare of their partners (McAllister, 1995;Zhang et al, 2018). In such cases, people can develop strong inter-relationships and shared identities that will enable them to work together and create collective strengths.…”

Section: Identity-based Trustmentioning

confidence: 99%

Why do users continually seek knowledge in online Q&A communities? An empirical investigation

Jin

Zhang

Yan

2022

IDD

View full text Add to dashboard Cite

Purpose Online Q&A communities have been widely highlighted as an important knowledge exchange market. Although motivations for users’ initial knowledge-seeking behavior have been widely investigated, the factors that affect online Q&A users’ continued knowledge-seeking behavior are still vague. This study aims to investigate the factors that affect users continuously seeking knowledge from online social Q&A communities. Design/methodology/approach Based on social information processing theory, social capital theory, social exchange theory and social cognitive theory, this study used a negative binomial regression model to explore what would affect people’s continued knowledge-seeking behavior. Empirical data was collected from a popular Chinese online social Q&A community. Findings The results indicate that while previous knowledge sharing behavior, peer responses for previous seeking behavior, identity-based trust have a positive impact on knowledge-seeking behaviors, social exposure has a negative impact. In addition, self-presentation negatively moderates the relationship between social exposure and knowledge-seeking behavior. Originality/value This study contributed to the theoretical basis for knowledge-seeking behavior in online Q&A communities. The research findings can be used to derive guidelines for the development and operation of online social Q&A communities.

show abstract

Section: Identity-based Trustmentioning

confidence: 99%

Why do users continually seek knowledge in online Q&A communities? An empirical investigation

Jin

Zhang

Yan

2022

IDD

View full text Add to dashboard Cite

show abstract

“…According to Zhang et al (2018), the influence of peers is influenced by the surrounding factors. The pinnacle of peer influence happens at fourteen years old during which the surrounding affects their life's actions.…”

Section: Peer Influencementioning

confidence: 99%

Facebook Live: How It Affects the Purchase Intention of Generation Y in Malaysia?

Lim

Mohamad

et al. 2022

JBMA

View full text Add to dashboard Cite

Today, people use social media for communicating and browsing the internet during their spare time. Additionally, people are using social media as a means of leisure during their free time. When Facebook launched its Facebook Live streaming application in 2016, the phenomenon created new opportunities for marketers. Recently, Facebook Live streaming is getting popular among companies in promoting their products and services. This research aims to investigate the factors that influence consumers’ purchase intention using Facebook Live streaming. The dependent variable of this study is the purchase intention whereas the independent variable is the attitude towards the broadcasters, interactivity, peer influence, perceived risk and product quality. There were 200 Generation Y respondents from whom information was collected via Facebook using a questionnaire. The result of the study showed that attitude and peer influence affect the consumer purchase intention when watching Facebook Live. This study gives marketers insight into improving their strategies in influencing consumer purchase intention when using Facebook Live streaming.

show abstract

“…Optimization of ML strategies and adaptation to cell motility investigation need the identification of the correct learning examples. Differently from other social contexts (10,11), none of the cells and related trajectories can be judged by experts, both because it cannot be practically done and because the heterogeneity of cell behavior and the massive number of cells make it impossible to extract the "truth" at sight. Because the acquired samples (cells) are not labeled by experts, cell trajectories would directly inherit the same label assigned to the entire experiment, i.e., cells moving in a control experiment would be assumed to behave in a unique, similar way.…”

Section: Introductionmentioning

confidence: 99%

“…In in vitro experiments, cells naturally cluster before reaching the confluence; consensus strategies can be exploited to acquire a unique decision for the cluster. In this regard, we applied two distinct cooperative learning criteria, inspired by collective phenomena and peer influence studies (11); on the one hand, we applied a majority voting procedure to all the labels assigned by the classifier to the cell trajectories selected for that cluster; on the other, we summed up all the scores assigned to each category of the cells belonging to the same cluster and assigned the class with the largest total score to the cluster. We refer to the two criteria as majority voting criterion (maj-vot) and maximum trustiness criterion (max-trust).…”

Section: Introductionmentioning

confidence: 99%

Deciphering Cancer Cell Behavior From Motility and Shape Features: Peer Prediction and Dynamic Selection to Support Cancer Diagnosis and Therapy

et al. 2020

View full text Add to dashboard Cite

Cell motility varies according to intrinsic features and microenvironmental stimuli, being a signature of underlying biological phenomena. The heterogeneity in cell response, due to multilevel cell diversity especially relevant in cancer, poses a challenge in identifying the biological scenario from cell trajectories. We propose here a novel peer prediction strategy among cell trajectories, deciphering cell state (tumor vs. nontumor), tumor stage, and response to the anticancer drug etoposide, based on morphology and motility features, solving the strong heterogeneity of individual cell properties. The proposed approach first barcodes cell trajectories, then automatically selects the good ones for optimal model construction (good teacher and test sample selection), and finally extracts a collective response from the heterogeneous populations via cooperative learning approaches, discriminating with high accuracy prostate noncancer vs. cancer cells of high vs. low malignancy. Comparison with standard classification methods validates our approach, which therefore represents a promising tool for addressing clinically relevant issues in cancer diagnosis and therapy, e.g., detection of potentially metastatic cells and anticancer drug screening.

show abstract

Collective behavior learning by differentiating personal preference from peer influence

Cited by 7 publications

References 20 publications

Why do users continually seek knowledge in online Q&A communities? An empirical investigation

Why do users continually seek knowledge in online Q&A communities? An empirical investigation

Facebook Live: How It Affects the Purchase Intention of Generation Y in Malaysia?

Deciphering Cancer Cell Behavior From Motility and Shape Features: Peer Prediction and Dynamic Selection to Support Cancer Diagnosis and Therapy

Contact Info

Product

Resources

About